From 3f40e96217418590ca66af6912f595cc04425849 Mon Sep 17 00:00:00 2001 From: lian-manonog Date: Mon, 19 Aug 2024 15:52:14 +0100 Subject: wip: setting up test files for transform_lambda --- src/transform_lambda.py | 9 +++++++++ tests/test_transform_lambda.py | 1 + 2 files changed, 10 insertions(+) create mode 100644 tests/test_transform_lambda.py diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 6ee681f..7c29df9 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -1,2 +1,11 @@ +import boto3 +import csv +from botocore.exceptions import ClientError +import logging +import json +from datetime import datetime +import re + + def lambda_handler(): pass \ No newline at end of file diff --git a/tests/test_transform_lambda.py b/tests/test_transform_lambda.py new file mode 100644 index 0000000..dd08b6a --- /dev/null +++ b/tests/test_transform_lambda.py @@ -0,0 +1 @@ +from src.transform_lambda import lambda_handler \ No newline at end of file -- cgit v1.2.3 From 29eace351c8e35d104992119a3762ab07be1f95d Mon Sep 17 00:00:00 2001 From: lian-manonog Date: Mon, 19 Aug 2024 16:49:06 +0100 Subject: wip: added read_csb functionailty to lambda_handler --- src/transform_lambda.py | 40 ++++++++++++++++++++++++++++++++-------- 1 file changed, 32 insertions(+), 8 deletions(-) diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 7c29df9..f62f1d4 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -1,11 +1,35 @@ -import boto3 -import csv -from botocore.exceptions import ClientError -import logging import json -from datetime import datetime -import re +import boto3 +import io +from io import StringIO +import pandas as pd + + +##add trigger window from extract bucket (on console?) +##suffix: must .csv --> reads only this file type that is uploaded to extract +##In-order to use PANDAS module in lambda function, a Lambda Layer needs to be attached to the AWS Lambda Function. +##need a function that normalises the data + + +s3_client = boto3.client('s3') +def lambda_handler(event, context): + try: + s3_bucket_name = event["Records"][0]["s3"]["bucket"]["name"] + s3_file_name = event["Records"][0]["s3"]["object"]["key"] + + object = s3_client.get_object(Bucket=s3_bucket_name, Key=s3_file_name) + body = object['Body'] + csv_string = body.read().decode('utf-8') + dataframe = pd.read_csv(StringIO(csv_string)) ##this is the streaming body + + print(dataframe.head(3)) -def lambda_handler(): - pass \ No newline at end of file + except Exception as err: + print(err) + + # TODO implement + return { + 'statusCode': 200, + 'body': json.dumps('') + } \ No newline at end of file -- cgit v1.2.3 From 687eaa762bb598c61e2385dc0462d7375f86f779 Mon Sep 17 00:00:00 2001 From: lian-manonog Date: Tue, 20 Aug 2024 19:58:15 +0100 Subject: wip: writing pseudocode logic for the lambda_handler --- src/transform_lambda.py | 36 ++++++++++++++++++++++-------------- 1 file changed, 22 insertions(+), 14 deletions(-) diff --git a/src/transform_lambda.py b/src/transform_lambda.py index f62f1d4..2a97931 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -1,35 +1,43 @@ import json import boto3 +import re import io from io import StringIO import pandas as pd - ##add trigger window from extract bucket (on console?) ##suffix: must .csv --> reads only this file type that is uploaded to extract ##In-order to use PANDAS module in lambda function, a Lambda Layer needs to be attached to the AWS Lambda Function. ##need a function that normalises the data -s3_client = boto3.client('s3') + +s3_resource = boto3.resource('s3') ##need this for a way of reuploading data after transformation def lambda_handler(event, context): + s3_client = boto3.client('s3') + + # tables = ['sales_order', + # 'transaction', + # 'payment', + # 'counterparty', + # 'address', + # 'staff', + # 'purchase_order', + # 'department', + # 'currency', + # 'design', + # 'payment_type'] try: s3_bucket_name = event["Records"][0]["s3"]["bucket"]["name"] s3_file_name = event["Records"][0]["s3"]["object"]["key"] - + + ## concatanating the file per table - most recent + ## iterate through the subfolders + ## table name prefix to iterate through the files written to that table + object = s3_client.get_object(Bucket=s3_bucket_name, Key=s3_file_name) body = object['Body'] csv_string = body.read().decode('utf-8') dataframe = pd.read_csv(StringIO(csv_string)) ##this is the streaming body - - print(dataframe.head(3)) - - except Exception as err: - print(err) - - # TODO implement - return { - 'statusCode': 200, - 'body': json.dumps('') - } \ No newline at end of file + \ No newline at end of file -- cgit v1.2.3 From 8a67c688b402fae27d47399b3ae04cc8475f82b7 Mon Sep 17 00:00:00 2001 From: lian-manonog Date: Tue, 20 Aug 2024 21:12:11 +0100 Subject: wip: just more pseudocode --- src/transform_lambda.py | 38 ++++++++++++++++++++++++++------------ 1 file changed, 26 insertions(+), 12 deletions(-) diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 2a97931..900bf4b 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -17,17 +17,17 @@ s3_resource = boto3.resource('s3') ##need this for a way of reuploading data aft def lambda_handler(event, context): s3_client = boto3.client('s3') - # tables = ['sales_order', - # 'transaction', - # 'payment', - # 'counterparty', - # 'address', - # 'staff', - # 'purchase_order', - # 'department', - # 'currency', - # 'design', - # 'payment_type'] + tables = ['sales_order', + 'transaction', + 'payment', + 'counterparty', + 'address', + 'staff', + 'purchase_order', + 'department', + 'currency', + 'design', + 'payment_type'] try: s3_bucket_name = event["Records"][0]["s3"]["bucket"]["name"] s3_file_name = event["Records"][0]["s3"]["object"]["key"] @@ -40,4 +40,18 @@ def lambda_handler(event, context): body = object['Body'] csv_string = body.read().decode('utf-8') dataframe = pd.read_csv(StringIO(csv_string)) ##this is the streaming body - \ No newline at end of file + + print(dataframe.head(3)) + + except Exception as err: + print(err) + + # TODO implement + return { + 'statusCode': 200, + 'body': json.dumps('') + } + +## each csv file must be converted into a pandas df +## done via read_csv, where stringIO creates an file-like-object from string - treats string like a file: as file is not physically stored in file +## each file needs its own panda df (?) to be normalised \ No newline at end of file -- cgit v1.2.3 From ad19a8bac6ad0411e3c2c2530b0ca6ee1541d072 Mon Sep 17 00:00:00 2001 From: Alex Date: Tue, 20 Aug 2024 22:51:05 +0100 Subject: chore: rm workflow file from development --- .github/workflows/deploy.yml | 43 ------------------------------------------- 1 file changed, 43 deletions(-) delete mode 100644 .github/workflows/deploy.yml diff --git a/.github/workflows/deploy.yml b/.github/workflows/deploy.yml deleted file mode 100644 index 09b8490..0000000 --- a/.github/workflows/deploy.yml +++ /dev/null @@ -1,43 +0,0 @@ -name: deploy-terraform - -on: - pull_request: - branches: - - main - push: - branches: - - main - - -jobs: - deploy-terraform: - if: github.ref == 'refs/heads/main' - name: Deploy Terraform - runs-on: ubuntu-latest - #needs: run-checks (must ref on-commit.yml file) - environment: production - steps: - - name: Checkout Repo - uses: actions/checkout@v4 - - - name: Install Terraform - uses: hashicorp/setup-terraform@v3 - - - name: Configure AWS Credentials - uses: aws-actions/configure-aws-credentials@v4 - with: - aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }} - aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }} - aws-region: ${{ secrets.AWS_REGION }} - - - name: Terraform Init - working-directory: terraform - run: terraform init - - - name: Terraform Plan - working-directory: terraform - run: terraform plan - - - name: Terraform Apply - working-directory: terraform - run: terraform apply --auto-approve -- cgit v1.2.3 From f259504a87e24b0dae6f2e06acafdf881d4ec96e Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Tue, 20 Aug 2024 23:01:39 +0100 Subject: test: test trigger for ci/cd --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index cbb446c..7d7e499 100644 --- a/README.md +++ b/README.md @@ -21,7 +21,7 @@ The solution showcases our skills in: - Amazon Web Services (AWS) - Agile methodologies -# Main Objective +# Main Objectives Our goal is to create a reliable ETL (Extract, Transform, Load) pipeline that can: @@ -48,4 +48,4 @@ others. TBA # Contributors -TBA \ No newline at end of file +TBA -- cgit v1.2.3 From 9511ac7958efcadad6cd1323027674988042bee9 Mon Sep 17 00:00:00 2001 From: Alex Date: Tue, 20 Aug 2024 23:09:46 +0100 Subject: ci: create dev-tests.yml --- .github/workflows/dev-tests.yml | 49 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) create mode 100644 .github/workflows/dev-tests.yml diff --git a/.github/workflows/dev-tests.yml b/.github/workflows/dev-tests.yml new file mode 100644 index 0000000..9f71515 --- /dev/null +++ b/.github/workflows/dev-tests.yml @@ -0,0 +1,49 @@ +name: dev-tests + +on: + pull_request: + branches: + - development + push: + branches: + - development + +jobs: + validate-and-test: + name: Validate Terraform and Run Tests + runs-on: ubuntu-latest + environment: testing + steps: + - name: Checkout Repo + uses: actions/checkout@v4 + + - name: Install Terraform + uses: hashicorp/setup-terraform@v3 + + - name: Terraform Init + working-directory: terraform + run: terraform init -backend=false + + - name: Terraform Validate + working-directory: terraform + run: terraform validate + + - name: Set up Python + uses: actions/setup-python@v5 + with: + python-version: '3.11' + + - name: Install Python dependencies + run: | + python -m pip install --upgrade pip + pip install pytest pytest-testdox + pip install -r requirements.txt + + - name: Run pytest + run: pytest tests/ -vvrP --testdox + continue-on-error: true + id: pytest + + - name: Check on failures + if: steps.pytest.outcome == 'failure' + run: exit 1 -- cgit v1.2.3 From 0cf8f2c238c2f86ee6c97ed7b95e78c67d1782b5 Mon Sep 17 00:00:00 2001 From: Alex Date: Tue, 20 Aug 2024 23:13:34 +0100 Subject: ci: remove environment for dev-tests.yml --- .github/workflows/dev-tests.yml | 1 - 1 file changed, 1 deletion(-) diff --git a/.github/workflows/dev-tests.yml b/.github/workflows/dev-tests.yml index 9f71515..d66f1c6 100644 --- a/.github/workflows/dev-tests.yml +++ b/.github/workflows/dev-tests.yml @@ -12,7 +12,6 @@ jobs: validate-and-test: name: Validate Terraform and Run Tests runs-on: ubuntu-latest - environment: testing steps: - name: Checkout Repo uses: actions/checkout@v4 -- cgit v1.2.3 From b4fafcd9731f11f6f2efde843242b9c5cb84e85f Mon Sep 17 00:00:00 2001 From: Ang Bel Date: Wed, 21 Aug 2024 12:50:32 +0100 Subject: function to write files from s3 into a list of dataframes. Current test is failing due to AioClientCreator object has no attribute "_inject_s3_input_parameters" --- requirements.txt | 2 +- src/transform_lambda.py | 34 ++++++++++++++++++++++++++++++---- tests/test_transform_lambda.py | 34 +++++++++++++++++++++++++++++++++- 3 files changed, 64 insertions(+), 6 deletions(-) diff --git a/requirements.txt b/requirements.txt index 6f383f9..087d1c2 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,6 +1,6 @@ asn1crypto==1.5.1 boto3==1.34.159 -botocore==1.34.159 +botocore==1.34.7 certifi==2024.7.4 cffi==1.17.0 charset-normalizer==3.3.2 diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 900bf4b..6f65728 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -1,3 +1,4 @@ +#from src.extract_lambda import extract_bucket import json import boto3 import re @@ -10,9 +11,7 @@ import pandas as pd ##In-order to use PANDAS module in lambda function, a Lambda Layer needs to be attached to the AWS Lambda Function. ##need a function that normalises the data - - -s3_resource = boto3.resource('s3') ##need this for a way of reuploading data after transformation +#s3_resource = boto3.resource('s3') ##need this for a way of reuploading data after transformation def lambda_handler(event, context): s3_client = boto3.client('s3') @@ -54,4 +53,31 @@ def lambda_handler(event, context): ## each csv file must be converted into a pandas df ## done via read_csv, where stringIO creates an file-like-object from string - treats string like a file: as file is not physically stored in file -## each file needs its own panda df (?) to be normalised \ No newline at end of file +## each file needs its own panda df (?) to be normalised +tables = ['sales_order', + 'transaction', + 'payment', + 'counterparty', + 'address', + 'staff', + 'purchase_order', + 'department', + 'currency', + 'design', + 'payment_type'] + +def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client('s3')): + table_dfs = {} + for table in tables: + response = client.list_objects_v2(Bucket=bucket, Prefix=table) + list_of_keys = ['s3://'+object['Key'] for object in response['Contents']] + print(list_of_keys) + list_of_df = [pd.read_csv(key) for key in list_of_keys] + table_dfs[table] = pd.concat(list_of_df) + return table_dfs + # exec("%s = %d" % (table,pd.concat(list_of_df))) + # exec(f"{table} = {pd.concat(list_of_df)}") + # table_dfs = [sales_order, transaction, payment, counterparty, address, + # staff, purchase_order, department, currency, design, payment_type] + + diff --git a/tests/test_transform_lambda.py b/tests/test_transform_lambda.py index dd08b6a..a3ec4a8 100644 --- a/tests/test_transform_lambda.py +++ b/tests/test_transform_lambda.py @@ -1 +1,33 @@ -from src.transform_lambda import lambda_handler \ No newline at end of file +from src.transform_lambda import read_from_s3_subfolder_to_df +from moto import mock_aws +import pytest +import pandas as pd +import os +import boto3 + +@pytest.fixture(scope='class') +def aws_credentials(): + os.environ["AWS_ACCESS_KEY_ID"] = 'testing' + os.environ["AWS_SECRET_ACCESS_KEY"] = 'testing' + os.environ["AWS_SECURIT_TOKEN"] = 'testing' + os.environ["AWS_SESSION_TOKEN"] = 'testing' + os.environ["AWS_DEFAULT_REGION"]= 'eu-west-2' + +@pytest.fixture(scope='class') +def s3_client(aws_credentials): + with mock_aws(): + yield boto3.client('s3') +class TestReadFromS3: + + def test_returns_dictionary_with_correct_value_pair(self,s3_client): + s3_client.create_bucket(Bucket = 'dummy_buc',CreateBucketConfiguration={ + 'LocationConstraint': 'eu-west-2' + }) + s3_client.upload_file('tests/dummy_identical.csv', 'dummy_buc', 'Foods/2024/08/21/Foods_12:03:10.csv') + tables = ['Foods'] + result = read_from_s3_subfolder_to_df(tables,bucket='dummy_buc',client=s3_client) + print(result) + assert isinstance(result,dict) + assert list(result.keys()) == 'Foods' + assert isinstance(result['Foods'],pd.DataFrame) + \ No newline at end of file -- cgit v1.2.3 From da3d85dd2dc515226d16992c5f63b2a8b02a0a38 Mon Sep 17 00:00:00 2001 From: Ellie Date: Wed, 21 Aug 2024 13:41:01 +0100 Subject: add dim tables: design, staff, currency, location (wip) --- src/fact-sales-order.py | 54 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) create mode 100644 src/fact-sales-order.py diff --git a/src/fact-sales-order.py b/src/fact-sales-order.py new file mode 100644 index 0000000..a143889 --- /dev/null +++ b/src/fact-sales-order.py @@ -0,0 +1,54 @@ +import pandas as pd +from src.transform_lambda import get_dataframes + +dict_of_df = get_dataframes() # {"design": "design dataframe", "address": "address dataframe", ....} + + +# iterates through each dataframe in the list of dataframes and assigns them to a variable +df_design = dict_of_df[design] +df_currency = dict_of_df[currency] +df_address = dict_of_df[address] +df_staff = dict_of_df[staff] +df_department = dict_of_df[department] +df_counterparty = dict_of_df[counterparty] + + +# creates the dim_design dataframe +dim_design = df_design["design_id", "design_name", "file_name", "file_location"] + +# creates the dim_staff dataframe +staff_department = pd.merge(df_staff, df_department, on='department_id', how="outer") +dim_staff = staff_department['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address'] + +# creates the dim_currency dataframe +# currency names currently hardcoded and not taken from database, is this viable/how else to do this? +d = {"currency_id": [1, 2, 3], "currency_code": ["GBP", "USD", "EUR"], "currency_name": ["Pound", "US Dollar", "Euro"]} +currency_names = pd.DataFrame(data=d) +join_currency = pd.merge(df_currency, currency_names, on="currency_name", how="outer") +dim_currency = join_currency["currency_id", "currency_code", "currency_name"] + +# creates the dim_location dataframe +# need to change address id to location id +"dim_location dataframe: (location_id, address_line_1, address_line_2, district, city, postal code, country, phone)" +dim_location = df_address["address_id", "address_line_1", "address_line_2", "district", "city", "postal_code" "country", "phone"] + + + + + + + + + +# creates the dim_counterparty dataframe +# counterparty_address = pd.merge(df_counterparty, df_address, left_on="legal_address_id", right_on='address_id', how="outer") + +# dim_counterparty = df_counterparty["counterparty_id", "counterparty_legal_name", "counterparty_legal_address_line_1", +# "counterparty_legal_address_line_2", "counterparty_legal_district", "counterpart_legal_city", +# "counterparty_legal_postal_code", "counterparty_legal_country", "counterparty_legal_phone_number"] + + +# TO DO: +# dim_location +# dim_date +# fact_sales_order \ No newline at end of file -- cgit v1.2.3 From 562fac411ce0bedf3dbf067390cacef89ef47981 Mon Sep 17 00:00:00 2001 From: lian-manonog Date: Wed, 21 Aug 2024 14:18:23 +0100 Subject: wip: updated requirements --- requirements.txt | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/requirements.txt b/requirements.txt index 087d1c2..62ebbf4 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,6 +1,6 @@ asn1crypto==1.5.1 -boto3==1.34.159 -botocore==1.34.7 +boto3 +botocore certifi==2024.7.4 cffi==1.17.0 charset-normalizer==3.3.2 @@ -27,4 +27,6 @@ scramp==1.4.5 six==1.16.0 urllib3==2.2.2 Werkzeug==3.0.3 -xmltodict==0.13.0 \ No newline at end of file +xmltodict==0.13.0 +s3fs +pandas \ No newline at end of file -- cgit v1.2.3 From 0c6e2f8486d1ec4d9b0bd4984e01baca3a159df0 Mon Sep 17 00:00:00 2001 From: Ang Bel Date: Wed, 21 Aug 2024 15:07:51 +0100 Subject: (tests) Read from s3 to df passes --- src/transform_lambda.py | 26 ++++---------------------- tests/dummy_2.csv | 5 +++++ tests/test_transform_lambda.py | 21 +++++++++++++++++++-- 3 files changed, 28 insertions(+), 24 deletions(-) create mode 100644 tests/dummy_2.csv diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 6f65728..ea4e16f 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -15,18 +15,6 @@ import pandas as pd def lambda_handler(event, context): s3_client = boto3.client('s3') - - tables = ['sales_order', - 'transaction', - 'payment', - 'counterparty', - 'address', - 'staff', - 'purchase_order', - 'department', - 'currency', - 'design', - 'payment_type'] try: s3_bucket_name = event["Records"][0]["s3"]["bucket"]["name"] s3_file_name = event["Records"][0]["s3"]["object"]["key"] @@ -51,9 +39,8 @@ def lambda_handler(event, context): 'body': json.dumps('') } -## each csv file must be converted into a pandas df -## done via read_csv, where stringIO creates an file-like-object from string - treats string like a file: as file is not physically stored in file -## each file needs its own panda df (?) to be normalised +## Started from fresh on Wed 21st Aug: + tables = ['sales_order', 'transaction', 'payment', @@ -70,14 +57,9 @@ def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client('s3')): table_dfs = {} for table in tables: response = client.list_objects_v2(Bucket=bucket, Prefix=table) - list_of_keys = ['s3://'+object['Key'] for object in response['Contents']] - print(list_of_keys) + list_of_keys = ['s3://'+bucket+'/'+object['Key'] for object in response['Contents']] list_of_df = [pd.read_csv(key) for key in list_of_keys] table_dfs[table] = pd.concat(list_of_df) return table_dfs - # exec("%s = %d" % (table,pd.concat(list_of_df))) - # exec(f"{table} = {pd.concat(list_of_df)}") - # table_dfs = [sales_order, transaction, payment, counterparty, address, - # staff, purchase_order, department, currency, design, payment_type] - + diff --git a/tests/dummy_2.csv b/tests/dummy_2.csv new file mode 100644 index 0000000..8abc9bf --- /dev/null +++ b/tests/dummy_2.csv @@ -0,0 +1,5 @@ +Car_type,Brand,Colour +Truck,Chevrolet,Grey +Convertible,Mercedes,Red +Van,Volkswagen,Blue + diff --git a/tests/test_transform_lambda.py b/tests/test_transform_lambda.py index a3ec4a8..7de1bf3 100644 --- a/tests/test_transform_lambda.py +++ b/tests/test_transform_lambda.py @@ -4,6 +4,7 @@ import pytest import pandas as pd import os import boto3 +import numpy as np @pytest.fixture(scope='class') def aws_credentials(): @@ -27,7 +28,23 @@ class TestReadFromS3: tables = ['Foods'] result = read_from_s3_subfolder_to_df(tables,bucket='dummy_buc',client=s3_client) print(result) + expected_df = pd.DataFrame(np.array([['Vegetable', 'Sour', 'Green'], ['Berry', 'Sweet', 'Red']]), + columns=['Food_type', 'Flavour', 'Colour']) assert isinstance(result,dict) - assert list(result.keys()) == 'Foods' + assert list(result.keys())[0] == 'Foods' assert isinstance(result['Foods'],pd.DataFrame) - \ No newline at end of file + assert result['Foods'].eq(expected_df,axis='columns').all(axis=None) + + def test_returns_dictionary_of_dataframes_for_multiple_tables(self,s3_client): + s3_client.upload_file('tests/dummy_2.csv', 'dummy_buc', 'Cars/2024/08/21/Cars_14:03:56.csv') + tables = ['Foods','Cars'] + result = read_from_s3_subfolder_to_df(tables,bucket='dummy_buc',client=s3_client) + expected_foods_df = pd.DataFrame(np.array([['Vegetable', 'Sour', 'Green'], ['Berry', 'Sweet', 'Red']]), + columns=['Food_type', 'Flavour', 'Colour']) + expected_cars_df = pd.DataFrame(np.array([['Truck', 'Chevrolet', 'Grey'], ['Convertible', 'Mercedes','Red'],['Van','Volkswagen','Blue']]), + columns=['Car_type', 'Brand', 'Colour']) + assert list(result.keys()) == tables + assert result['Foods'].eq(expected_foods_df,axis='columns').all(axis=None) + assert result['Cars'].eq(expected_cars_df,axis='columns').all(axis=None) + + -- cgit v1.2.3 From b882bb03882ce91c25880defb1461bfbd09dce43 Mon Sep 17 00:00:00 2001 From: Ang Bel Date: Wed, 21 Aug 2024 15:48:41 +0100 Subject: complete version of read from s3 subfolder --- src/transform_lambda.py | 33 +-------------------------------- 1 file changed, 1 insertion(+), 32 deletions(-) diff --git a/src/transform_lambda.py b/src/transform_lambda.py index ea4e16f..3a7cf43 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -6,40 +6,9 @@ import io from io import StringIO import pandas as pd -##add trigger window from extract bucket (on console?) -##suffix: must .csv --> reads only this file type that is uploaded to extract -##In-order to use PANDAS module in lambda function, a Lambda Layer needs to be attached to the AWS Lambda Function. -##need a function that normalises the data - -#s3_resource = boto3.resource('s3') ##need this for a way of reuploading data after transformation - def lambda_handler(event, context): - s3_client = boto3.client('s3') - try: - s3_bucket_name = event["Records"][0]["s3"]["bucket"]["name"] - s3_file_name = event["Records"][0]["s3"]["object"]["key"] - - ## concatanating the file per table - most recent - ## iterate through the subfolders - ## table name prefix to iterate through the files written to that table - - object = s3_client.get_object(Bucket=s3_bucket_name, Key=s3_file_name) - body = object['Body'] - csv_string = body.read().decode('utf-8') - dataframe = pd.read_csv(StringIO(csv_string)) ##this is the streaming body - - print(dataframe.head(3)) - - except Exception as err: - print(err) - - # TODO implement - return { - 'statusCode': 200, - 'body': json.dumps('') - } + pass -## Started from fresh on Wed 21st Aug: tables = ['sales_order', 'transaction', -- cgit v1.2.3 From c8e94530b65d6807b2b9bb246a542963839cce9d Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Wed, 21 Aug 2024 14:49:56 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in b882bb0 according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/84 --- src/transform_lambda.py | 36 +++++++++------- tests/test_transform_lambda.py | 94 ++++++++++++++++++++++++++---------------- 2 files changed, 79 insertions(+), 51 deletions(-) diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 3a7cf43..b176ccc 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -1,4 +1,4 @@ -#from src.extract_lambda import extract_bucket +# from src.extract_lambda import extract_bucket import json import boto3 import re @@ -6,29 +6,33 @@ import io from io import StringIO import pandas as pd + def lambda_handler(event, context): pass -tables = ['sales_order', - 'transaction', - 'payment', - 'counterparty', - 'address', - 'staff', - 'purchase_order', - 'department', - 'currency', - 'design', - 'payment_type'] +tables = [ + "sales_order", + "transaction", + "payment", + "counterparty", + "address", + "staff", + "purchase_order", + "department", + "currency", + "design", + "payment_type", +] + -def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client('s3')): +def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client("s3")): table_dfs = {} for table in tables: response = client.list_objects_v2(Bucket=bucket, Prefix=table) - list_of_keys = ['s3://'+bucket+'/'+object['Key'] for object in response['Contents']] + list_of_keys = [ + "s3://" + bucket + "/" + object["Key"] for object in response["Contents"] + ] list_of_df = [pd.read_csv(key) for key in list_of_keys] table_dfs[table] = pd.concat(list_of_df) return table_dfs - - diff --git a/tests/test_transform_lambda.py b/tests/test_transform_lambda.py index 7de1bf3..5121905 100644 --- a/tests/test_transform_lambda.py +++ b/tests/test_transform_lambda.py @@ -6,45 +6,69 @@ import os import boto3 import numpy as np -@pytest.fixture(scope='class') + +@pytest.fixture(scope="class") def aws_credentials(): - os.environ["AWS_ACCESS_KEY_ID"] = 'testing' - os.environ["AWS_SECRET_ACCESS_KEY"] = 'testing' - os.environ["AWS_SECURIT_TOKEN"] = 'testing' - os.environ["AWS_SESSION_TOKEN"] = 'testing' - os.environ["AWS_DEFAULT_REGION"]= 'eu-west-2' + os.environ["AWS_ACCESS_KEY_ID"] = "testing" + os.environ["AWS_SECRET_ACCESS_KEY"] = "testing" + os.environ["AWS_SECURIT_TOKEN"] = "testing" + os.environ["AWS_SESSION_TOKEN"] = "testing" + os.environ["AWS_DEFAULT_REGION"] = "eu-west-2" + -@pytest.fixture(scope='class') +@pytest.fixture(scope="class") def s3_client(aws_credentials): with mock_aws(): - yield boto3.client('s3') + yield boto3.client("s3") + + class TestReadFromS3: - - def test_returns_dictionary_with_correct_value_pair(self,s3_client): - s3_client.create_bucket(Bucket = 'dummy_buc',CreateBucketConfiguration={ - 'LocationConstraint': 'eu-west-2' - }) - s3_client.upload_file('tests/dummy_identical.csv', 'dummy_buc', 'Foods/2024/08/21/Foods_12:03:10.csv') - tables = ['Foods'] - result = read_from_s3_subfolder_to_df(tables,bucket='dummy_buc',client=s3_client) + def test_returns_dictionary_with_correct_value_pair(self, s3_client): + s3_client.create_bucket( + Bucket="dummy_buc", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) + s3_client.upload_file( + "tests/dummy_identical.csv", + "dummy_buc", + "Foods/2024/08/21/Foods_12:03:10.csv", + ) + tables = ["Foods"] + result = read_from_s3_subfolder_to_df( + tables, bucket="dummy_buc", client=s3_client + ) print(result) - expected_df = pd.DataFrame(np.array([['Vegetable', 'Sour', 'Green'], ['Berry', 'Sweet', 'Red']]), - columns=['Food_type', 'Flavour', 'Colour']) - assert isinstance(result,dict) - assert list(result.keys())[0] == 'Foods' - assert isinstance(result['Foods'],pd.DataFrame) - assert result['Foods'].eq(expected_df,axis='columns').all(axis=None) - - def test_returns_dictionary_of_dataframes_for_multiple_tables(self,s3_client): - s3_client.upload_file('tests/dummy_2.csv', 'dummy_buc', 'Cars/2024/08/21/Cars_14:03:56.csv') - tables = ['Foods','Cars'] - result = read_from_s3_subfolder_to_df(tables,bucket='dummy_buc',client=s3_client) - expected_foods_df = pd.DataFrame(np.array([['Vegetable', 'Sour', 'Green'], ['Berry', 'Sweet', 'Red']]), - columns=['Food_type', 'Flavour', 'Colour']) - expected_cars_df = pd.DataFrame(np.array([['Truck', 'Chevrolet', 'Grey'], ['Convertible', 'Mercedes','Red'],['Van','Volkswagen','Blue']]), - columns=['Car_type', 'Brand', 'Colour']) - assert list(result.keys()) == tables - assert result['Foods'].eq(expected_foods_df,axis='columns').all(axis=None) - assert result['Cars'].eq(expected_cars_df,axis='columns').all(axis=None) - + expected_df = pd.DataFrame( + np.array([["Vegetable", "Sour", "Green"], ["Berry", "Sweet", "Red"]]), + columns=["Food_type", "Flavour", "Colour"], + ) + assert isinstance(result, dict) + assert list(result.keys())[0] == "Foods" + assert isinstance(result["Foods"], pd.DataFrame) + assert result["Foods"].eq(expected_df, axis="columns").all(axis=None) + def test_returns_dictionary_of_dataframes_for_multiple_tables(self, s3_client): + s3_client.upload_file( + "tests/dummy_2.csv", "dummy_buc", "Cars/2024/08/21/Cars_14:03:56.csv" + ) + tables = ["Foods", "Cars"] + result = read_from_s3_subfolder_to_df( + tables, bucket="dummy_buc", client=s3_client + ) + expected_foods_df = pd.DataFrame( + np.array([["Vegetable", "Sour", "Green"], ["Berry", "Sweet", "Red"]]), + columns=["Food_type", "Flavour", "Colour"], + ) + expected_cars_df = pd.DataFrame( + np.array( + [ + ["Truck", "Chevrolet", "Grey"], + ["Convertible", "Mercedes", "Red"], + ["Van", "Volkswagen", "Blue"], + ] + ), + columns=["Car_type", "Brand", "Colour"], + ) + assert list(result.keys()) == tables + assert result["Foods"].eq(expected_foods_df, axis="columns").all(axis=None) + assert result["Cars"].eq(expected_cars_df, axis="columns").all(axis=None) -- cgit v1.2.3 From ccedcc10ed533688188a82d2fd364032a326941f Mon Sep 17 00:00:00 2001 From: Alex Date: Tue, 20 Aug 2024 22:59:33 +0100 Subject: ci: add dev-test.yml --- .github/workflows/dev-test.yml | 48 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) create mode 100644 .github/workflows/dev-test.yml diff --git a/.github/workflows/dev-test.yml b/.github/workflows/dev-test.yml new file mode 100644 index 0000000..ebdad5f --- /dev/null +++ b/.github/workflows/dev-test.yml @@ -0,0 +1,48 @@ +name: Development CI + +on: + pull_request: + branches: + - development + push: + branches: + - development + +jobs: + validate-and-test: + name: Validate Terraform and Run Tests + runs-on: ubuntu-latest + steps: + - name: Checkout Repo + uses: actions/checkout@v4 + + - name: Install Terraform + uses: hashicorp/setup-terraform@v3 + + - name: Terraform Init + working-directory: terraform + run: terraform init -backend=false + + - name: Terraform Validate + working-directory: terraform + run: terraform validate + + - name: Set up Python + uses: actions/setup-python@v5 + with: + python-version: '3.11' + + - name: Install Python dependencies + run: | + python -m pip install --upgrade pip + pip install pytest pytest-testdox + pip install -r requirements.txt + + - name: Run pytest + run: pytest tests/ -vvrP --testdox + continue-on-error: true + id: pytest + + - name: Check on failures + if: steps.pytest.outcome == 'failure' + run: exit 1 -- cgit v1.2.3 From 24ad8521b88c6a9b43c74d69443895872b8917ec Mon Sep 17 00:00:00 2001 From: Alex Date: Tue, 20 Aug 2024 23:04:55 +0100 Subject: ci: update dev-test.yml --- .github/workflows/dev-test.yml | 1 + 1 file changed, 1 insertion(+) diff --git a/.github/workflows/dev-test.yml b/.github/workflows/dev-test.yml index ebdad5f..a1e64b2 100644 --- a/.github/workflows/dev-test.yml +++ b/.github/workflows/dev-test.yml @@ -12,6 +12,7 @@ jobs: validate-and-test: name: Validate Terraform and Run Tests runs-on: ubuntu-latest + environment: testing steps: - name: Checkout Repo uses: actions/checkout@v4 -- cgit v1.2.3 From 095acc642a5abbf79209040aa2ac3d413a4ff49a Mon Sep 17 00:00:00 2001 From: Alex Date: Tue, 20 Aug 2024 23:07:55 +0100 Subject: ci: rm dev-test.yml It's in the wrong branch... --- .github/workflows/dev-test.yml | 49 ------------------------------------------ 1 file changed, 49 deletions(-) delete mode 100644 .github/workflows/dev-test.yml diff --git a/.github/workflows/dev-test.yml b/.github/workflows/dev-test.yml deleted file mode 100644 index a1e64b2..0000000 --- a/.github/workflows/dev-test.yml +++ /dev/null @@ -1,49 +0,0 @@ -name: Development CI - -on: - pull_request: - branches: - - development - push: - branches: - - development - -jobs: - validate-and-test: - name: Validate Terraform and Run Tests - runs-on: ubuntu-latest - environment: testing - steps: - - name: Checkout Repo - uses: actions/checkout@v4 - - - name: Install Terraform - uses: hashicorp/setup-terraform@v3 - - - name: Terraform Init - working-directory: terraform - run: terraform init -backend=false - - - name: Terraform Validate - working-directory: terraform - run: terraform validate - - - name: Set up Python - uses: actions/setup-python@v5 - with: - python-version: '3.11' - - - name: Install Python dependencies - run: | - python -m pip install --upgrade pip - pip install pytest pytest-testdox - pip install -r requirements.txt - - - name: Run pytest - run: pytest tests/ -vvrP --testdox - continue-on-error: true - id: pytest - - - name: Check on failures - if: steps.pytest.outcome == 'failure' - run: exit 1 -- cgit v1.2.3 From 4dc7b885950d7c352c53cdd31ac7bb0e905304dd Mon Sep 17 00:00:00 2001 From: Ellie Date: Wed, 21 Aug 2024 13:41:01 +0100 Subject: add dim tables: design, staff, currency, location (wip) --- src/fact-sales-order.py | 54 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) create mode 100644 src/fact-sales-order.py diff --git a/src/fact-sales-order.py b/src/fact-sales-order.py new file mode 100644 index 0000000..a143889 --- /dev/null +++ b/src/fact-sales-order.py @@ -0,0 +1,54 @@ +import pandas as pd +from src.transform_lambda import get_dataframes + +dict_of_df = get_dataframes() # {"design": "design dataframe", "address": "address dataframe", ....} + + +# iterates through each dataframe in the list of dataframes and assigns them to a variable +df_design = dict_of_df[design] +df_currency = dict_of_df[currency] +df_address = dict_of_df[address] +df_staff = dict_of_df[staff] +df_department = dict_of_df[department] +df_counterparty = dict_of_df[counterparty] + + +# creates the dim_design dataframe +dim_design = df_design["design_id", "design_name", "file_name", "file_location"] + +# creates the dim_staff dataframe +staff_department = pd.merge(df_staff, df_department, on='department_id', how="outer") +dim_staff = staff_department['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address'] + +# creates the dim_currency dataframe +# currency names currently hardcoded and not taken from database, is this viable/how else to do this? +d = {"currency_id": [1, 2, 3], "currency_code": ["GBP", "USD", "EUR"], "currency_name": ["Pound", "US Dollar", "Euro"]} +currency_names = pd.DataFrame(data=d) +join_currency = pd.merge(df_currency, currency_names, on="currency_name", how="outer") +dim_currency = join_currency["currency_id", "currency_code", "currency_name"] + +# creates the dim_location dataframe +# need to change address id to location id +"dim_location dataframe: (location_id, address_line_1, address_line_2, district, city, postal code, country, phone)" +dim_location = df_address["address_id", "address_line_1", "address_line_2", "district", "city", "postal_code" "country", "phone"] + + + + + + + + + +# creates the dim_counterparty dataframe +# counterparty_address = pd.merge(df_counterparty, df_address, left_on="legal_address_id", right_on='address_id', how="outer") + +# dim_counterparty = df_counterparty["counterparty_id", "counterparty_legal_name", "counterparty_legal_address_line_1", +# "counterparty_legal_address_line_2", "counterparty_legal_district", "counterpart_legal_city", +# "counterparty_legal_postal_code", "counterparty_legal_country", "counterparty_legal_phone_number"] + + +# TO DO: +# dim_location +# dim_date +# fact_sales_order \ No newline at end of file -- cgit v1.2.3 From 74be9f231ad560eed8630125045532b5975553dc Mon Sep 17 00:00:00 2001 From: T-Aji Date: Wed, 21 Aug 2024 15:58:45 +0100 Subject: 5 dim tables created --- src/fact-sales-order.py | 48 +++++++++++++++++++++++++++++++++--------------- 1 file changed, 33 insertions(+), 15 deletions(-) diff --git a/src/fact-sales-order.py b/src/fact-sales-order.py index a143889..30c958f 100644 --- a/src/fact-sales-order.py +++ b/src/fact-sales-order.py @@ -11,7 +11,7 @@ df_address = dict_of_df[address] df_staff = dict_of_df[staff] df_department = dict_of_df[department] df_counterparty = dict_of_df[counterparty] - +df_sales = dict_of_df[sales] # creates the dim_design dataframe dim_design = df_design["design_id", "design_name", "file_name", "file_location"] @@ -27,28 +27,46 @@ currency_names = pd.DataFrame(data=d) join_currency = pd.merge(df_currency, currency_names, on="currency_name", how="outer") dim_currency = join_currency["currency_id", "currency_code", "currency_name"] -# creates the dim_location dataframe -# need to change address id to location id -"dim_location dataframe: (location_id, address_line_1, address_line_2, district, city, postal code, country, phone)" -dim_location = df_address["address_id", "address_line_1", "address_line_2", "district", "city", "postal_code" "country", "phone"] - - - +# Using .map to add currency_name column and link it to the currency code +# dim_currency = df_currency["currency_id", "currency_code"] +# mappings = { +# "GBP": "Pound", +# "USD": "US Dollar", +# "EUR": "Euro" +# } +# dim_currency["currency_name"] = dim_currency["currency_code"].map(mappings) +# creates the dim_location dataframe +# need to change address id to location id +"dim_location dataframe: (location_id, address_line_1, address_line_2, district, city, postal code, country, phone)" +df_address.rename(columns={"address_id": "location_id"}) +dim_location = df_address["location_id", "address_line_1", "address_line_2", "district", "city", "postal_code" "country", "phone"] +# creates the dim_counterparty dataframe +counterparty_address = pd.merge(df_counterparty, df_address, left_on="legal_address_id", right_on='address_id', how="outer") +counterparty_address.rename(columns={"address_line_1": "counterparty_legal_address_line_1", "address_line_2": "counterparty_legal_address_line_2", + "district": "counterparty_legal_district", "city": "counterparty_legal_city", "postal_code": "counterparty_postal_code", + "country": "counterparty_legal_country", "phone": "counterparty_legal_phone_number"}) +dim_counterparty = df_counterparty["counterparty_id", "counterparty_legal_name", "counterparty_legal_address_line_1", + "counterparty_legal_address_line_2", "counterparty_legal_district", "counterpart_legal_city", + "counterparty_legal_postal_code", "counterparty_legal_country", "counterparty_legal_phone_number"] -# creates the dim_counterparty dataframe -# counterparty_address = pd.merge(df_counterparty, df_address, left_on="legal_address_id", right_on='address_id', how="outer") +# creates the dim_date dataframe +df_sales = df_sales["agreed_delivery_date"] +df_sales["agreed_delivery_date"] = pd.to_datetime["agreed_delivery_date"] +df_sales["year"] = df_sales["agreed_delivery_date"].dt.year +df_sales["month"] = df_sales["agreed_delivery_date"].dt.month +df_sales["day"] = df_sales["agreed_delivery_date"].dt.day +df_sales["day_of_week"] = df_sales["agreed_delivery_date"].dt.dayofweek +df_sales["day_name"] = df_sales["agreed_delivery_date"].dt.day_name() +df_sales["month_name"] = df_sales["agreed_delivery_date"].dt.month_name() +df_sales["quarter"] = df_sales["agreed_delivery_date"].dt.quarter() -# dim_counterparty = df_counterparty["counterparty_id", "counterparty_legal_name", "counterparty_legal_address_line_1", -# "counterparty_legal_address_line_2", "counterparty_legal_district", "counterpart_legal_city", -# "counterparty_legal_postal_code", "counterparty_legal_country", "counterparty_legal_phone_number"] +dim_date = ["date_id", "year", "month", "day", "day_of_week", "day_name", "month_name", "quarter"] #series.dt.quarter() # TO DO: -# dim_location -# dim_date # fact_sales_order \ No newline at end of file -- cgit v1.2.3 From 0c02bd3636ed8815aadf73685c20f8c76a073c99 Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Wed, 21 Aug 2024 15:09:58 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 20a3bd8 according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/85 --- src/fact-sales-order.py | 86 ++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 68 insertions(+), 18 deletions(-) diff --git a/src/fact-sales-order.py b/src/fact-sales-order.py index 30c958f..399e435 100644 --- a/src/fact-sales-order.py +++ b/src/fact-sales-order.py @@ -1,7 +1,8 @@ import pandas as pd from src.transform_lambda import get_dataframes -dict_of_df = get_dataframes() # {"design": "design dataframe", "address": "address dataframe", ....} +# {"design": "design dataframe", "address": "address dataframe", ....} +dict_of_df = get_dataframes() # iterates through each dataframe in the list of dataframes and assigns them to a variable @@ -17,12 +18,23 @@ df_sales = dict_of_df[sales] dim_design = df_design["design_id", "design_name", "file_name", "file_location"] # creates the dim_staff dataframe -staff_department = pd.merge(df_staff, df_department, on='department_id', how="outer") -dim_staff = staff_department['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address'] +staff_department = pd.merge(df_staff, df_department, on="department_id", how="outer") +dim_staff = staff_department[ + "staff_id", + "first_name", + "last_name", + "department_name", + "location", + "email_address", +] # creates the dim_currency dataframe -# currency names currently hardcoded and not taken from database, is this viable/how else to do this? -d = {"currency_id": [1, 2, 3], "currency_code": ["GBP", "USD", "EUR"], "currency_name": ["Pound", "US Dollar", "Euro"]} +# currency names currently hardcoded and not taken from database, is this viable/how else to do this? +d = { + "currency_id": [1, 2, 3], + "currency_code": ["GBP", "USD", "EUR"], + "currency_name": ["Pound", "US Dollar", "Euro"], +} currency_names = pd.DataFrame(data=d) join_currency = pd.merge(df_currency, currency_names, on="currency_name", how="outer") dim_currency = join_currency["currency_id", "currency_code", "currency_name"] @@ -37,22 +49,51 @@ dim_currency = join_currency["currency_id", "currency_code", "currency_name"] # dim_currency["currency_name"] = dim_currency["currency_code"].map(mappings) - # creates the dim_location dataframe -# need to change address id to location id +# need to change address id to location id "dim_location dataframe: (location_id, address_line_1, address_line_2, district, city, postal code, country, phone)" df_address.rename(columns={"address_id": "location_id"}) -dim_location = df_address["location_id", "address_line_1", "address_line_2", "district", "city", "postal_code" "country", "phone"] +dim_location = df_address[ + "location_id", + "address_line_1", + "address_line_2", + "district", + "city", + "postal_code" "country", + "phone", +] # creates the dim_counterparty dataframe -counterparty_address = pd.merge(df_counterparty, df_address, left_on="legal_address_id", right_on='address_id', how="outer") -counterparty_address.rename(columns={"address_line_1": "counterparty_legal_address_line_1", "address_line_2": "counterparty_legal_address_line_2", - "district": "counterparty_legal_district", "city": "counterparty_legal_city", "postal_code": "counterparty_postal_code", - "country": "counterparty_legal_country", "phone": "counterparty_legal_phone_number"}) - -dim_counterparty = df_counterparty["counterparty_id", "counterparty_legal_name", "counterparty_legal_address_line_1", - "counterparty_legal_address_line_2", "counterparty_legal_district", "counterpart_legal_city", - "counterparty_legal_postal_code", "counterparty_legal_country", "counterparty_legal_phone_number"] +counterparty_address = pd.merge( + df_counterparty, + df_address, + left_on="legal_address_id", + right_on="address_id", + how="outer", +) +counterparty_address.rename( + columns={ + "address_line_1": "counterparty_legal_address_line_1", + "address_line_2": "counterparty_legal_address_line_2", + "district": "counterparty_legal_district", + "city": "counterparty_legal_city", + "postal_code": "counterparty_postal_code", + "country": "counterparty_legal_country", + "phone": "counterparty_legal_phone_number", + } +) + +dim_counterparty = df_counterparty[ + "counterparty_id", + "counterparty_legal_name", + "counterparty_legal_address_line_1", + "counterparty_legal_address_line_2", + "counterparty_legal_district", + "counterpart_legal_city", + "counterparty_legal_postal_code", + "counterparty_legal_country", + "counterparty_legal_phone_number", +] # creates the dim_date dataframe df_sales = df_sales["agreed_delivery_date"] @@ -65,8 +106,17 @@ df_sales["day_name"] = df_sales["agreed_delivery_date"].dt.day_name() df_sales["month_name"] = df_sales["agreed_delivery_date"].dt.month_name() df_sales["quarter"] = df_sales["agreed_delivery_date"].dt.quarter() -dim_date = ["date_id", "year", "month", "day", "day_of_week", "day_name", "month_name", "quarter"] #series.dt.quarter() +dim_date = [ + "date_id", + "year", + "month", + "day", + "day_of_week", + "day_name", + "month_name", + "quarter", +] # series.dt.quarter() # TO DO: -# fact_sales_order \ No newline at end of file +# fact_sales_order -- cgit v1.2.3 From 77fa5b0922c214ae0b16d5582aa20af9c75e2f31 Mon Sep 17 00:00:00 2001 From: Alex Date: Wed, 21 Aug 2024 16:46:09 +0100 Subject: Update dev-tests.yml --- .github/workflows/dev-tests.yml | 1 + 1 file changed, 1 insertion(+) diff --git a/.github/workflows/dev-tests.yml b/.github/workflows/dev-tests.yml index d66f1c6..b64032e 100644 --- a/.github/workflows/dev-tests.yml +++ b/.github/workflows/dev-tests.yml @@ -10,6 +10,7 @@ on: jobs: validate-and-test: + environment: testing name: Validate Terraform and Run Tests runs-on: ubuntu-latest steps: -- cgit v1.2.3 From 93a56e57daee737ae87be8f3174ad69ca16f7392 Mon Sep 17 00:00:00 2001 From: Alex Date: Wed, 21 Aug 2024 16:49:30 +0100 Subject: ci: update dev-tests.yml --- .github/workflows/dev-tests.yml | 3 +++ 1 file changed, 3 insertions(+) diff --git a/.github/workflows/dev-tests.yml b/.github/workflows/dev-tests.yml index b64032e..443e03b 100644 --- a/.github/workflows/dev-tests.yml +++ b/.github/workflows/dev-tests.yml @@ -8,6 +8,9 @@ on: branches: - development +env: + PYTHONPATH: ${{ github.workspace }} + jobs: validate-and-test: environment: testing -- cgit v1.2.3 From 09f0e49f2c63e941ab255157a937904ce6b4eb74 Mon Sep 17 00:00:00 2001 From: Alex Date: Wed, 21 Aug 2024 16:53:24 +0100 Subject: chore: delete test for secrets_manager.py We don't need this anymore since we removed the secrets_manager.py file, and it's making the GH Action fail too. --- tests/test_secrets_manager.py | 84 ------------------------------------------- 1 file changed, 84 deletions(-) delete mode 100644 tests/test_secrets_manager.py diff --git a/tests/test_secrets_manager.py b/tests/test_secrets_manager.py deleted file mode 100644 index 609c572..0000000 --- a/tests/test_secrets_manager.py +++ /dev/null @@ -1,84 +0,0 @@ -from src.secrets_manager import sm_client, retrieve_secrets -import boto3 -import botocore.exceptions -from moto import mock_aws -import json -import pytest -import os - - -@pytest.fixture(scope="function") -def aws_credentials(): - """Mocked AWS Credentials for moto.""" - os.environ["AWS_ACCESS_KEY_ID"] = "testing" - os.environ["AWS_SECRET_ACCESS_KEY"] = "testing" - os.environ["AWS_SECURITY_TOKEN"] = "testing" - os.environ["AWS_SESSION_TOKEN"] = "testing" - os.environ["AWS_DEFAULT_REGION"] = "eu-west-2" - - -@pytest.fixture(scope="function") -def mock_sm_client(aws_credentials): - with mock_aws(): - yield boto3.client("secretsmanager") - - -@pytest.fixture(scope="function") -def mock_store_secret(mock_sm_client): - secret = { - "cohort_id": "test_cohort_id", - "user": "test_user_id", - "password": "test_password", - "host": "test_host", - "database": "test_database", - "port": "test_port", - } - - secret_name = "test_secret" - - response = mock_sm_client.create_secret( - Name=secret_name, SecretString=json.dumps(secret) - ) - - return response - - -def test_retrieves_secrets_returns_dictionary(mock_sm_client, mock_store_secret): - secret_name = "test_secret" - - result = retrieve_secrets(mock_sm_client, secret_name) - - assert isinstance(result, dict) - - -def test_retrieves_secrets_returns_correct_keys_and_values( - mock_sm_client, mock_store_secret -): - secret_name = "test_secret" - - result = retrieve_secrets(mock_sm_client, secret_name) - - assert result["cohort_id"] == "test_cohort_id" - assert result["user"] == "test_user_id" - assert result["password"] == "test_password" - assert result["host"] == "test_host" - assert result["database"] == "test_database" - assert result["port"] == "test_port" - - -def test_retrieves_secrets_raises_error_if_secret_name_incorrect_data_type( - mock_sm_client, -): - secret_name = [1, 2, 3] - - with pytest.raises(botocore.exceptions.ParamValidationError) as error: - retrieve_secrets(mock_sm_client, secret_name) - - -def test_retrieves_secrets_raises_error_if_secret_name_does_not_exist( - mock_sm_client, mock_store_secret -): - secret_name = "test_secret_2" - - with pytest.raises(botocore.exceptions.ClientError) as error: - retrieve_secrets(mock_sm_client, secret_name) -- cgit v1.2.3 From 5b2b4864eae129e112e70d093eb66498d7de401e Mon Sep 17 00:00:00 2001 From: lian-manonog Date: Wed, 21 Aug 2024 17:11:57 +0100 Subject: wip: fact_purchase_order schema --- src/fact-purchase-table.py | 34 ++++++++++++++++++++++++++++++++++ src/fact-sales-order.py | 2 +- src/transform_lambda.py | 4 ++-- 3 files changed, 37 insertions(+), 3 deletions(-) create mode 100644 src/fact-purchase-table.py diff --git a/src/fact-purchase-table.py b/src/fact-purchase-table.py new file mode 100644 index 0000000..53c0148 --- /dev/null +++ b/src/fact-purchase-table.py @@ -0,0 +1,34 @@ +from src.transform_lambda import read_from_s3_subfolder_to_df, tables +from src.extract_lambda import extract_bucket +import json +import boto3 +import re +import pandas as pd + + +dict_of_df = read_from_s3_subfolder_to_df(tables, extract_bucket(), client=boto3.client("s3")) + + +# iterates through each dataframe in the list of dataframes and assigns them to a variable +df_staff = dict_of_df['staff'] ##no change +df_currency = dict_of_df['currency'] ##scraping API +df_counterparty = dict_of_df['counterparty'] +df_address = dict_of_df['address'] +df_department = dict_of_df['department'] +df_purchase_order = dict_of_df['purchase_order'] + +## dim_staff table is the same across the schemas (no change) + +## dim_counterparty table + +## dim_location df_currency --> drops 2 columns +dim_location = df_address.drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}) + +## dim_counterparty +df_prefixed_address = df_address.add_prefix('counterparty_legal_', axis=1) +pd.merge(df_counterparty, + df_prefixed_address, + left_on="legal_address_id", + right_on="address_id", + how="outer") + diff --git a/src/fact-sales-order.py b/src/fact-sales-order.py index 399e435..57e2e84 100644 --- a/src/fact-sales-order.py +++ b/src/fact-sales-order.py @@ -69,7 +69,7 @@ counterparty_address = pd.merge( df_address, left_on="legal_address_id", right_on="address_id", - how="outer", + how="outer" ) counterparty_address.rename( columns={ diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 9238180..920a24f 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -1,8 +1,6 @@ import json import boto3 import re -import io -from io import StringIO import pandas as pd @@ -35,3 +33,5 @@ def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client("s3")): list_of_df = [pd.read_csv(key) for key in list_of_keys] table_dfs[table] = pd.concat(list_of_df) return table_dfs + + -- cgit v1.2.3 From 956bc9223a584c9cb687277f9000967f9b3ddc6b Mon Sep 17 00:00:00 2001 From: T-Aji Date: Wed, 21 Aug 2024 20:04:13 +0100 Subject: began dim_date df --- src/fact-sales-order.py | 35 +++++++++++++++++------------------ 1 file changed, 17 insertions(+), 18 deletions(-) diff --git a/src/fact-sales-order.py b/src/fact-sales-order.py index 30c958f..ef18f02 100644 --- a/src/fact-sales-order.py +++ b/src/fact-sales-order.py @@ -14,27 +14,21 @@ df_counterparty = dict_of_df[counterparty] df_sales = dict_of_df[sales] # creates the dim_design dataframe -dim_design = df_design["design_id", "design_name", "file_name", "file_location"] +dim_design = df_design.loc[:, "design_id", "design_name", "file_name", "file_location"] # creates the dim_staff dataframe staff_department = pd.merge(df_staff, df_department, on='department_id', how="outer") -dim_staff = staff_department['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address'] +dim_staff = staff_department.loc[:, 'staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address'] # creates the dim_currency dataframe -# currency names currently hardcoded and not taken from database, is this viable/how else to do this? -d = {"currency_id": [1, 2, 3], "currency_code": ["GBP", "USD", "EUR"], "currency_name": ["Pound", "US Dollar", "Euro"]} -currency_names = pd.DataFrame(data=d) -join_currency = pd.merge(df_currency, currency_names, on="currency_name", how="outer") -dim_currency = join_currency["currency_id", "currency_code", "currency_name"] - # Using .map to add currency_name column and link it to the currency code -# dim_currency = df_currency["currency_id", "currency_code"] -# mappings = { -# "GBP": "Pound", -# "USD": "US Dollar", -# "EUR": "Euro" -# } -# dim_currency["currency_name"] = dim_currency["currency_code"].map(mappings) +dim_currency = df_currency.loc[:, "currency_id", "currency_code"] +mappings = { + "GBP": "Pound", + "USD": "US Dollar", + "EUR": "Euro" +} +dim_currency["currency_name"] = dim_currency["currency_code"].map(mappings) @@ -42,7 +36,7 @@ dim_currency = join_currency["currency_id", "currency_code", "currency_name"] # need to change address id to location id "dim_location dataframe: (location_id, address_line_1, address_line_2, district, city, postal code, country, phone)" df_address.rename(columns={"address_id": "location_id"}) -dim_location = df_address["location_id", "address_line_1", "address_line_2", "district", "city", "postal_code" "country", "phone"] +dim_location = df_address.loc[:, "location_id", "address_line_1", "address_line_2", "district", "city", "postal_code" "country", "phone"] # creates the dim_counterparty dataframe counterparty_address = pd.merge(df_counterparty, df_address, left_on="legal_address_id", right_on='address_id', how="outer") @@ -50,12 +44,12 @@ counterparty_address.rename(columns={"address_line_1": "counterparty_legal_addre "district": "counterparty_legal_district", "city": "counterparty_legal_city", "postal_code": "counterparty_postal_code", "country": "counterparty_legal_country", "phone": "counterparty_legal_phone_number"}) -dim_counterparty = df_counterparty["counterparty_id", "counterparty_legal_name", "counterparty_legal_address_line_1", +dim_counterparty = df_counterparty.loc[:, "counterparty_id", "counterparty_legal_name", "counterparty_legal_address_line_1", "counterparty_legal_address_line_2", "counterparty_legal_district", "counterpart_legal_city", "counterparty_legal_postal_code", "counterparty_legal_country", "counterparty_legal_phone_number"] # creates the dim_date dataframe -df_sales = df_sales["agreed_delivery_date"] +df_sales = df_sales.loc[:, "agreed_delivery_date"] df_sales["agreed_delivery_date"] = pd.to_datetime["agreed_delivery_date"] df_sales["year"] = df_sales["agreed_delivery_date"].dt.year df_sales["month"] = df_sales["agreed_delivery_date"].dt.month @@ -65,6 +59,11 @@ df_sales["day_name"] = df_sales["agreed_delivery_date"].dt.day_name() df_sales["month_name"] = df_sales["agreed_delivery_date"].dt.month_name() df_sales["quarter"] = df_sales["agreed_delivery_date"].dt.quarter() +# repeat ln 52 - 60 for each column +# merge dataframes into one dataframe +# remove duplicates + + dim_date = ["date_id", "year", "month", "day", "day_of_week", "day_name", "month_name", "quarter"] #series.dt.quarter() -- cgit v1.2.3 From 51cae81184785f1700247d88a3185e82a458fe5f Mon Sep 17 00:00:00 2001 From: Alex Date: Thu, 22 Aug 2024 08:58:34 +0100 Subject: test: re-add test_secrets_manager Amended import path to extract_lambda --- tests/test_secrets_manager.py | 84 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 84 insertions(+) create mode 100644 tests/test_secrets_manager.py diff --git a/tests/test_secrets_manager.py b/tests/test_secrets_manager.py new file mode 100644 index 0000000..79d8193 --- /dev/null +++ b/tests/test_secrets_manager.py @@ -0,0 +1,84 @@ +from src.extract_lambda import sm_client, retrieve_secrets +import boto3 +import botocore.exceptions +from moto import mock_aws +import json +import pytest +import os + + +@pytest.fixture(scope="function") +def aws_credentials(): + """Mocked AWS Credentials for moto.""" + os.environ["AWS_ACCESS_KEY_ID"] = "testing" + os.environ["AWS_SECRET_ACCESS_KEY"] = "testing" + os.environ["AWS_SECURITY_TOKEN"] = "testing" + os.environ["AWS_SESSION_TOKEN"] = "testing" + os.environ["AWS_DEFAULT_REGION"] = "eu-west-2" + + +@pytest.fixture(scope="function") +def mock_sm_client(aws_credentials): + with mock_aws(): + yield boto3.client("secretsmanager") + + +@pytest.fixture(scope="function") +def mock_store_secret(mock_sm_client): + secret = { + "cohort_id": "test_cohort_id", + "user": "test_user_id", + "password": "test_password", + "host": "test_host", + "database": "test_database", + "port": "test_port", + } + + secret_name = "test_secret" + + response = mock_sm_client.create_secret( + Name=secret_name, SecretString=json.dumps(secret) + ) + + return response + + +def test_retrieves_secrets_returns_dictionary(mock_sm_client, mock_store_secret): + secret_name = "test_secret" + + result = retrieve_secrets(mock_sm_client, secret_name) + + assert isinstance(result, dict) + + +def test_retrieves_secrets_returns_correct_keys_and_values( + mock_sm_client, mock_store_secret +): + secret_name = "test_secret" + + result = retrieve_secrets(mock_sm_client, secret_name) + + assert result["cohort_id"] == "test_cohort_id" + assert result["user"] == "test_user_id" + assert result["password"] == "test_password" + assert result["host"] == "test_host" + assert result["database"] == "test_database" + assert result["port"] == "test_port" + + +def test_retrieves_secrets_raises_error_if_secret_name_incorrect_data_type( + mock_sm_client, +): + secret_name = [1, 2, 3] + + with pytest.raises(botocore.exceptions.ParamValidationError) as error: + retrieve_secrets(mock_sm_client, secret_name) + + +def test_retrieves_secrets_raises_error_if_secret_name_does_not_exist( + mock_sm_client, mock_store_secret +): + secret_name = "test_secret_2" + + with pytest.raises(botocore.exceptions.ClientError) as error: + retrieve_secrets(mock_sm_client, secret_name) -- cgit v1.2.3 From c5338ebb198a79604e36d65de39e28baf54f0ecd Mon Sep 17 00:00:00 2001 From: T-Aji Date: Thu, 22 Aug 2024 10:29:34 +0100 Subject: refactor df creation into func --- src/fact-sales-order.py | 104 ++++++++++++++++-------------------------------- 1 file changed, 34 insertions(+), 70 deletions(-) diff --git a/src/fact-sales-order.py b/src/fact-sales-order.py index 870f660..7921047 100644 --- a/src/fact-sales-order.py +++ b/src/fact-sales-order.py @@ -1,86 +1,50 @@ import pandas as pd -from src.transform_lambda import get_dataframes -# {"design": "design dataframe", "address": "address dataframe", ....} -dict_of_df = get_dataframes() +def create_dim_design(dict_of_df): + df_design = dict_of_df["design"] + dim_design = df_design.loc[:, ["design_id", "design_name", "file_name", "file_location"]] + return dim_design -# iterates through each dataframe in the list of dataframes and assigns them to a variable -df_design = dict_of_df[design] -df_currency = dict_of_df[currency] -df_address = dict_of_df[address] -df_staff = dict_of_df[staff] -df_department = dict_of_df[department] -df_counterparty = dict_of_df[counterparty] -df_sales = dict_of_df[sales] +def create_dim_staff(dict_of_df): + staff_department = pd.merge(dict_of_df["staff"], dict_of_df["department"], on='department_id', how="outer") + dim_staff = staff_department.loc[:, ['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address']] + return dim_staff -# creates the dim_design dataframe -dim_design = df_design.loc[:, "design_id", "design_name", "file_name", "file_location"] - -# creates the dim_staff dataframe -staff_department = pd.merge(df_staff, df_department, on='department_id', how="outer") -dim_staff = staff_department.loc[:, 'staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address'] - -# creates the dim_currency dataframe -# Using .map to add currency_name column and link it to the currency code -dim_currency = df_currency.loc[:, "currency_id", "currency_code"] -mappings = { - "GBP": "Pound", - "USD": "US Dollar", - "EUR": "Euro" -} -dim_currency["currency_name"] = dim_currency["currency_code"].map(mappings) - - - -# creates the dim_location dataframe -# need to change address id to location id -"dim_location dataframe: (location_id, address_line_1, address_line_2, district, city, postal code, country, phone)" -df_address.rename(columns={"address_id": "location_id"}) -dim_location = df_address.loc[:, "location_id", "address_line_1", "address_line_2", "district", "city", "postal_code" "country", "phone"] - -# creates the dim_counterparty dataframe -counterparty_address = pd.merge( - df_counterparty, - df_address, - left_on="legal_address_id", - right_on="address_id", - how="outer" -) -counterparty_address.rename( - columns={ - "address_line_1": "counterparty_legal_address_line_1", - "address_line_2": "counterparty_legal_address_line_2", - "district": "counterparty_legal_district", - "city": "counterparty_legal_city", - "postal_code": "counterparty_postal_code", - "country": "counterparty_legal_country", - "phone": "counterparty_legal_phone_number", +def create_dim_currency(dict_of_df): + df_currency = dict_of_df["currency"] + dim_currency = df_currency.loc[:, ["currency_id", "currency_code"]] + mappings = { + "GBP": "Pound", + "USD": "US Dollar", + "EUR": "Euro" } -) - -dim_counterparty = df_counterparty.loc[:, "counterparty_id", "counterparty_legal_name", "counterparty_legal_address_line_1", - "counterparty_legal_address_line_2", "counterparty_legal_district", "counterpart_legal_city", - "counterparty_legal_postal_code", "counterparty_legal_country", "counterparty_legal_phone_number"] - -# creates the dim_date dataframe -df_sales = df_sales.loc[:, "agreed_delivery_date"] -df_sales["agreed_delivery_date"] = pd.to_datetime["agreed_delivery_date"] -df_sales["year"] = df_sales["agreed_delivery_date"].dt.year -df_sales["month"] = df_sales["agreed_delivery_date"].dt.month -df_sales["day"] = df_sales["agreed_delivery_date"].dt.day -df_sales["day_of_week"] = df_sales["agreed_delivery_date"].dt.dayofweek -df_sales["day_name"] = df_sales["agreed_delivery_date"].dt.day_name() -df_sales["month_name"] = df_sales["agreed_delivery_date"].dt.month_name() -df_sales["quarter"] = df_sales["agreed_delivery_date"].dt.quarter() + dim_currency["currency_name"] = dim_currency["currency_code"].map(mappings) + return dim_currency + + +def create_dim_date(dict_of_df): + df_sales = dict_of_df["sales"] + df_sales = df_sales.loc[:, ["agreed_delivery_date"]] + df_sales["agreed_delivery_date"] = pd.to_datetime["agreed_delivery_date"] + df_sales["year"] = df_sales["agreed_delivery_date"].dt.year + df_sales["month"] = df_sales["agreed_delivery_date"].dt.month + df_sales["day"] = df_sales["agreed_delivery_date"].dt.day + df_sales["day_of_week"] = df_sales["agreed_delivery_date"].dt.dayofweek + df_sales["day_name"] = df_sales["agreed_delivery_date"].dt.day_name() + df_sales["month_name"] = df_sales["agreed_delivery_date"].dt.month_name() + df_sales["quarter"] = df_sales["agreed_delivery_date"].dt.quarter() + dim_date = ["date_id", "year", "month", "day", "day_of_week", "day_name", "month_name", "quarter"] #series.dt.quarter() + return dim_date # repeat ln 52 - 60 for each column # merge dataframes into one dataframe # remove duplicates -dim_date = ["date_id", "year", "month", "day", "day_of_week", "day_name", "month_name", "quarter"] #series.dt.quarter() + # TO DO: +# complete dim_date # fact_sales_order -- cgit v1.2.3 From 548b8678e4d5f725e086f0e4eb115c9aa11b55be Mon Sep 17 00:00:00 2001 From: T-Aji Date: Thu, 22 Aug 2024 10:48:54 +0100 Subject: passing tests create_dim_design and create_dim_staff --- src/fact_sales_order.py | 50 ++++++++++++++++++++++++++++++++++++++++++ tests/test_fact_sales_order.py | 40 +++++++++++++++++++++++++++++++++ 2 files changed, 90 insertions(+) create mode 100644 src/fact_sales_order.py create mode 100644 tests/test_fact_sales_order.py diff --git a/src/fact_sales_order.py b/src/fact_sales_order.py new file mode 100644 index 0000000..870a030 --- /dev/null +++ b/src/fact_sales_order.py @@ -0,0 +1,50 @@ +import pandas as pd + + +def create_dim_design(dict_of_df): + df_design = dict_of_df["design"] + dim_design = df_design.loc[:, ["design_id", "design_name", "file_name", "file_location"]] + return dim_design + +def create_dim_staff(dict_of_df): + staff_department = pd.merge(dict_of_df["staff"], dict_of_df["department"], on='department_id', how="left") + dim_staff = staff_department.loc[:, ['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address']] + return dim_staff + +def create_dim_currency(dict_of_df): + df_currency = dict_of_df["currency"] + dim_currency = df_currency.loc[:, ["currency_id", "currency_code"]] + mappings = { + "GBP": "Pound", + "USD": "US Dollar", + "EUR": "Euro" + } + dim_currency["currency_name"] = dim_currency["currency_code"].map(mappings) + return dim_currency + + +def create_dim_date(dict_of_df): + df_sales = dict_of_df["sales"] + df_sales = df_sales.loc[:, ["agreed_delivery_date"]] + df_sales["agreed_delivery_date"] = pd.to_datetime["agreed_delivery_date"] + df_sales["year"] = df_sales["agreed_delivery_date"].dt.year + df_sales["month"] = df_sales["agreed_delivery_date"].dt.month + df_sales["day"] = df_sales["agreed_delivery_date"].dt.day + df_sales["day_of_week"] = df_sales["agreed_delivery_date"].dt.dayofweek + df_sales["day_name"] = df_sales["agreed_delivery_date"].dt.day_name() + df_sales["month_name"] = df_sales["agreed_delivery_date"].dt.month_name() + df_sales["quarter"] = df_sales["agreed_delivery_date"].dt.quarter() + dim_date = ["date_id", "year", "month", "day", "day_of_week", "day_name", "month_name", "quarter"] #series.dt.quarter() + return dim_date + +# repeat ln 52 - 60 for each column +# merge dataframes into one dataframe +# remove duplicates + + + + + +# TO DO: +# complete dim_date +# fact_sales_order diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py new file mode 100644 index 0000000..13196d5 --- /dev/null +++ b/tests/test_fact_sales_order.py @@ -0,0 +1,40 @@ +from src.fact_sales_order import create_dim_design, create_dim_staff +import pandas as pd + +class TestCreateDimDesign: + def test_dim_design_returns_dataframe(self): + d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + test_df = {"design": pd.DataFrame(data=d)} + result = create_dim_design(test_df) + assert isinstance(result, pd.DataFrame) + + def test_dim_design_returns_correct_columns_and_values(self): + d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + test_df = {"design": pd.DataFrame(data=d)} + result = create_dim_design(test_df) + d2 = {"design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"]} + expected_df = pd.DataFrame(data=d2) + expected_result = expected_df.copy() + assert result.equals(expected_result) + +class TestCreateDimStaff: + def test_dim_staff_returns_dataframe(self): + d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} + result = create_dim_staff(test_df) + assert isinstance(result, pd.DataFrame) + + def test_dim_staff_returns_correct_columns_and_values(self): + d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} + result = create_dim_staff(test_df) + expected_d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"]} + expected_df = pd.DataFrame(data=expected_d) + expected_result = expected_df.copy() + assert result.equals(expected_result) + \ No newline at end of file -- cgit v1.2.3 From 21229b09564befcd58363ed7bc1774bbb457ee4b Mon Sep 17 00:00:00 2001 From: T-Aji Date: Thu, 22 Aug 2024 11:03:15 +0100 Subject: passing TestCreateDimCurrency --- tests/test_fact_sales_order.py | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py index 13196d5..82845d7 100644 --- a/tests/test_fact_sales_order.py +++ b/tests/test_fact_sales_order.py @@ -1,4 +1,4 @@ -from src.fact_sales_order import create_dim_design, create_dim_staff +from src.fact_sales_order import create_dim_design, create_dim_staff, create_dim_currency import pandas as pd class TestCreateDimDesign: @@ -37,4 +37,21 @@ class TestCreateDimStaff: expected_df = pd.DataFrame(data=expected_d) expected_result = expected_df.copy() assert result.equals(expected_result) + +class TestCreateDimCurrency: + def test_dim_currency_returns_dataframe(self): + d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"]} + test_df = {"currency": pd.DataFrame(data=d)} + result = create_dim_currency(test_df) + assert isinstance(result, pd.DataFrame) + + def test_dim_currency_returns_columns_and_values(self): + d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"]} + test_df = {"currency": pd.DataFrame(data=d)} + result = create_dim_currency(test_df) + expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} + expected_df = pd.DataFrame(data=expected_d) + expected_result = expected_df.copy() + assert result.equals(expected_result) + \ No newline at end of file -- cgit v1.2.3 From 395731433d9e10eb748fc44669886d8aa80951e1 Mon Sep 17 00:00:00 2001 From: Ang Bel Date: Thu, 22 Aug 2024 11:09:36 +0100 Subject: refactored approach to writing transformation as functions per df. WIP --- src/fact-purchase-table.py | 53 ++++++++++++++++++++++++++-------------------- 1 file changed, 30 insertions(+), 23 deletions(-) diff --git a/src/fact-purchase-table.py b/src/fact-purchase-table.py index 53c0148..91f5077 100644 --- a/src/fact-purchase-table.py +++ b/src/fact-purchase-table.py @@ -6,29 +6,36 @@ import re import pandas as pd -dict_of_df = read_from_s3_subfolder_to_df(tables, extract_bucket(), client=boto3.client("s3")) - - -# iterates through each dataframe in the list of dataframes and assigns them to a variable -df_staff = dict_of_df['staff'] ##no change -df_currency = dict_of_df['currency'] ##scraping API -df_counterparty = dict_of_df['counterparty'] -df_address = dict_of_df['address'] -df_department = dict_of_df['department'] -df_purchase_order = dict_of_df['purchase_order'] +# iterates through each dataframe in the list of dataframes and assigns them to a variable +def get_dfs_from_dict(tables,dictionary=dict_of_df): + for table in tables: + df_staff = dict_of_df['staff'] ##no change + df_currency = dict_of_df['currency'] ##scraping API + df_counterparty = dict_of_df['counterparty'] + df_address = dict_of_df['address'] + df_department = dict_of_df['department'] + df_purchase_order = dict_of_df['purchase_order'] ## dim_staff table is the same across the schemas (no change) -## dim_counterparty table - -## dim_location df_currency --> drops 2 columns -dim_location = df_address.drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}) - -## dim_counterparty -df_prefixed_address = df_address.add_prefix('counterparty_legal_', axis=1) -pd.merge(df_counterparty, - df_prefixed_address, - left_on="legal_address_id", - right_on="address_id", - how="outer") - +## dim_location from address --> drops 2 columns +def create_dim_location(dict_of_df): + dim_location = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}) + return dim_location + +## dim_counterparty from address and counterparty +def create_dim_counterparty(dict_of_df): + df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) + pd.merge(dict_of_df['counterparty'], + df_prefixed_address, + left_on="legal_address_id", + right_on="address_id", + how="outer") + +def create_fact_purchase_order(dict_of_df): + df_po = dict_of_df['purchase_order'] + df_po.index.name = 'purchase_record_id' + #df_po['create_date'] = df_po['create_at'].date() + #df_po['create_time'] = df_po['create_at'].time() + df_po['agreed_delivery_date'] = + df_po['agreed_payment_date'] \ No newline at end of file -- cgit v1.2.3 From 2fa95ee69bb863dde8c31b870c08863cad84c65b Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Thu, 22 Aug 2024 11:14:11 +0100 Subject: fix: change fixture scope to function instead of class --- tests/test_extract_lambda.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tests/test_extract_lambda.py b/tests/test_extract_lambda.py index 548ce67..c340fab 100644 --- a/tests/test_extract_lambda.py +++ b/tests/test_extract_lambda.py @@ -19,7 +19,7 @@ from src.extract_lambda import ( ) -@pytest.fixture(scope="class") +@pytest.fixture(scope="function") def mock_config(): env_vars = { "host": "abc", @@ -34,7 +34,7 @@ def mock_config(): yield mock_config -@pytest.fixture(scope="class") +@pytest.fixture(scope="function") def aws_credentials(): os.environ["AWS_ACCESS_KEY_ID"] = "testing" os.environ["AWS_SECRET_ACCESS_KEY"] = "testing" -- cgit v1.2.3 From d5e4192a16eb6bb60e1f245124c681999a582572 Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Thu, 22 Aug 2024 11:17:19 +0100 Subject: fix: update additional fixtures to use scope function --- tests/test_extract_lambda.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tests/test_extract_lambda.py b/tests/test_extract_lambda.py index c340fab..2f5ff71 100644 --- a/tests/test_extract_lambda.py +++ b/tests/test_extract_lambda.py @@ -43,13 +43,13 @@ def aws_credentials(): os.environ["AWS_DEFAULT_REGION"] = "eu-west-2" -@pytest.fixture(scope="class") +@pytest.fixture(scope="function") def s3_client(aws_credentials): with mock_aws(): yield boto3.client("s3") -@pytest.fixture(scope="class") +@pytest.fixture(scope="function") def s3_mock_bucket(s3_client): bucket = s3_client.create_bucket( Bucket="extract_bucket", -- cgit v1.2.3 From 844d79fdcfb4ff7118f8ae02aa77b6a29f1467c2 Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Thu, 22 Aug 2024 11:18:32 +0100 Subject: feat: autouse credentials fixture --- tests/test_extract_lambda.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/test_extract_lambda.py b/tests/test_extract_lambda.py index 2f5ff71..9cf5684 100644 --- a/tests/test_extract_lambda.py +++ b/tests/test_extract_lambda.py @@ -34,7 +34,7 @@ def mock_config(): yield mock_config -@pytest.fixture(scope="function") +@pytest.fixture(scope="function", autouse=True) def aws_credentials(): os.environ["AWS_ACCESS_KEY_ID"] = "testing" os.environ["AWS_SECRET_ACCESS_KEY"] = "testing" -- cgit v1.2.3 From 01d48158121472229bad675fa0596cc09efca746 Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Thu, 22 Aug 2024 11:34:19 +0100 Subject: fix: create two mocked buckets and check if extract_bucket is returned --- tests/test_extract_lambda.py | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/tests/test_extract_lambda.py b/tests/test_extract_lambda.py index 9cf5684..92f53aa 100644 --- a/tests/test_extract_lambda.py +++ b/tests/test_extract_lambda.py @@ -153,7 +153,14 @@ class TestExtractBucket: assert result == "extract_bucket" def test_bucket_returns_first_bucket(self, s3_client): - bucket1 = s3_client.create_bucket( + # Redefine what the test does + # Create two buckets and check that only extract_bucket is returned + + s3_client.create_bucket( + Bucket="extract_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) + s3_client.create_bucket( Bucket="bucket1", CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, ) -- cgit v1.2.3 From 6f614bfe226f3cd002d2d2d9f698d9dfa4c390ef Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Thu, 22 Aug 2024 11:36:38 +0100 Subject: fix: remove bucket deletion for index error test --- tests/test_extract_lambda.py | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/tests/test_extract_lambda.py b/tests/test_extract_lambda.py index 92f53aa..db6e25f 100644 --- a/tests/test_extract_lambda.py +++ b/tests/test_extract_lambda.py @@ -168,9 +168,8 @@ class TestExtractBucket: assert result == "extract_bucket" def test_returns_index_error_if_no_buckets(self, s3_client): - s3_client.delete_bucket(Bucket="extract_bucket") - s3_client.delete_bucket(Bucket="bucket1") - + # We don't even need to delete the bucket as there are no buckets + # due to the mock being reset for each test function now with pytest.raises(IndexError, match="list index out of range"): extract_bucket(s3_client) -- cgit v1.2.3 From 60459fbd98156849c399747c20635ff92d6718f8 Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Thu, 22 Aug 2024 11:42:14 +0100 Subject: fix: add missing mock_conn fixture --- tests/test_extract_lambda.py | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/tests/test_extract_lambda.py b/tests/test_extract_lambda.py index db6e25f..9d4d63c 100644 --- a/tests/test_extract_lambda.py +++ b/tests/test_extract_lambda.py @@ -19,6 +19,12 @@ from src.extract_lambda import ( ) +@pytest.fixture +def mock_conn(): + with patch("src.extract_lambda.Connection") as mock: + yield mock + + @pytest.fixture(scope="function") def mock_config(): env_vars = { @@ -214,6 +220,7 @@ class TestConnectToDatabase: class TestProcessAndUploadTables: + # Added missing mock_conn fixture def test_error_process_and_upload_tables(self, mock_conn, s3_client, caplog): caplog.set_level(logging.INFO) -- cgit v1.2.3 From 7a66e9c46e58e58c62ec7dfe5fccbd9d826a1bf7 Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Thu, 22 Aug 2024 11:46:04 +0100 Subject: fix: convert credentials to json dict --- tests/test_extract_lambda.py | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/tests/test_extract_lambda.py b/tests/test_extract_lambda.py index 9d4d63c..af3503d 100644 --- a/tests/test_extract_lambda.py +++ b/tests/test_extract_lambda.py @@ -27,13 +27,15 @@ def mock_conn(): @pytest.fixture(scope="function") def mock_config(): - env_vars = { - "host": "abc", - "port": "5432", - "user": "def", - "password": "password", - "database": "db", - } + env_vars = json.dumps( + { + "host": "abc", + "port": "5432", + "user": "def", + "password": "password", + "database": "db", + } + ) with patch( "src.extract_lambda.retrieve_secrets", return_value=env_vars ) as mock_config: -- cgit v1.2.3 From 4a3835d70bb143de23437e6f50f1050f810cd0b1 Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Thu, 22 Aug 2024 11:56:43 +0100 Subject: fix: inject mock_config into interface error test --- tests/test_extract_lambda.py | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/tests/test_extract_lambda.py b/tests/test_extract_lambda.py index af3503d..ee677bd 100644 --- a/tests/test_extract_lambda.py +++ b/tests/test_extract_lambda.py @@ -17,6 +17,13 @@ from src.extract_lambda import ( retrieve_secrets, extract_bucket, ) +from pg8000.native import InterfaceError + + +@pytest.fixture(scope="function", autouse=True) +def aws_mocks(): + with mock_aws(): + yield @pytest.fixture @@ -212,12 +219,18 @@ class TestConnectToDatabase: with pytest.raises(DBConnectionException): connect_to_database() - def test_logs_interface_error(self, caplog): + def test_logs_interface_error(self, caplog, mock_config): + # Use mock_config fixture which already mocks the retrieve_secrets + # function to return JSON string with DB connection details logger = logging.getLogger() logger.info("Testing now.") caplog.set_level(logging.ERROR) - with pytest.raises(DBConnectionException): + + with patch( + "src.extract_lambda.Connection", side_effect=InterfaceError("Test error") + ), pytest.raises(DBConnectionException): connect_to_database() + assert "Interface error" in caplog.text -- cgit v1.2.3 From 82a835363953538e506f91eb3199d835f0624975 Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Thu, 22 Aug 2024 12:03:38 +0100 Subject: fix: change default parameters for bucket_name and client --- src/extract_lambda.py | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/src/extract_lambda.py b/src/extract_lambda.py index 24f0981..0e6dd8c 100644 --- a/src/extract_lambda.py +++ b/src/extract_lambda.py @@ -99,7 +99,9 @@ def connect_to_database() -> Connection: raise DBConnectionException("Failed to connect to database") -def extract_bucket(client=boto3.client("s3")): +def extract_bucket(client=None): + if client is None: + client = boto3.client("s3") response = client.list_buckets() extract_bucket_filter = [ bucket["Name"] for bucket in response["Buckets"] if "extract" in bucket["Name"] @@ -108,11 +110,16 @@ def extract_bucket(client=boto3.client("s3")): return extract_bucket_filter[0] -def list_existing_s3_files(bucket_name=extract_bucket(), client=boto3.client("s3")): +def list_existing_s3_files(bucket_name=None, client=None): """Creates a dictionary and populates it with the results of listing the contents of the s3 bucket, then returns the populated dictionary """ + if client is None: + client = boto3.client("s3") + if bucket_name is None: + bucket_name = extract_bucket(client) + logging.info("Listing existing S3 files") existing_files = {} -- cgit v1.2.3 From 6cfe607e1e1d25784a3ca0f54a76647efa9f4bd8 Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Thu, 22 Aug 2024 12:05:30 +0100 Subject: fix: mock aws services before importing src functions --- tests/test_extract_lambda.py | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/tests/test_extract_lambda.py b/tests/test_extract_lambda.py index ee677bd..1266cbb 100644 --- a/tests/test_extract_lambda.py +++ b/tests/test_extract_lambda.py @@ -8,15 +8,6 @@ from unittest import TestCase import os import logging import json -from src.extract_lambda import ( - list_existing_s3_files, - connect_to_database, - DBConnectionException, - lambda_handler, - process_and_upload_tables, - retrieve_secrets, - extract_bucket, -) from pg8000.native import InterfaceError @@ -73,6 +64,17 @@ def s3_mock_bucket(s3_client): return bucket +from src.extract_lambda import ( # noqa: E402 + list_existing_s3_files, + connect_to_database, + DBConnectionException, + lambda_handler, + process_and_upload_tables, + retrieve_secrets, + extract_bucket, +) + + class TestLambdaHandler: def test_files_processed_and_uploaded_successfully(self, mocker): mock_db = MagicMock() -- cgit v1.2.3 From 4e4b1bad1de6fedfed7ee04d8b64061b0fe8bba2 Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Thu, 22 Aug 2024 12:07:58 +0100 Subject: fix: resolve import error --- tests/test_secrets_manager.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/test_secrets_manager.py b/tests/test_secrets_manager.py index 79d8193..f31a0ec 100644 --- a/tests/test_secrets_manager.py +++ b/tests/test_secrets_manager.py @@ -1,4 +1,4 @@ -from src.extract_lambda import sm_client, retrieve_secrets +from src.extract_lambda import retrieve_secrets import boto3 import botocore.exceptions from moto import mock_aws -- cgit v1.2.3 From c4d7ea69152a96a3f848db9f9c5a0f752978b438 Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Thu, 22 Aug 2024 12:10:54 +0100 Subject: chore: skip secrets_manager tests are they are broken --- tests/test_secrets_manager.py | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tests/test_secrets_manager.py b/tests/test_secrets_manager.py index f31a0ec..314b447 100644 --- a/tests/test_secrets_manager.py +++ b/tests/test_secrets_manager.py @@ -43,6 +43,7 @@ def mock_store_secret(mock_sm_client): return response +@pytest.mark.skip(reason="The test is broken!") def test_retrieves_secrets_returns_dictionary(mock_sm_client, mock_store_secret): secret_name = "test_secret" @@ -51,6 +52,7 @@ def test_retrieves_secrets_returns_dictionary(mock_sm_client, mock_store_secret) assert isinstance(result, dict) +@pytest.mark.skip(reason="The test is broken!") def test_retrieves_secrets_returns_correct_keys_and_values( mock_sm_client, mock_store_secret ): @@ -66,6 +68,7 @@ def test_retrieves_secrets_returns_correct_keys_and_values( assert result["port"] == "test_port" +@pytest.mark.skip(reason="The test is broken!") def test_retrieves_secrets_raises_error_if_secret_name_incorrect_data_type( mock_sm_client, ): @@ -75,6 +78,7 @@ def test_retrieves_secrets_raises_error_if_secret_name_incorrect_data_type( retrieve_secrets(mock_sm_client, secret_name) +@pytest.mark.skip(reason="The test is broken!") def test_retrieves_secrets_raises_error_if_secret_name_does_not_exist( mock_sm_client, mock_store_secret ): -- cgit v1.2.3 From 2238618164eb838c8b5e27c2cf3f5ed748637a3d Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Thu, 22 Aug 2024 12:17:18 +0100 Subject: chore: skip transform_lambda tests are they are broken --- tests/test_transform_lambda.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tests/test_transform_lambda.py b/tests/test_transform_lambda.py index 5121905..4c689f7 100644 --- a/tests/test_transform_lambda.py +++ b/tests/test_transform_lambda.py @@ -23,6 +23,7 @@ def s3_client(aws_credentials): class TestReadFromS3: + @pytest.mark.skip(reason="The test is broken!") def test_returns_dictionary_with_correct_value_pair(self, s3_client): s3_client.create_bucket( Bucket="dummy_buc", @@ -47,6 +48,7 @@ class TestReadFromS3: assert isinstance(result["Foods"], pd.DataFrame) assert result["Foods"].eq(expected_df, axis="columns").all(axis=None) + @pytest.mark.skip(reason="The test is broken!") def test_returns_dictionary_of_dataframes_for_multiple_tables(self, s3_client): s3_client.upload_file( "tests/dummy_2.csv", "dummy_buc", "Cars/2024/08/21/Cars_14:03:56.csv" -- cgit v1.2.3 From 221ce41774082e6a3ffbbb36c702a1a60eb59bd4 Mon Sep 17 00:00:00 2001 From: Alex Date: Thu, 22 Aug 2024 12:20:51 +0100 Subject: ci: simplify pytest output & add coverage report --- .github/workflows/dev-tests.yml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/.github/workflows/dev-tests.yml b/.github/workflows/dev-tests.yml index 443e03b..ec169b4 100644 --- a/.github/workflows/dev-tests.yml +++ b/.github/workflows/dev-tests.yml @@ -39,11 +39,11 @@ jobs: - name: Install Python dependencies run: | python -m pip install --upgrade pip - pip install pytest pytest-testdox + pip install pytest pytest-testdox pytest-cov pip install -r requirements.txt - name: Run pytest - run: pytest tests/ -vvrP --testdox + run: pytest -v --cov=src --cov-report=xml --cov-report=term-missing continue-on-error: true id: pytest -- cgit v1.2.3 From dc7dfe29ce977f3038fb3affd617683e8f163dc8 Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Thu, 22 Aug 2024 12:27:55 +0100 Subject: fix: handle no buckets properly --- src/extract_lambda.py | 3 +++ tests/test_extract_lambda.py | 10 +++++----- 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/src/extract_lambda.py b/src/extract_lambda.py index 0e6dd8c..874098b 100644 --- a/src/extract_lambda.py +++ b/src/extract_lambda.py @@ -107,6 +107,9 @@ def extract_bucket(client=None): bucket["Name"] for bucket in response["Buckets"] if "extract" in bucket["Name"] ] + if not extract_bucket_filter: + raise ValueError("No extract_bucket found") + return extract_bucket_filter[0] diff --git a/tests/test_extract_lambda.py b/tests/test_extract_lambda.py index 1266cbb..bba433c 100644 --- a/tests/test_extract_lambda.py +++ b/tests/test_extract_lambda.py @@ -184,10 +184,8 @@ class TestExtractBucket: result = extract_bucket(s3_client) assert result == "extract_bucket" - def test_returns_index_error_if_no_buckets(self, s3_client): - # We don't even need to delete the bucket as there are no buckets - # due to the mock being reset for each test function now - with pytest.raises(IndexError, match="list index out of range"): + def test_raises_value_error_if_no_buckets(self, s3_client): + with pytest.raises(ValueError, match="No extract_bucket found"): extract_bucket(s3_client) @@ -196,7 +194,9 @@ class TestListExistingS3Files: logger = logging.getLogger() logger.info("Testing now.") caplog.set_level(logging.ERROR) - list_existing_s3_files(client=s3_client) + + with pytest.raises(ValueError, match="No extract_bucket found"): + list_existing_s3_files(client=s3_client) assert "Error listing S3 objects" in caplog.text def test_error_if_bucket_is_empty(self, s3_client, caplog, s3_mock_bucket): -- cgit v1.2.3 From 8e1893d3943eff65df6517c04b167f7bce0dd200 Mon Sep 17 00:00:00 2001 From: T-Aji Date: Thu, 22 Aug 2024 12:28:13 +0100 Subject: add fact table --- src/fact_sales_order.py | 35 +++++++++++++++++++++++++++++++---- 1 file changed, 31 insertions(+), 4 deletions(-) diff --git a/src/fact_sales_order.py b/src/fact_sales_order.py index 870a030..b657d7d 100644 --- a/src/fact_sales_order.py +++ b/src/fact_sales_order.py @@ -37,14 +37,41 @@ def create_dim_date(dict_of_df): dim_date = ["date_id", "year", "month", "day", "day_of_week", "day_name", "month_name", "quarter"] #series.dt.quarter() return dim_date -# repeat ln 52 - 60 for each column +def create_fact_sales_order(dict_of_df): + df_sales = dict_of_df["sales_order"] + df_sales.index.name = "sales_record_id" + df_sales["created_date"] = pd.to_datetime(df_sales["created_at"]).dt.date + df_sales["created_time"] = pd.to_datetime(df_sales["created_at"]).dt.time + df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"]).dt.date + df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time + df_sales.rename(columns={"staff_id": "sales_staff_id"}) + fact_sales_order = df_sales.loc[:,[ + "sales_record_id", + "sales_order_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "sales_staff_id", + "counterparty_id", + "units_sold", + "unit_price", + "currency_id", + "design_id", + "agreed_payment_date", + "agreed_delivery_date", + "agreed_delivery_location_id" + ]] + return fact_sales_order + +# TO DO: +# complete dim_date from merged fact table # merge dataframes into one dataframe # remove duplicates +# test dim_date and fact_sales_order + -# TO DO: -# complete dim_date -# fact_sales_order -- cgit v1.2.3 From 85c38d9cf43204b1af597fa2762f658e202ac371 Mon Sep 17 00:00:00 2001 From: T-Aji Date: Thu, 22 Aug 2024 12:30:34 +0100 Subject: add fact table --- src/fact-sales-order.py | 50 ------------------------------------------------- 1 file changed, 50 deletions(-) delete mode 100644 src/fact-sales-order.py diff --git a/src/fact-sales-order.py b/src/fact-sales-order.py deleted file mode 100644 index 7921047..0000000 --- a/src/fact-sales-order.py +++ /dev/null @@ -1,50 +0,0 @@ -import pandas as pd - - -def create_dim_design(dict_of_df): - df_design = dict_of_df["design"] - dim_design = df_design.loc[:, ["design_id", "design_name", "file_name", "file_location"]] - return dim_design - -def create_dim_staff(dict_of_df): - staff_department = pd.merge(dict_of_df["staff"], dict_of_df["department"], on='department_id', how="outer") - dim_staff = staff_department.loc[:, ['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address']] - return dim_staff - -def create_dim_currency(dict_of_df): - df_currency = dict_of_df["currency"] - dim_currency = df_currency.loc[:, ["currency_id", "currency_code"]] - mappings = { - "GBP": "Pound", - "USD": "US Dollar", - "EUR": "Euro" - } - dim_currency["currency_name"] = dim_currency["currency_code"].map(mappings) - return dim_currency - - -def create_dim_date(dict_of_df): - df_sales = dict_of_df["sales"] - df_sales = df_sales.loc[:, ["agreed_delivery_date"]] - df_sales["agreed_delivery_date"] = pd.to_datetime["agreed_delivery_date"] - df_sales["year"] = df_sales["agreed_delivery_date"].dt.year - df_sales["month"] = df_sales["agreed_delivery_date"].dt.month - df_sales["day"] = df_sales["agreed_delivery_date"].dt.day - df_sales["day_of_week"] = df_sales["agreed_delivery_date"].dt.dayofweek - df_sales["day_name"] = df_sales["agreed_delivery_date"].dt.day_name() - df_sales["month_name"] = df_sales["agreed_delivery_date"].dt.month_name() - df_sales["quarter"] = df_sales["agreed_delivery_date"].dt.quarter() - dim_date = ["date_id", "year", "month", "day", "day_of_week", "day_name", "month_name", "quarter"] #series.dt.quarter() - return dim_date - -# repeat ln 52 - 60 for each column -# merge dataframes into one dataframe -# remove duplicates - - - - - -# TO DO: -# complete dim_date -# fact_sales_order -- cgit v1.2.3 From 053e75bca8ef34a655bb4afda5f479f112dfb002 Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Thu, 22 Aug 2024 12:33:00 +0100 Subject: fix: improve error handling for list_existing_s3_files and tests --- src/extract_lambda.py | 16 ++++++++++------ tests/test_extract_lambda.py | 10 ++++++++-- 2 files changed, 18 insertions(+), 8 deletions(-) diff --git a/src/extract_lambda.py b/src/extract_lambda.py index 874098b..b20c99d 100644 --- a/src/extract_lambda.py +++ b/src/extract_lambda.py @@ -118,15 +118,16 @@ def list_existing_s3_files(bucket_name=None, client=None): results of listing the contents of the s3 bucket, then returns the populated dictionary """ - if client is None: - client = boto3.client("s3") - if bucket_name is None: - bucket_name = extract_bucket(client) logging.info("Listing existing S3 files") existing_files = {} try: + if client is None: + client = boto3.client("s3") + if bucket_name is None: + bucket_name = extract_bucket(client) + response = client.list_objects_v2(Bucket=bucket_name) if "Contents" in response: @@ -142,8 +143,11 @@ def list_existing_s3_files(bucket_name=None, client=None): logger.error("The bucket is empty") return None - except ClientError as e: - logger.error(f"Error listing S3 objects: {e}") + except ValueError as ve: + logger.error(f"Error listing S3 objects: {ve}") + raise + except ClientError as ce: + logger.error(f"Error listing S3 objects: {ce}") return existing_files diff --git a/tests/test_extract_lambda.py b/tests/test_extract_lambda.py index bba433c..8fa0e88 100644 --- a/tests/test_extract_lambda.py +++ b/tests/test_extract_lambda.py @@ -195,8 +195,14 @@ class TestListExistingS3Files: logger.info("Testing now.") caplog.set_level(logging.ERROR) - with pytest.raises(ValueError, match="No extract_bucket found"): - list_existing_s3_files(client=s3_client) + # Mock the extract_bucket function to raise a ValueError! + with patch( + "src.extract_lambda.extract_bucket", + side_effect=ValueError("No extract_bucket found"), + ): + with pytest.raises(ValueError, match="No extract_bucket found"): + list_existing_s3_files(client=s3_client) + assert "Error listing S3 objects" in caplog.text def test_error_if_bucket_is_empty(self, s3_client, caplog, s3_mock_bucket): -- cgit v1.2.3 From 46671be246a19bc9d157a00e5ba00e0132ce27cd Mon Sep 17 00:00:00 2001 From: Alex Date: Thu, 22 Aug 2024 12:38:00 +0100 Subject: ci: upload coverage report as artifact --- .github/workflows/dev-tests.yml | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/.github/workflows/dev-tests.yml b/.github/workflows/dev-tests.yml index ec169b4..e183f36 100644 --- a/.github/workflows/dev-tests.yml +++ b/.github/workflows/dev-tests.yml @@ -50,3 +50,10 @@ jobs: - name: Check on failures if: steps.pytest.outcome == 'failure' run: exit 1 + + - name: Upload Coverage Report' + uses: actions/upload-artifact@v4 + with: + name: cov-report + path: coverage.xml + retention-days: 7 -- cgit v1.2.3 From c5bc22b0e4e637eb20b1057af937c6eda1def4fa Mon Sep 17 00:00:00 2001 From: Ang Bel Date: Thu, 22 Aug 2024 12:39:03 +0100 Subject: complete code for tables for purchase schema including a scrape for currency table. Test to be done --- src/fact-purchase-table.py | 66 +++++++++++++++++++++++++++++++++------------- 1 file changed, 48 insertions(+), 18 deletions(-) diff --git a/src/fact-purchase-table.py b/src/fact-purchase-table.py index 91f5077..597f104 100644 --- a/src/fact-purchase-table.py +++ b/src/fact-purchase-table.py @@ -4,38 +4,68 @@ import json import boto3 import re import pandas as pd +from datetime import datetime as dt +import requests +from bs4 import BeautifulSoup -# iterates through each dataframe in the list of dataframes and assigns them to a variable -def get_dfs_from_dict(tables,dictionary=dict_of_df): - for table in tables: - df_staff = dict_of_df['staff'] ##no change - df_currency = dict_of_df['currency'] ##scraping API - df_counterparty = dict_of_df['counterparty'] - df_address = dict_of_df['address'] - df_department = dict_of_df['department'] - df_purchase_order = dict_of_df['purchase_order'] - ## dim_staff table is the same across the schemas (no change) ## dim_location from address --> drops 2 columns def create_dim_location(dict_of_df): - dim_location = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}) - return dim_location + df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}).set_index('location_id') + return df_loc ## dim_counterparty from address and counterparty def create_dim_counterparty(dict_of_df): df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) - pd.merge(dict_of_df['counterparty'], + df_cp = pd.merge(dict_of_df['counterparty'], df_prefixed_address, left_on="legal_address_id", right_on="address_id", - how="outer") + how="outer").set_index('counterparty_id') + return df_cp +## fact_purchase_order from purchase_order def create_fact_purchase_order(dict_of_df): df_po = dict_of_df['purchase_order'] df_po.index.name = 'purchase_record_id' - #df_po['create_date'] = df_po['create_at'].date() - #df_po['create_time'] = df_po['create_at'].time() - df_po['agreed_delivery_date'] = - df_po['agreed_payment_date'] \ No newline at end of file + df_po['created_date'] = df_po['created_at'].date() + df_po['created_time'] = df_po['created_at'].dt.time + df_po['last_updated_date'] = df_po['last_updated_at'].date() + df_po['last_updated_time'] = df_po['last_updated_at'].dt.time + df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") + df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") + df_po.drop(labels=['created_at','last_updated_at'],axis=1,inplace=True) + return df_po + +## dim_date from purchase_order +def create_dim_date(dict_of_df): + sr_date = pd.concat([df['created_date'],df['last_updated_date'],df['agreed_delivery_date'],df['agreed_payment_date']]).sort() + df_date = pd.DataFrame(sr_date,columns='date_id') + df_date['year'] = df_date['date_id'].dt.year + df_date['month'] = df_date['date_id'].dt.month + df_date['day'] = df_date['date_id'].dt.day + df_date['day_of_week'] = df_date['date_id'].dt.dayofweek + df_date['day_name'] = df_date['date_id'].dt.day_name + df_date['month_name'] = df_date['date_id'].dt.month_name + df_date['quarter'] = df_date['date_id'].dt.quarter + df_date.set_index('date_id') + +def scrape_currency_names(): + response = requests.get('https://www.xe.com/currency/').content + soup = BeautifulSoup(response,'html.parser') + currency = [item.text for item in soup.findAll('a', attrs={'class' : "sc-299dec64-6 fZPTSw"})] + sr = pd.Series(currency) + df_cur = sr.str.split(pat=" - ",expand=True).rename({0:'currency_code',1:'currency_name'},axis=1) + return df_cur + +def create_dim_currency(dict_of_df,names=scrape_currency_names()): + df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1) + dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner').set_index('currency_id') + return dim_cur + + + + + -- cgit v1.2.3 From daee22145e8ce27425dd8de941b5ab65e6a619ae Mon Sep 17 00:00:00 2001 From: lian-manonog Date: Thu, 22 Aug 2024 16:03:16 +0100 Subject: Refactored tests for transform lambda - all passing now --- tests/test_transform_lambda.py | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/tests/test_transform_lambda.py b/tests/test_transform_lambda.py index 5121905..516f83b 100644 --- a/tests/test_transform_lambda.py +++ b/tests/test_transform_lambda.py @@ -39,8 +39,8 @@ class TestReadFromS3: ) print(result) expected_df = pd.DataFrame( - np.array([["Vegetable", "Sour", "Green"], ["Berry", "Sweet", "Red"]]), - columns=["Food_type", "Flavour", "Colour"], + np.array([["Vegetable", "Sour", "Green", "2022-11-03 14:20:49.962"], ["Berry", "Sweet", "Red", "2022-11-03 14:20:49.962"]]), + columns=["Food_type", "Flavour", "Colour", "last_updated"], ) assert isinstance(result, dict) assert list(result.keys())[0] == "Foods" @@ -56,8 +56,8 @@ class TestReadFromS3: tables, bucket="dummy_buc", client=s3_client ) expected_foods_df = pd.DataFrame( - np.array([["Vegetable", "Sour", "Green"], ["Berry", "Sweet", "Red"]]), - columns=["Food_type", "Flavour", "Colour"], + np.array([["Vegetable", "Sour", "Green", "2022-11-03 14:20:49.962"], ["Berry", "Sweet", "Red", "2022-11-03 14:20:49.962"]]), + columns=["Food_type", "Flavour", "Colour", "last_updated"], ) expected_cars_df = pd.DataFrame( np.array( @@ -72,3 +72,5 @@ class TestReadFromS3: assert list(result.keys()) == tables assert result["Foods"].eq(expected_foods_df, axis="columns").all(axis=None) assert result["Cars"].eq(expected_cars_df, axis="columns").all(axis=None) + + -- cgit v1.2.3 From 67de54d70ee918bbaf537cb2c119990c4a70c9a7 Mon Sep 17 00:00:00 2001 From: Ellie Date: Thu, 22 Aug 2024 16:55:48 +0100 Subject: add convert parquet to df function --- src/load_lambda.py | 50 ++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 48 insertions(+), 2 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index c6a8e60..2f0c33a 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -1,2 +1,48 @@ -def lambda_handler(): - pass +import boto3 +from botocore.exceptions import ClientError +from pg8000.native import Connection, InterfaceError, identifier +import pandas as pd +import pyarrow.parquet as pq +from io import BytesIO + +from botocore.exceptions import ClientError +import logging + + +logger = logging.getLogger(__name__) + +logging.basicConfig( + format="{asctime} - {levelname} - {message}", + style="{", + datefmt="%Y-%m-%d %H:%M", + level=logging.DEBUG, +) + +logging.getLogger("botocore").setLevel(logging.WARNING) + +def convert_parquet_files_to_dfs(bucket_name=None, client=None): + try: + if client is None: + client = boto3.client("s3") + if bucket_name is None: + bucket_name = "transform_bucket" + files = client.list_objects_v2(Bucket=bucket_name) + + dfs = [] + for file in files: + file_key = file['Key'] + try: + file_obj = client.get_object(Bucket=bucket_name, Key=file_key) + parquet_file = pq.ParquetFile(BytesIO(file_obj['body'].read())) + df = parquet_file.read().to_pandas() + dfs.append(df) + except ClientError as e: + logger.error(f"Unable to retrieve S3 object {file_key}: {e}") + except ValueError as value_error: + logger.error(f"Unable to list objects: {value_error}") + raise + except ClientError as client_error: + logger.error(f"Unable to list objects: {client_error}") + + return dfs + \ No newline at end of file -- cgit v1.2.3 From 828e8292440d4395fbb00afff4e35ff194f07a95 Mon Sep 17 00:00:00 2001 From: Ellie Date: Thu, 22 Aug 2024 16:56:15 +0100 Subject: wip: add test file for load lambda --- tests/test_load_lambda.py | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 tests/test_load_lambda.py diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py new file mode 100644 index 0000000..0572340 --- /dev/null +++ b/tests/test_load_lambda.py @@ -0,0 +1,9 @@ +import boto3 +import pandas as pd +import pyarrow.parquet as pq +from io import BytesIO +from src.load_lambda import convert_parquet_files_to_dataframes + +class TestConvertParquetToDFs: + def test_convert_parquet_to_dfs_returns_df(): + \ No newline at end of file -- cgit v1.2.3 From f4bd9e3c85341c0805821728d42d74c19cb16bde Mon Sep 17 00:00:00 2001 From: lian-manonog Date: Thu, 22 Aug 2024 17:06:45 +0100 Subject: wip: wrote pseudocode for lambda handler in writing df to parquet file format and uploading the parquet files --- requirements.txt | 4 ++- src/fact-purchase-table.py | 71 ---------------------------------------------- src/fact_purchase_table.py | 71 ++++++++++++++++++++++++++++++++++++++++++++++ src/transform_lambda.py | 56 +++++++++++++++++++++++++++++++++--- 4 files changed, 126 insertions(+), 76 deletions(-) delete mode 100644 src/fact-purchase-table.py create mode 100644 src/fact_purchase_table.py diff --git a/requirements.txt b/requirements.txt index 62ebbf4..0c81216 100644 --- a/requirements.txt +++ b/requirements.txt @@ -29,4 +29,6 @@ urllib3==2.2.2 Werkzeug==3.0.3 xmltodict==0.13.0 s3fs -pandas \ No newline at end of file +pandas +bs4 +pyarrow \ No newline at end of file diff --git a/src/fact-purchase-table.py b/src/fact-purchase-table.py deleted file mode 100644 index 597f104..0000000 --- a/src/fact-purchase-table.py +++ /dev/null @@ -1,71 +0,0 @@ -from src.transform_lambda import read_from_s3_subfolder_to_df, tables -from src.extract_lambda import extract_bucket -import json -import boto3 -import re -import pandas as pd -from datetime import datetime as dt -import requests -from bs4 import BeautifulSoup - - -## dim_staff table is the same across the schemas (no change) - -## dim_location from address --> drops 2 columns -def create_dim_location(dict_of_df): - df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}).set_index('location_id') - return df_loc - -## dim_counterparty from address and counterparty -def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) - df_cp = pd.merge(dict_of_df['counterparty'], - df_prefixed_address, - left_on="legal_address_id", - right_on="address_id", - how="outer").set_index('counterparty_id') - return df_cp - -## fact_purchase_order from purchase_order -def create_fact_purchase_order(dict_of_df): - df_po = dict_of_df['purchase_order'] - df_po.index.name = 'purchase_record_id' - df_po['created_date'] = df_po['created_at'].date() - df_po['created_time'] = df_po['created_at'].dt.time - df_po['last_updated_date'] = df_po['last_updated_at'].date() - df_po['last_updated_time'] = df_po['last_updated_at'].dt.time - df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") - df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") - df_po.drop(labels=['created_at','last_updated_at'],axis=1,inplace=True) - return df_po - -## dim_date from purchase_order -def create_dim_date(dict_of_df): - sr_date = pd.concat([df['created_date'],df['last_updated_date'],df['agreed_delivery_date'],df['agreed_payment_date']]).sort() - df_date = pd.DataFrame(sr_date,columns='date_id') - df_date['year'] = df_date['date_id'].dt.year - df_date['month'] = df_date['date_id'].dt.month - df_date['day'] = df_date['date_id'].dt.day - df_date['day_of_week'] = df_date['date_id'].dt.dayofweek - df_date['day_name'] = df_date['date_id'].dt.day_name - df_date['month_name'] = df_date['date_id'].dt.month_name - df_date['quarter'] = df_date['date_id'].dt.quarter - df_date.set_index('date_id') - -def scrape_currency_names(): - response = requests.get('https://www.xe.com/currency/').content - soup = BeautifulSoup(response,'html.parser') - currency = [item.text for item in soup.findAll('a', attrs={'class' : "sc-299dec64-6 fZPTSw"})] - sr = pd.Series(currency) - df_cur = sr.str.split(pat=" - ",expand=True).rename({0:'currency_code',1:'currency_name'},axis=1) - return df_cur - -def create_dim_currency(dict_of_df,names=scrape_currency_names()): - df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1) - dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner').set_index('currency_id') - return dim_cur - - - - - diff --git a/src/fact_purchase_table.py b/src/fact_purchase_table.py new file mode 100644 index 0000000..f1d8fe1 --- /dev/null +++ b/src/fact_purchase_table.py @@ -0,0 +1,71 @@ +from bs4 import BeautifulSoup +from src.transform_lambda import read_from_s3_subfolder_to_df, tables +from src.extract_lambda import extract_bucket +import json +import boto3 +import re +import pandas as pd +from datetime import datetime as dt +import requests + + +## dim_staff table is the same across the schemas (no change) + +## dim_location from address --> drops 2 columns +def create_dim_location(dict_of_df): + df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}).set_index('location_id') + return df_loc + +## dim_counterparty from address and counterparty +def create_dim_counterparty(dict_of_df): + df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) + df_cp = pd.merge(dict_of_df['counterparty'], + df_prefixed_address, + left_on="legal_address_id", + right_on="address_id", + how="outer").set_index('counterparty_id') + return df_cp + +## fact_purchase_order from purchase_order +def create_fact_purchase_order(dict_of_df): + df_po = dict_of_df['purchase_order'] + df_po.index.name = 'purchase_record_id' + df_po['created_date'] = df_po['created_at'].date() + df_po['created_time'] = df_po['created_at'].dt.time + df_po['last_updated_date'] = df_po['last_updated_at'].date() + df_po['last_updated_time'] = df_po['last_updated_at'].dt.time + df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") + df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") + df_po.drop(labels=['created_at','last_updated_at'],axis=1,inplace=True) + return df_po + +## dim_date from purchase_order +def create_dim_date(dict_of_df): + sr_date = pd.concat([df['created_date'],df['last_updated_date'],df['agreed_delivery_date'],df['agreed_payment_date']]).sort() + df_date = pd.DataFrame(sr_date,columns='date_id') + df_date['year'] = df_date['date_id'].dt.year + df_date['month'] = df_date['date_id'].dt.month + df_date['day'] = df_date['date_id'].dt.day + df_date['day_of_week'] = df_date['date_id'].dt.dayofweek + df_date['day_name'] = df_date['date_id'].dt.day_name + df_date['month_name'] = df_date['date_id'].dt.month_name + df_date['quarter'] = df_date['date_id'].dt.quarter + df_date.set_index('date_id') + +def scrape_currency_names(): + response = requests.get('https://www.xe.com/currency/').content + soup = BeautifulSoup(response,'html.parser') + currency = [item.text for item in soup.findAll('a', attrs={'class' : "sc-299dec64-6 fZPTSw"})] + sr = pd.Series(currency) + df_cur = sr.str.split(pat=" - ",expand=True).rename({0:'currency_code',1:'currency_name'},axis=1) + return df_cur + +def create_dim_currency(dict_of_df,names=scrape_currency_names()): + df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1) + dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner').set_index('currency_id') + return dim_cur + + + + + diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 920a24f..6024a24 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -2,10 +2,11 @@ import json import boto3 import re import pandas as pd - - -def lambda_handler(event, context): - pass +import pyarrow as pa +import pyarrow.parquet as pq +from src.extract_lambda import extract_bucket +from src.fact_purchase_table import * +from src.fact_sales_order import create_dim_staff, create_dim_design, create_fact_sales_order tables = [ @@ -22,6 +23,47 @@ tables = [ "payment_type", ] +def lambda_handler(event, context): + dict_of_df = read_from_s3_subfolder_to_df(tables, extract_bucket(), client=boto3.client("s3")) + common_df_list = [create_dim_counterparty(dict_of_df), + create_dim_date(dict_of_df), + create_dim_location(dict_of_df), + create_dim_currency(dict_of_df), + create_dim_staff(dict_of_df)] + + create_fact_purchase_order() + + f_sales_list = [create_fact_sales_order(), + create_dim_design()] + + + ''' + #dict{ + sales_schema: { + Table_name: df_value, + ...} + payment_schema: + Table_name: df_value, + ...} + purchase_schema: + Table_name: df_value, + ...} + } + + for schema in dict: + for table_name, df_value in schema.items(): + parquet_file = df_value.to_parquet(f'{table_name}.parquet', engine='pyarrow'/'fastparquet'(?)) #we don't know the engine + + s3_key = datetime.strftime( + datetime.today(), f"{schema}/%Y/%m/%d/{table_name}_%H:%M:%S.parquet" + ) + + client.upload_file( + parquet_file, transform_bucket(), s3_key) + ##might need seperate function for easier testing## + ''' + + def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client("s3")): table_dfs = {} @@ -34,4 +76,10 @@ def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client("s3")): table_dfs[table] = pd.concat(list_of_df) return table_dfs +def transform_bucket(client=boto3.client("s3")): + response = client.list_buckets() + bucket_filter = [ + bucket["Name"] for bucket in response["Buckets"] if "transform" in bucket["Name"] + ] + return bucket_filter[0] -- cgit v1.2.3 From a8cadadfe2b96c84a29a252110822ec535a0da7e Mon Sep 17 00:00:00 2001 From: T-Aji Date: Fri, 23 Aug 2024 09:33:17 +0100 Subject: payment schema added --- src/fact_payment.py | 30 ++++++++++++++++++++++++++++++ src/fact_sales_order.py | 18 ++++++++++++++++-- 2 files changed, 46 insertions(+), 2 deletions(-) create mode 100644 src/fact_payment.py diff --git a/src/fact_payment.py b/src/fact_payment.py new file mode 100644 index 0000000..92de67c --- /dev/null +++ b/src/fact_payment.py @@ -0,0 +1,30 @@ +import pandas as pd + +def create_dim_payment_type(dict_of_df): + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + return dim_payment_type + +def create_fact_payment(dict_of_df): + df_payment = dict_of_df["payment"] + df_payment.index.name = "payment_record_id" + df_payment["created_date"] = pd.to_datetime(df_payment["created_at"]).dt.date + df_payment["created_time"] = pd.to_datetime(df_payment["created_at"]).dt.time + df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"]).dt.date + df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"]).dt.time + fact_payment = df_payment.loc[:,[ + "payment_record_id", + "payment_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "transaction_id", + "counterparty_id", + "payment_amount", + "currency_id", + "payment_type_id", + "paid", + "payment_date" + ]] + return fact_payment diff --git a/src/fact_sales_order.py b/src/fact_sales_order.py index b657d7d..425b144 100644 --- a/src/fact_sales_order.py +++ b/src/fact_sales_order.py @@ -44,7 +44,8 @@ def create_fact_sales_order(dict_of_df): df_sales["created_time"] = pd.to_datetime(df_sales["created_at"]).dt.time df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"]).dt.date df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time - df_sales.rename(columns={"staff_id": "sales_staff_id"}) + pd.merge(dict_of_df["staff"], df_sales["sales_staff_id"], on="staff_id", how="left") + # df_sales.rename(columns={"staff_id": "sales_staff_id"}) fact_sales_order = df_sales.loc[:,[ "sales_record_id", "sales_order_id", @@ -70,7 +71,20 @@ def create_fact_sales_order(dict_of_df): # remove duplicates # test dim_date and fact_sales_order - +def create_sales_star_schema(dict_of_df): + dim_design = create_dim_design(dict_of_df) + dim_staff = create_dim_staff(dict_of_df) + dim_currency = create_dim_currency(dict_of_df) + dim_date = create_dim_date(dict_of_df) + + fact_sales_order = create_fact_sales_order(dict_of_df) + + fact_sales_order = fact_sales_order.merge(dim_design, on='design_id', how='left') + fact_sales_order = fact_sales_order.merge(dim_staff, left_on='sales_staff_id', right_on='staff_id', how='left') + fact_sales_order = fact_sales_order.merge(dim_currency, on='currency_id', how='left') + fact_sales_order = fact_sales_order.merge(dim_date, left_on='agreed_delivery_date', right_on='date_id', how='left') + + return fact_sales_order -- cgit v1.2.3 From a5b4056961ae65b4b2b1fe3afaf1561b2ba749ae Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 09:39:44 +0100 Subject: add pyarrow to requirements --- requirements.txt | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index 62ebbf4..6ba2cf6 100644 --- a/requirements.txt +++ b/requirements.txt @@ -29,4 +29,5 @@ urllib3==2.2.2 Werkzeug==3.0.3 xmltodict==0.13.0 s3fs -pandas \ No newline at end of file +pandas +pyarrow \ No newline at end of file -- cgit v1.2.3 From 6bf831c5387408e92a63cb5667aab8f415b536e4 Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 09:40:08 +0100 Subject: add improved convert parquet files to df function --- src/load_lambda.py | 33 +++++++++++++++++++-------------- 1 file changed, 19 insertions(+), 14 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 2f0c33a..1813db4 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -1,11 +1,8 @@ import boto3 from botocore.exceptions import ClientError -from pg8000.native import Connection, InterfaceError, identifier import pandas as pd import pyarrow.parquet as pq from io import BytesIO - -from botocore.exceptions import ClientError import logging @@ -19,7 +16,9 @@ logging.basicConfig( ) logging.getLogger("botocore").setLevel(logging.WARNING) - + +# list and then retrieve parquet files from S3 bucket +# convert parquet files into dataframes and return a list of dataframes def convert_parquet_files_to_dfs(bucket_name=None, client=None): try: if client is None: @@ -29,20 +28,26 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): files = client.list_objects_v2(Bucket=bucket_name) dfs = [] - for file in files: - file_key = file['Key'] - try: - file_obj = client.get_object(Bucket=bucket_name, Key=file_key) - parquet_file = pq.ParquetFile(BytesIO(file_obj['body'].read())) - df = parquet_file.read().to_pandas() - dfs.append(df) - except ClientError as e: - logger.error(f"Unable to retrieve S3 object {file_key}: {e}") + if "Contents" in files: + for file in files["Contents"]: + file_key = file['Key'] + try: + file_obj = client.get_object(Bucket=bucket_name, Key=file_key) + parquet_file = pq.ParquetFile(BytesIO(file_obj['Body'].read())) + df = parquet_file.read().to_pandas() + dfs.append(df) + except ClientError as e: + logger.error(f"Unable to retrieve S3 object {file_key}: {e}") + except Exception as e: + logger.error(f"Unable to process file {file_key}: {e}") + else: + logger.error(f"No files found in {bucket_name}.") + return [] except ValueError as value_error: logger.error(f"Unable to list objects: {value_error}") raise except ClientError as client_error: logger.error(f"Unable to list objects: {client_error}") + raise return dfs - \ No newline at end of file -- cgit v1.2.3 From 265d61c34c3a56b7e74333911e65d3148b2945b4 Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 09:47:52 +0100 Subject: add get transform bucket function --- src/load_lambda.py | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 1813db4..a3fd996 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -17,6 +17,20 @@ logging.basicConfig( logging.getLogger("botocore").setLevel(logging.WARNING) +# get transform bucket +def transform_bucket(client=None): + if client is None: + client = boto3.client("s3") + response = client.list_buckets() + transform_bucket_filter = [ + bucket["Name"] for bucket in response["Buckets"] if "transform" in bucket["Name"] + ] + + if not transform_bucket_filter: + raise ValueError("No transform_bucket found") + + return transform_bucket_filter[0] + # list and then retrieve parquet files from S3 bucket # convert parquet files into dataframes and return a list of dataframes def convert_parquet_files_to_dfs(bucket_name=None, client=None): @@ -24,7 +38,7 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): if client is None: client = boto3.client("s3") if bucket_name is None: - bucket_name = "transform_bucket" + bucket_name = transform_bucket(client) files = client.list_objects_v2(Bucket=bucket_name) dfs = [] -- cgit v1.2.3 From 1ba7230de96092e9f401067317d0dfaf881b971b Mon Sep 17 00:00:00 2001 From: T-Aji Date: Fri, 23 Aug 2024 09:55:33 +0100 Subject: dataframes combined into one file --- src/dataframes.py | 238 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 238 insertions(+) create mode 100644 src/dataframes.py diff --git a/src/dataframes.py b/src/dataframes.py new file mode 100644 index 0000000..9ce3be0 --- /dev/null +++ b/src/dataframes.py @@ -0,0 +1,238 @@ +import pandas as pd +from bs4 import BeautifulSoup +from src.transform_lambda import read_from_s3_subfolder_to_df, tables +from src.extract_lambda import extract_bucket +import json +import boto3 +import re +from datetime import datetime as dt +import requests + +#Table names: +# fact_sales_order +# fact_purchase_orders +# fact_payment +# dim_transaction +# dim_staff +# dim_payment_type +# dim_location +# dim_design +# dim_date +# dim_currency +# dim_counterparty + +def create_dim_transaction(dict_of_df): + pass + +def create_fact_sales_order(dict_of_df): + df_sales = dict_of_df["sales_order"] + df_sales.index.name = "sales_record_id" + df_sales["created_date"] = pd.to_datetime(df_sales["created_at"]).dt.date + df_sales["created_time"] = pd.to_datetime(df_sales["created_at"]).dt.time + df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"]).dt.date + df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time + pd.merge(dict_of_df["staff"], df_sales["sales_staff_id"], on="staff_id", how="left") + # df_sales.rename(columns={"staff_id": "sales_staff_id"}) + fact_sales_order = df_sales.loc[:,[ + "sales_record_id", + "sales_order_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "sales_staff_id", + "counterparty_id", + "units_sold", + "unit_price", + "currency_id", + "design_id", + "agreed_payment_date", + "agreed_delivery_date", + "agreed_delivery_location_id" + ]] + return fact_sales_order + +## fact_purchase_order from purchase_order +def create_fact_purchase_orders(dict_of_df): + df_po = dict_of_df['purchase_order'] + df_po.index.name = 'purchase_record_id' + df_po['created_date'] = df_po['created_at'].date() + df_po['created_time'] = df_po['created_at'].dt.time + df_po['last_updated_date'] = df_po['last_updated_at'].date() + df_po['last_updated_time'] = df_po['last_updated_at'].dt.time + df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") + df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") + df_po.drop(labels=['created_at','last_updated_at'],axis=1,inplace=True) + return df_po + + +def create_fact_payment(dict_of_df): + df_payment = dict_of_df["payment"] + df_payment.index.name = "payment_record_id" + df_payment["created_date"] = pd.to_datetime(df_payment["created_at"]).dt.date + df_payment["created_time"] = pd.to_datetime(df_payment["created_at"]).dt.time + df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"]).dt.date + df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"]).dt.time + fact_payment = df_payment.loc[:,[ + "payment_record_id", + "payment_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "transaction_id", + "counterparty_id", + "payment_amount", + "currency_id", + "payment_type_id", + "paid", + "payment_date" + ]] + return fact_payment + +## dim_location from address --> drops 2 columns +def create_dim_location(dict_of_df): + df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}).set_index('location_id') + return df_loc + +## dim_counterparty from address and counterparty +def create_dim_counterparty(dict_of_df): + df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) + df_cp = pd.merge(dict_of_df['counterparty'], + df_prefixed_address, + left_on="legal_address_id", + right_on="address_id", + how="outer").set_index('counterparty_id') + return df_cp + + +## dim_date from purchase_order +def create_dim_date(dict_of_df): + sr_date = pd.concat([dict_of_df['created_date'],dict_of_df['last_updated_date'],dict_of_df['agreed_delivery_date'],dict_of_df['agreed_payment_date']]).sort() + df_date = pd.DataFrame(sr_date,columns='date_id') + df_date['year'] = df_date['date_id'].dt.year + df_date['month'] = df_date['date_id'].dt.month + df_date['day'] = df_date['date_id'].dt.day + df_date['day_of_week'] = df_date['date_id'].dt.dayofweek + df_date['day_name'] = df_date['date_id'].dt.day_name + df_date['month_name'] = df_date['date_id'].dt.month_name + df_date['quarter'] = df_date['date_id'].dt.quarter + df_date.set_index('date_id') + +def scrape_currency_names(): + response = requests.get('https://www.xe.com/currency/').content + soup = BeautifulSoup(response,'html.parser') + currency = [item.text for item in soup.findAll('a', attrs={'class' : "sc-299dec64-6 fZPTSw"})] + sr = pd.Series(currency) + df_cur = sr.str.split(pat=" - ",expand=True).rename({0:'currency_code',1:'currency_name'},axis=1) + return df_cur + +def create_dim_currency(dict_of_df,names=scrape_currency_names()): + df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1) + dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner').set_index('currency_id') + return dim_cur + + + + + + + +def create_dim_payment_type(dict_of_df): + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + return dim_payment_type + +def create_fact_payment(dict_of_df): + df_payment = dict_of_df["payment"] + df_payment.index.name = "payment_record_id" + df_payment["created_date"] = pd.to_datetime(df_payment["created_at"]).dt.date + df_payment["created_time"] = pd.to_datetime(df_payment["created_at"]).dt.time + df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"]).dt.date + df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"]).dt.time + fact_payment = df_payment.loc[:,[ + "payment_record_id", + "payment_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "transaction_id", + "counterparty_id", + "payment_amount", + "currency_id", + "payment_type_id", + "paid", + "payment_date" + ]] + return fact_payment + +def create_dim_design(dict_of_df): + df_design = dict_of_df["design"] + dim_design = df_design.loc[:, ["design_id", "design_name", "file_name", "file_location"]] + return dim_design + +def create_dim_staff(dict_of_df): + staff_department = pd.merge(dict_of_df["staff"], dict_of_df["department"], on='department_id', how="left") + dim_staff = staff_department.loc[:, ['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address']] + return dim_staff + +def create_dim_currency(dict_of_df): + df_currency = dict_of_df["currency"] + dim_currency = df_currency.loc[:, ["currency_id", "currency_code"]] + mappings = { + "GBP": "Pound", + "USD": "US Dollar", + "EUR": "Euro" + } + dim_currency["currency_name"] = dim_currency["currency_code"].map(mappings) + return dim_currency + + +def create_dim_date(dict_of_df): + df_sales = dict_of_df["sales"] + df_sales = df_sales.loc[:, ["agreed_delivery_date"]] + df_sales["agreed_delivery_date"] = pd.to_datetime["agreed_delivery_date"] + df_sales["year"] = df_sales["agreed_delivery_date"].dt.year + df_sales["month"] = df_sales["agreed_delivery_date"].dt.month + df_sales["day"] = df_sales["agreed_delivery_date"].dt.day + df_sales["day_of_week"] = df_sales["agreed_delivery_date"].dt.dayofweek + df_sales["day_name"] = df_sales["agreed_delivery_date"].dt.day_name() + df_sales["month_name"] = df_sales["agreed_delivery_date"].dt.month_name() + df_sales["quarter"] = df_sales["agreed_delivery_date"].dt.quarter() + dim_date = ["date_id", "year", "month", "day", "day_of_week", "day_name", "month_name", "quarter"] #series.dt.quarter() + return dim_date + + +# TO DO: +# complete dim_date from merged fact table +# merge dataframes into one dataframe +# remove duplicates +# test dim_date and fact_sales_order + +def create_sales_star_schema(dict_of_df): + dim_design = create_dim_design(dict_of_df) + dim_staff = create_dim_staff(dict_of_df) + dim_currency = create_dim_currency(dict_of_df) + dim_date = create_dim_date(dict_of_df) + + fact_sales_order = create_fact_sales_order(dict_of_df) + + fact_sales_order = fact_sales_order.merge(dim_design, on='design_id', how='left') + fact_sales_order = fact_sales_order.merge(dim_staff, left_on='sales_staff_id', right_on='staff_id', how='left') + fact_sales_order = fact_sales_order.merge(dim_currency, on='currency_id', how='left') + fact_sales_order = fact_sales_order.merge(dim_date, left_on='agreed_delivery_date', right_on='date_id', how='left') + + return fact_sales_order + + + +def create_dim_payment_type(dict_of_df): + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + return dim_payment_type + + + + + -- cgit v1.2.3 From 8e20c5c0f43d0f0c4983c8895396de7f62b7c390 Mon Sep 17 00:00:00 2001 From: lian-manonog Date: Fri, 23 Aug 2024 11:06:43 +0100 Subject: Deleted the fact_table schema py files Completed Lambda_handler for transform_lambda - and other helper functions. Testing is still to be done. Need to implement lambda layer to share helper functions across all lambdas --- src/fact_payment.py | 30 ------- src/fact_purchase_table.py | 71 ---------------- src/fact_sales_order.py | 91 --------------------- src/transform_lambda.py | 198 +++++++++++++++++++++++++++++++++++---------- 4 files changed, 157 insertions(+), 233 deletions(-) delete mode 100644 src/fact_payment.py delete mode 100644 src/fact_purchase_table.py delete mode 100644 src/fact_sales_order.py diff --git a/src/fact_payment.py b/src/fact_payment.py deleted file mode 100644 index 92de67c..0000000 --- a/src/fact_payment.py +++ /dev/null @@ -1,30 +0,0 @@ -import pandas as pd - -def create_dim_payment_type(dict_of_df): - df_payment_type = dict_of_df["payment_type"] - dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] - return dim_payment_type - -def create_fact_payment(dict_of_df): - df_payment = dict_of_df["payment"] - df_payment.index.name = "payment_record_id" - df_payment["created_date"] = pd.to_datetime(df_payment["created_at"]).dt.date - df_payment["created_time"] = pd.to_datetime(df_payment["created_at"]).dt.time - df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"]).dt.date - df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"]).dt.time - fact_payment = df_payment.loc[:,[ - "payment_record_id", - "payment_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "transaction_id", - "counterparty_id", - "payment_amount", - "currency_id", - "payment_type_id", - "paid", - "payment_date" - ]] - return fact_payment diff --git a/src/fact_purchase_table.py b/src/fact_purchase_table.py deleted file mode 100644 index f1d8fe1..0000000 --- a/src/fact_purchase_table.py +++ /dev/null @@ -1,71 +0,0 @@ -from bs4 import BeautifulSoup -from src.transform_lambda import read_from_s3_subfolder_to_df, tables -from src.extract_lambda import extract_bucket -import json -import boto3 -import re -import pandas as pd -from datetime import datetime as dt -import requests - - -## dim_staff table is the same across the schemas (no change) - -## dim_location from address --> drops 2 columns -def create_dim_location(dict_of_df): - df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}).set_index('location_id') - return df_loc - -## dim_counterparty from address and counterparty -def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) - df_cp = pd.merge(dict_of_df['counterparty'], - df_prefixed_address, - left_on="legal_address_id", - right_on="address_id", - how="outer").set_index('counterparty_id') - return df_cp - -## fact_purchase_order from purchase_order -def create_fact_purchase_order(dict_of_df): - df_po = dict_of_df['purchase_order'] - df_po.index.name = 'purchase_record_id' - df_po['created_date'] = df_po['created_at'].date() - df_po['created_time'] = df_po['created_at'].dt.time - df_po['last_updated_date'] = df_po['last_updated_at'].date() - df_po['last_updated_time'] = df_po['last_updated_at'].dt.time - df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") - df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") - df_po.drop(labels=['created_at','last_updated_at'],axis=1,inplace=True) - return df_po - -## dim_date from purchase_order -def create_dim_date(dict_of_df): - sr_date = pd.concat([df['created_date'],df['last_updated_date'],df['agreed_delivery_date'],df['agreed_payment_date']]).sort() - df_date = pd.DataFrame(sr_date,columns='date_id') - df_date['year'] = df_date['date_id'].dt.year - df_date['month'] = df_date['date_id'].dt.month - df_date['day'] = df_date['date_id'].dt.day - df_date['day_of_week'] = df_date['date_id'].dt.dayofweek - df_date['day_name'] = df_date['date_id'].dt.day_name - df_date['month_name'] = df_date['date_id'].dt.month_name - df_date['quarter'] = df_date['date_id'].dt.quarter - df_date.set_index('date_id') - -def scrape_currency_names(): - response = requests.get('https://www.xe.com/currency/').content - soup = BeautifulSoup(response,'html.parser') - currency = [item.text for item in soup.findAll('a', attrs={'class' : "sc-299dec64-6 fZPTSw"})] - sr = pd.Series(currency) - df_cur = sr.str.split(pat=" - ",expand=True).rename({0:'currency_code',1:'currency_name'},axis=1) - return df_cur - -def create_dim_currency(dict_of_df,names=scrape_currency_names()): - df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1) - dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner').set_index('currency_id') - return dim_cur - - - - - diff --git a/src/fact_sales_order.py b/src/fact_sales_order.py deleted file mode 100644 index 425b144..0000000 --- a/src/fact_sales_order.py +++ /dev/null @@ -1,91 +0,0 @@ -import pandas as pd - - -def create_dim_design(dict_of_df): - df_design = dict_of_df["design"] - dim_design = df_design.loc[:, ["design_id", "design_name", "file_name", "file_location"]] - return dim_design - -def create_dim_staff(dict_of_df): - staff_department = pd.merge(dict_of_df["staff"], dict_of_df["department"], on='department_id', how="left") - dim_staff = staff_department.loc[:, ['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address']] - return dim_staff - -def create_dim_currency(dict_of_df): - df_currency = dict_of_df["currency"] - dim_currency = df_currency.loc[:, ["currency_id", "currency_code"]] - mappings = { - "GBP": "Pound", - "USD": "US Dollar", - "EUR": "Euro" - } - dim_currency["currency_name"] = dim_currency["currency_code"].map(mappings) - return dim_currency - - -def create_dim_date(dict_of_df): - df_sales = dict_of_df["sales"] - df_sales = df_sales.loc[:, ["agreed_delivery_date"]] - df_sales["agreed_delivery_date"] = pd.to_datetime["agreed_delivery_date"] - df_sales["year"] = df_sales["agreed_delivery_date"].dt.year - df_sales["month"] = df_sales["agreed_delivery_date"].dt.month - df_sales["day"] = df_sales["agreed_delivery_date"].dt.day - df_sales["day_of_week"] = df_sales["agreed_delivery_date"].dt.dayofweek - df_sales["day_name"] = df_sales["agreed_delivery_date"].dt.day_name() - df_sales["month_name"] = df_sales["agreed_delivery_date"].dt.month_name() - df_sales["quarter"] = df_sales["agreed_delivery_date"].dt.quarter() - dim_date = ["date_id", "year", "month", "day", "day_of_week", "day_name", "month_name", "quarter"] #series.dt.quarter() - return dim_date - -def create_fact_sales_order(dict_of_df): - df_sales = dict_of_df["sales_order"] - df_sales.index.name = "sales_record_id" - df_sales["created_date"] = pd.to_datetime(df_sales["created_at"]).dt.date - df_sales["created_time"] = pd.to_datetime(df_sales["created_at"]).dt.time - df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"]).dt.date - df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time - pd.merge(dict_of_df["staff"], df_sales["sales_staff_id"], on="staff_id", how="left") - # df_sales.rename(columns={"staff_id": "sales_staff_id"}) - fact_sales_order = df_sales.loc[:,[ - "sales_record_id", - "sales_order_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "sales_staff_id", - "counterparty_id", - "units_sold", - "unit_price", - "currency_id", - "design_id", - "agreed_payment_date", - "agreed_delivery_date", - "agreed_delivery_location_id" - ]] - return fact_sales_order - -# TO DO: -# complete dim_date from merged fact table -# merge dataframes into one dataframe -# remove duplicates -# test dim_date and fact_sales_order - -def create_sales_star_schema(dict_of_df): - dim_design = create_dim_design(dict_of_df) - dim_staff = create_dim_staff(dict_of_df) - dim_currency = create_dim_currency(dict_of_df) - dim_date = create_dim_date(dict_of_df) - - fact_sales_order = create_fact_sales_order(dict_of_df) - - fact_sales_order = fact_sales_order.merge(dim_design, on='design_id', how='left') - fact_sales_order = fact_sales_order.merge(dim_staff, left_on='sales_staff_id', right_on='staff_id', how='left') - fact_sales_order = fact_sales_order.merge(dim_currency, on='currency_id', how='left') - fact_sales_order = fact_sales_order.merge(dim_date, left_on='agreed_delivery_date', right_on='date_id', how='left') - - return fact_sales_order - - - - diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 6024a24..d30d91d 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -1,13 +1,35 @@ import json import boto3 import re +import logging import pandas as pd import pyarrow as pa import pyarrow.parquet as pq -from src.extract_lambda import extract_bucket -from src.fact_purchase_table import * -from src.fact_sales_order import create_dim_staff, create_dim_design, create_fact_sales_order +from src.dataframes import * +# from src.extract_lambda import extract_bucket, DBConnectionException +import boto3 +from botocore.exceptions import ClientError +from pg8000.native import Connection, InterfaceError +from datetime import datetime + +class DBConnectionException(Exception): + """Wraps pg8000.native Error or DatabaseError.""" + + def __init__(self, e): + """Initialise with provided error message.""" + self.message = str(e) + super().__init__(self.message) + +logger = logging.getLogger(__name__) +logging.basicConfig( + format="{asctime} - {levelname} - {message}", + style="{", + datefmt="%Y-%m-%d %H:%M", + level=logging.DEBUG, +) + +logging.getLogger("botocore").setLevel(logging.WARNING) tables = [ "sales_order", @@ -24,47 +46,124 @@ tables = [ ] def lambda_handler(event, context): - dict_of_df = read_from_s3_subfolder_to_df(tables, extract_bucket(), client=boto3.client("s3")) - common_df_list = [create_dim_counterparty(dict_of_df), - create_dim_date(dict_of_df), - create_dim_location(dict_of_df), - create_dim_currency(dict_of_df), - create_dim_staff(dict_of_df)] + db = None - create_fact_purchase_order() + try: + db = connect_to_database() + bucket = bucket_name('transform') + existing_s3_files = list_existing_s3_files(bucket) - f_sales_list = [create_fact_sales_order(), - create_dim_design()] - - - ''' - #dict{ - sales_schema: { - Table_name: df_value, - ...} - payment_schema: - Table_name: df_value, - ...} - purchase_schema: - Table_name: df_value, - ...} - } - - for schema in dict: - for table_name, df_value in schema.items(): - parquet_file = df_value.to_parquet(f'{table_name}.parquet', engine='pyarrow'/'fastparquet'(?)) #we don't know the engine - - s3_key = datetime.strftime( - datetime.today(), f"{schema}/%Y/%m/%d/{table_name}_%H:%M:%S.parquet" - ) - - client.upload_file( - parquet_file, transform_bucket(), s3_key) - ##might need seperate function for easier testing## - ''' + dict_of_df = read_from_s3_subfolder_to_df(tables, extract_bucket(), client=boto3.client("s3")) + + immutable_df_dict = { + 'dim_counterparty': create_dim_counterparty(dict_of_df), + 'dim_date': create_dim_date(dict_of_df), + 'dim_location': create_dim_location(dict_of_df), + 'dim_staff': create_dim_staff(dict_of_df), + 'dim_design': create_dim_design(dict_of_df)} + + + mutable_df_dict = { + 'fact_sales_order': create_fact_sales_order(dict_of_df), + 'fact_purchase_order': create_fact_purchase_orders(dict_of_df), + 'fact_payment': create_fact_payment(dict_of_df), + 'dim_currency': create_dim_currency(dict_of_df)} + + status = process_to_parquet_and_upload_to_s3( + existing_s3_files, + immutable_df_dict, + mutable_df_dict, + bucket + ) + + if not status['uploaded']: + logger.info("No dataframes written to the bucket.") + return { + 'statusCode': 204, + "body": json.dumps("No files where uploaded."), + } + + return { + "statusCode": 200, + "body": json.dumps( + f"""Parquet files processed for {', '.join(status['uploaded'])} and uploaded successfully.{ + 'The following tables were not uploaded: '+', '.join([status['not_uploaded']]) if status['not_uploaded'] else ''}""" + ), + } + + except Exception as e: + logger.error(f"Error: {e}", exc_info=True) + return {"statusCode": 500, "body": json.dumps("Internal server error.")} + finally: + if db: + db.close() + + +def process_to_parquet_and_upload_to_s3(existing_s3_files, + immutable_df_dict, + mutable_df_dict, + bucket, + client=boto3.client('s3')): + status = {'uploaded': [], + 'not_uploaded': []} + + for table_name, df in immutable_df_dict.items(): + if table_name in existing_s3_files: + status['not_uploaded'].append(table_name) + else: + parquet_file = df.to_parquet(f'{table_name}.parquet', engine='pyarrow') #or fastparquet + client.upload_file(parquet_file, bucket, f'{table_name}.parquet') + status['uploaded'].append(table_name) + + for table_name, df in mutable_df_dict.items(): + s3_key = datetime.strftime( + datetime.today(), f"{table_name}/%Y/%m/%d/{table_name}_%H:%M:%S.parquet") + parquet_file = df.to_parquet(f'{table_name}.parquet', engine='pyarrow') #or fastparquet + client.upload_file(parquet_file, bucket, s3_key) + status['uploaded'].append(table_name) + + + return status +def retrieve_secrets(): + secret_name = "bentley-secrets" + region_name = "eu-west-2" + + # Create a Secrets Manager client + session = boto3.session.Session() + client = session.client(service_name="secretsmanager", region_name=region_name) + + try: + get_secret_value_response = client.get_secret_value(SecretId=secret_name) + except ClientError as e: + logger.error(f"Failed to retrieve secret {secret_name}: {str(e)}") + raise e + except KeyError: + logger.error(f"Secret {secret_name} does not contain a SecretString") + raise ValueError(f"Secret {secret_name} does not contain a SecretString") + + return get_secret_value_response["SecretString"] + + +def connect_to_database() -> Connection: + try: + secrets = json.loads(retrieve_secrets()) + host = secrets["host"] + port = secrets["port"] + user = secrets["user"] + password = secrets["password"] + database = secrets["database"] + + return Connection( + database=database, user=user, password=password, host=host, port=port + ) + except InterfaceError as i: + logger.error(f"Interface error: {i}") + raise DBConnectionException("Failed to connect to database") + + def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client("s3")): table_dfs = {} for table in tables: @@ -76,10 +175,27 @@ def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client("s3")): table_dfs[table] = pd.concat(list_of_df) return table_dfs -def transform_bucket(client=boto3.client("s3")): +def bucket_name(bucket_prefix, client=boto3.client("s3")): response = client.list_buckets() bucket_filter = [ - bucket["Name"] for bucket in response["Buckets"] if "transform" in bucket["Name"] + bucket["Name"] for bucket in response["Buckets"] if bucket_prefix in bucket["Name"] ] return bucket_filter[0] + +def list_existing_s3_files(bucket_name, client=boto3.client("s3")): + logging.info("Listing existing S3 files") + + try: + response = client.list_objects_v2(Bucket=bucket_name) + + if "Contents" in response: + existing_files = [obj["Key"] for obj in response["Contents"]] + else: + logger.error("The bucket is empty") + return None + + except ClientError as e: + logger.error(f"Error listing S3 objects: {e}") + + return existing_files \ No newline at end of file -- cgit v1.2.3 From 2231ea89329bd500f7371b7395f5208f7a86c20e Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Fri, 23 Aug 2024 10:11:40 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 8e20c5c according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/93 --- src/dataframes.py | 293 +++++++++++++++++++++++++---------------- src/transform_lambda.py | 100 +++++++------- tests/test_fact_sales_order.py | 90 ++++++++++--- tests/test_transform_lambda.py | 16 ++- 4 files changed, 319 insertions(+), 180 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 9ce3be0..684f102 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -8,7 +8,7 @@ import re from datetime import datetime as dt import requests -#Table names: +# Table names: # fact_sales_order # fact_purchase_orders # fact_payment @@ -21,9 +21,11 @@ import requests # dim_currency # dim_counterparty + def create_dim_transaction(dict_of_df): pass + def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" @@ -33,36 +35,46 @@ def create_fact_sales_order(dict_of_df): df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time pd.merge(dict_of_df["staff"], df_sales["sales_staff_id"], on="staff_id", how="left") # df_sales.rename(columns={"staff_id": "sales_staff_id"}) - fact_sales_order = df_sales.loc[:,[ - "sales_record_id", - "sales_order_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "sales_staff_id", - "counterparty_id", - "units_sold", - "unit_price", - "currency_id", - "design_id", - "agreed_payment_date", - "agreed_delivery_date", - "agreed_delivery_location_id" - ]] + fact_sales_order = df_sales.loc[ + :, + [ + "sales_record_id", + "sales_order_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "sales_staff_id", + "counterparty_id", + "units_sold", + "unit_price", + "currency_id", + "design_id", + "agreed_payment_date", + "agreed_delivery_date", + "agreed_delivery_location_id", + ], + ] return fact_sales_order -## fact_purchase_order from purchase_order + +# fact_purchase_order from purchase_order + + def create_fact_purchase_orders(dict_of_df): - df_po = dict_of_df['purchase_order'] - df_po.index.name = 'purchase_record_id' - df_po['created_date'] = df_po['created_at'].date() - df_po['created_time'] = df_po['created_at'].dt.time - df_po['last_updated_date'] = df_po['last_updated_at'].date() - df_po['last_updated_time'] = df_po['last_updated_at'].dt.time - df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") - df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") - df_po.drop(labels=['created_at','last_updated_at'],axis=1,inplace=True) + df_po = dict_of_df["purchase_order"] + df_po.index.name = "purchase_record_id" + df_po["created_date"] = df_po["created_at"].date() + df_po["created_time"] = df_po["created_at"].dt.time + df_po["last_updated_date"] = df_po["last_updated_at"].date() + df_po["last_updated_time"] = df_po["last_updated_at"].dt.time + df_po["agreed_delivery_date"] = pd.to_datetime( + df_po["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_po["agreed_payment_date"] = pd.to_datetime( + df_po["agreed_payment_date"], format="%Y-%m-%d" + ) + df_po.drop(labels=["created_at", "last_updated_at"], axis=1, inplace=True) return df_po @@ -73,69 +85,97 @@ def create_fact_payment(dict_of_df): df_payment["created_time"] = pd.to_datetime(df_payment["created_at"]).dt.time df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"]).dt.date df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"]).dt.time - fact_payment = df_payment.loc[:,[ - "payment_record_id", - "payment_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "transaction_id", - "counterparty_id", - "payment_amount", - "currency_id", - "payment_type_id", - "paid", - "payment_date" - ]] + fact_payment = df_payment.loc[ + :, + [ + "payment_record_id", + "payment_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "transaction_id", + "counterparty_id", + "payment_amount", + "currency_id", + "payment_type_id", + "paid", + "payment_date", + ], + ] return fact_payment -## dim_location from address --> drops 2 columns + +# dim_location from address --> drops 2 columns + + def create_dim_location(dict_of_df): - df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}).set_index('location_id') + df_loc = ( + dict_of_df["address"] + .drop(labels=["created_at", "last_updated"], axis=1) + .rename(columns={"address_id": "location_id"}) + .set_index("location_id") + ) return df_loc -## dim_counterparty from address and counterparty + +# dim_counterparty from address and counterparty + + def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) - df_cp = pd.merge(dict_of_df['counterparty'], - df_prefixed_address, - left_on="legal_address_id", - right_on="address_id", - how="outer").set_index('counterparty_id') + df_prefixed_address = dict_of_df["address"].add_prefix( + "counterparty_legal_", axis=1 + ) + df_cp = pd.merge( + dict_of_df["counterparty"], + df_prefixed_address, + left_on="legal_address_id", + right_on="address_id", + how="outer", + ).set_index("counterparty_id") return df_cp -## dim_date from purchase_order +# dim_date from purchase_order def create_dim_date(dict_of_df): - sr_date = pd.concat([dict_of_df['created_date'],dict_of_df['last_updated_date'],dict_of_df['agreed_delivery_date'],dict_of_df['agreed_payment_date']]).sort() - df_date = pd.DataFrame(sr_date,columns='date_id') - df_date['year'] = df_date['date_id'].dt.year - df_date['month'] = df_date['date_id'].dt.month - df_date['day'] = df_date['date_id'].dt.day - df_date['day_of_week'] = df_date['date_id'].dt.dayofweek - df_date['day_name'] = df_date['date_id'].dt.day_name - df_date['month_name'] = df_date['date_id'].dt.month_name - df_date['quarter'] = df_date['date_id'].dt.quarter - df_date.set_index('date_id') + sr_date = pd.concat( + [ + dict_of_df["created_date"], + dict_of_df["last_updated_date"], + dict_of_df["agreed_delivery_date"], + dict_of_df["agreed_payment_date"], + ] + ).sort() + df_date = pd.DataFrame(sr_date, columns="date_id") + df_date["year"] = df_date["date_id"].dt.year + df_date["month"] = df_date["date_id"].dt.month + df_date["day"] = df_date["date_id"].dt.day + df_date["day_of_week"] = df_date["date_id"].dt.dayofweek + df_date["day_name"] = df_date["date_id"].dt.day_name + df_date["month_name"] = df_date["date_id"].dt.month_name + df_date["quarter"] = df_date["date_id"].dt.quarter + df_date.set_index("date_id") + def scrape_currency_names(): - response = requests.get('https://www.xe.com/currency/').content - soup = BeautifulSoup(response,'html.parser') - currency = [item.text for item in soup.findAll('a', attrs={'class' : "sc-299dec64-6 fZPTSw"})] + response = requests.get("https://www.xe.com/currency/").content + soup = BeautifulSoup(response, "html.parser") + currency = [ + item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) + ] sr = pd.Series(currency) - df_cur = sr.str.split(pat=" - ",expand=True).rename({0:'currency_code',1:'currency_name'},axis=1) + df_cur = sr.str.split(pat=" - ", expand=True).rename( + {0: "currency_code", 1: "currency_name"}, axis=1 + ) return df_cur -def create_dim_currency(dict_of_df,names=scrape_currency_names()): - df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1) - dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner').set_index('currency_id') - return dim_cur - - - - +def create_dim_currency(dict_of_df, names=scrape_currency_names()): + df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) + dim_cur = pd.merge( + df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" + ).set_index("currency_id") + return dim_cur def create_dim_payment_type(dict_of_df): @@ -143,6 +183,7 @@ def create_dim_payment_type(dict_of_df): dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] return dim_payment_type + def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" @@ -150,41 +191,57 @@ def create_fact_payment(dict_of_df): df_payment["created_time"] = pd.to_datetime(df_payment["created_at"]).dt.time df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"]).dt.date df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"]).dt.time - fact_payment = df_payment.loc[:,[ - "payment_record_id", - "payment_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "transaction_id", - "counterparty_id", - "payment_amount", - "currency_id", - "payment_type_id", - "paid", - "payment_date" - ]] + fact_payment = df_payment.loc[ + :, + [ + "payment_record_id", + "payment_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "transaction_id", + "counterparty_id", + "payment_amount", + "currency_id", + "payment_type_id", + "paid", + "payment_date", + ], + ] return fact_payment + def create_dim_design(dict_of_df): df_design = dict_of_df["design"] - dim_design = df_design.loc[:, ["design_id", "design_name", "file_name", "file_location"]] + dim_design = df_design.loc[ + :, ["design_id", "design_name", "file_name", "file_location"] + ] return dim_design + def create_dim_staff(dict_of_df): - staff_department = pd.merge(dict_of_df["staff"], dict_of_df["department"], on='department_id', how="left") - dim_staff = staff_department.loc[:, ['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address']] + staff_department = pd.merge( + dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" + ) + dim_staff = staff_department.loc[ + :, + [ + "staff_id", + "first_name", + "last_name", + "department_name", + "location", + "email_address", + ], + ] return dim_staff + def create_dim_currency(dict_of_df): df_currency = dict_of_df["currency"] dim_currency = df_currency.loc[:, ["currency_id", "currency_code"]] - mappings = { - "GBP": "Pound", - "USD": "US Dollar", - "EUR": "Euro" - } + mappings = {"GBP": "Pound", "USD": "US Dollar", "EUR": "Euro"} dim_currency["currency_name"] = dim_currency["currency_code"].map(mappings) return dim_currency @@ -200,39 +257,49 @@ def create_dim_date(dict_of_df): df_sales["day_name"] = df_sales["agreed_delivery_date"].dt.day_name() df_sales["month_name"] = df_sales["agreed_delivery_date"].dt.month_name() df_sales["quarter"] = df_sales["agreed_delivery_date"].dt.quarter() - dim_date = ["date_id", "year", "month", "day", "day_of_week", "day_name", "month_name", "quarter"] #series.dt.quarter() + dim_date = [ + "date_id", + "year", + "month", + "day", + "day_of_week", + "day_name", + "month_name", + "quarter", + ] # series.dt.quarter() return dim_date -# TO DO: +# TO DO: # complete dim_date from merged fact table # merge dataframes into one dataframe # remove duplicates # test dim_date and fact_sales_order + def create_sales_star_schema(dict_of_df): dim_design = create_dim_design(dict_of_df) dim_staff = create_dim_staff(dict_of_df) dim_currency = create_dim_currency(dict_of_df) dim_date = create_dim_date(dict_of_df) - + fact_sales_order = create_fact_sales_order(dict_of_df) - - fact_sales_order = fact_sales_order.merge(dim_design, on='design_id', how='left') - fact_sales_order = fact_sales_order.merge(dim_staff, left_on='sales_staff_id', right_on='staff_id', how='left') - fact_sales_order = fact_sales_order.merge(dim_currency, on='currency_id', how='left') - fact_sales_order = fact_sales_order.merge(dim_date, left_on='agreed_delivery_date', right_on='date_id', how='left') - - return fact_sales_order + fact_sales_order = fact_sales_order.merge(dim_design, on="design_id", how="left") + fact_sales_order = fact_sales_order.merge( + dim_staff, left_on="sales_staff_id", right_on="staff_id", how="left" + ) + fact_sales_order = fact_sales_order.merge( + dim_currency, on="currency_id", how="left" + ) + fact_sales_order = fact_sales_order.merge( + dim_date, left_on="agreed_delivery_date", right_on="date_id", how="left" + ) + + return fact_sales_order def create_dim_payment_type(dict_of_df): df_payment_type = dict_of_df["payment_type"] dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] return dim_payment_type - - - - - diff --git a/src/transform_lambda.py b/src/transform_lambda.py index d30d91d..3e74ee0 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -6,12 +6,14 @@ import pandas as pd import pyarrow as pa import pyarrow.parquet as pq from src.dataframes import * + # from src.extract_lambda import extract_bucket, DBConnectionException import boto3 from botocore.exceptions import ClientError from pg8000.native import Connection, InterfaceError from datetime import datetime + class DBConnectionException(Exception): """Wraps pg8000.native Error or DatabaseError.""" @@ -20,6 +22,7 @@ class DBConnectionException(Exception): self.message = str(e) super().__init__(self.message) + logger = logging.getLogger(__name__) logging.basicConfig( @@ -45,44 +48,45 @@ tables = [ "payment_type", ] + def lambda_handler(event, context): db = None - - try: + + try: db = connect_to_database() - bucket = bucket_name('transform') + bucket = bucket_name("transform") existing_s3_files = list_existing_s3_files(bucket) - dict_of_df = read_from_s3_subfolder_to_df(tables, extract_bucket(), client=boto3.client("s3")) + dict_of_df = read_from_s3_subfolder_to_df( + tables, extract_bucket(), client=boto3.client("s3") + ) immutable_df_dict = { - 'dim_counterparty': create_dim_counterparty(dict_of_df), - 'dim_date': create_dim_date(dict_of_df), - 'dim_location': create_dim_location(dict_of_df), - 'dim_staff': create_dim_staff(dict_of_df), - 'dim_design': create_dim_design(dict_of_df)} - + "dim_counterparty": create_dim_counterparty(dict_of_df), + "dim_date": create_dim_date(dict_of_df), + "dim_location": create_dim_location(dict_of_df), + "dim_staff": create_dim_staff(dict_of_df), + "dim_design": create_dim_design(dict_of_df), + } mutable_df_dict = { - 'fact_sales_order': create_fact_sales_order(dict_of_df), - 'fact_purchase_order': create_fact_purchase_orders(dict_of_df), - 'fact_payment': create_fact_payment(dict_of_df), - 'dim_currency': create_dim_currency(dict_of_df)} - + "fact_sales_order": create_fact_sales_order(dict_of_df), + "fact_purchase_order": create_fact_purchase_orders(dict_of_df), + "fact_payment": create_fact_payment(dict_of_df), + "dim_currency": create_dim_currency(dict_of_df), + } + status = process_to_parquet_and_upload_to_s3( - existing_s3_files, - immutable_df_dict, - mutable_df_dict, - bucket + existing_s3_files, immutable_df_dict, mutable_df_dict, bucket ) - - if not status['uploaded']: + + if not status["uploaded"]: logger.info("No dataframes written to the bucket.") return { - 'statusCode': 204, - "body": json.dumps("No files where uploaded."), + "statusCode": 204, + "body": json.dumps("No files where uploaded."), } - + return { "statusCode": 200, "body": json.dumps( @@ -90,7 +94,7 @@ def lambda_handler(event, context): 'The following tables were not uploaded: '+', '.join([status['not_uploaded']]) if status['not_uploaded'] else ''}""" ), } - + except Exception as e: logger.error(f"Error: {e}", exc_info=True) return {"statusCode": 500, "body": json.dumps("Internal server error.")} @@ -99,34 +103,38 @@ def lambda_handler(event, context): db.close() -def process_to_parquet_and_upload_to_s3(existing_s3_files, - immutable_df_dict, - mutable_df_dict, - bucket, - client=boto3.client('s3')): - status = {'uploaded': [], - 'not_uploaded': []} +def process_to_parquet_and_upload_to_s3( + existing_s3_files, + immutable_df_dict, + mutable_df_dict, + bucket, + client=boto3.client("s3"), +): + status = {"uploaded": [], "not_uploaded": []} for table_name, df in immutable_df_dict.items(): if table_name in existing_s3_files: - status['not_uploaded'].append(table_name) + status["not_uploaded"].append(table_name) else: - parquet_file = df.to_parquet(f'{table_name}.parquet', engine='pyarrow') #or fastparquet - client.upload_file(parquet_file, bucket, f'{table_name}.parquet') - status['uploaded'].append(table_name) + parquet_file = df.to_parquet( + f"{table_name}.parquet", engine="pyarrow" + ) # or fastparquet + client.upload_file(parquet_file, bucket, f"{table_name}.parquet") + status["uploaded"].append(table_name) for table_name, df in mutable_df_dict.items(): s3_key = datetime.strftime( - datetime.today(), f"{table_name}/%Y/%m/%d/{table_name}_%H:%M:%S.parquet") - parquet_file = df.to_parquet(f'{table_name}.parquet', engine='pyarrow') #or fastparquet + datetime.today(), f"{table_name}/%Y/%m/%d/{table_name}_%H:%M:%S.parquet" + ) + parquet_file = df.to_parquet( + f"{table_name}.parquet", engine="pyarrow" + ) # or fastparquet client.upload_file(parquet_file, bucket, s3_key) - status['uploaded'].append(table_name) - + status["uploaded"].append(table_name) return status - def retrieve_secrets(): secret_name = "bentley-secrets" region_name = "eu-west-2" @@ -175,19 +183,23 @@ def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client("s3")): table_dfs[table] = pd.concat(list_of_df) return table_dfs + def bucket_name(bucket_prefix, client=boto3.client("s3")): response = client.list_buckets() bucket_filter = [ - bucket["Name"] for bucket in response["Buckets"] if bucket_prefix in bucket["Name"] + bucket["Name"] + for bucket in response["Buckets"] + if bucket_prefix in bucket["Name"] ] return bucket_filter[0] + def list_existing_s3_files(bucket_name, client=boto3.client("s3")): logging.info("Listing existing S3 files") try: - response = client.list_objects_v2(Bucket=bucket_name) + response = client.list_objects_v2(Bucket=bucket_name) if "Contents" in response: existing_files = [obj["Key"] for obj in response["Contents"]] @@ -198,4 +210,4 @@ def list_existing_s3_files(bucket_name, client=boto3.client("s3")): except ClientError as e: logger.error(f"Error listing S3 objects: {e}") - return existing_files \ No newline at end of file + return existing_files diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py index 82845d7..87e3ade 100644 --- a/tests/test_fact_sales_order.py +++ b/tests/test_fact_sales_order.py @@ -1,57 +1,109 @@ -from src.fact_sales_order import create_dim_design, create_dim_staff, create_dim_currency +from src.fact_sales_order import ( + create_dim_design, + create_dim_staff, + create_dim_currency, +) import pandas as pd + class TestCreateDimDesign: def test_dim_design_returns_dataframe(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) assert isinstance(result, pd.DataFrame) def test_dim_design_returns_correct_columns_and_values(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) - d2 = {"design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"]} + d2 = { + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=d2) expected_result = expected_df.copy() assert result.equals(expected_result) + class TestCreateDimStaff: def test_dim_staff_returns_dataframe(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - assert isinstance(result, pd.DataFrame) + assert isinstance(result, pd.DataFrame) def test_dim_staff_returns_correct_columns_and_values(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - expected_d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"]} + expected_d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) expected_result = expected_df.copy() - assert result.equals(expected_result) + assert result.equals(expected_result) + class TestCreateDimCurrency: def test_dim_currency_returns_dataframe(self): d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"]} test_df = {"currency": pd.DataFrame(data=d)} result = create_dim_currency(test_df) - assert isinstance(result, pd.DataFrame) - + assert isinstance(result, pd.DataFrame) + def test_dim_currency_returns_columns_and_values(self): d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"]} test_df = {"currency": pd.DataFrame(data=d)} result = create_dim_currency(test_df) - expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} + expected_d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "currency_name": ["US Dollar", "Euro", "Pound"], + } expected_df = pd.DataFrame(data=expected_d) expected_result = expected_df.copy() assert result.equals(expected_result) - - \ No newline at end of file diff --git a/tests/test_transform_lambda.py b/tests/test_transform_lambda.py index 516f83b..a91da92 100644 --- a/tests/test_transform_lambda.py +++ b/tests/test_transform_lambda.py @@ -39,7 +39,12 @@ class TestReadFromS3: ) print(result) expected_df = pd.DataFrame( - np.array([["Vegetable", "Sour", "Green", "2022-11-03 14:20:49.962"], ["Berry", "Sweet", "Red", "2022-11-03 14:20:49.962"]]), + np.array( + [ + ["Vegetable", "Sour", "Green", "2022-11-03 14:20:49.962"], + ["Berry", "Sweet", "Red", "2022-11-03 14:20:49.962"], + ] + ), columns=["Food_type", "Flavour", "Colour", "last_updated"], ) assert isinstance(result, dict) @@ -56,7 +61,12 @@ class TestReadFromS3: tables, bucket="dummy_buc", client=s3_client ) expected_foods_df = pd.DataFrame( - np.array([["Vegetable", "Sour", "Green", "2022-11-03 14:20:49.962"], ["Berry", "Sweet", "Red", "2022-11-03 14:20:49.962"]]), + np.array( + [ + ["Vegetable", "Sour", "Green", "2022-11-03 14:20:49.962"], + ["Berry", "Sweet", "Red", "2022-11-03 14:20:49.962"], + ] + ), columns=["Food_type", "Flavour", "Colour", "last_updated"], ) expected_cars_df = pd.DataFrame( @@ -72,5 +82,3 @@ class TestReadFromS3: assert list(result.keys()) == tables assert result["Foods"].eq(expected_foods_df, axis="columns").all(axis=None) assert result["Cars"].eq(expected_cars_df, axis="columns").all(axis=None) - - -- cgit v1.2.3 From 09c8191ce983e4335cfb131d21ddb5413b849cfb Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 11:18:24 +0100 Subject: add tests --- src/load_lambda.py | 61 ++++++++++++++++++++++++++++++++++++++++++++--- tests/test_load_lambda.py | 3 +-- 2 files changed, 59 insertions(+), 5 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index a3fd996..d95c27a 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -4,6 +4,9 @@ import pandas as pd import pyarrow.parquet as pq from io import BytesIO import logging +import json +from src.extract_lambda import retrieve_secrets, connect_to_database +from sqlalchemy import create_engine logger = logging.getLogger(__name__) @@ -17,6 +20,43 @@ logging.basicConfig( logging.getLogger("botocore").setLevel(logging.WARNING) +def lambda_handler(event, context): + db = None + try: + uploaded_tables = upload_dfs_to_database() + if uploaded_tables == []: + return { + "statusCode": 200, + "body": json.dumps("No datframes were uploaded."), + } + return { + "statusCode": 200, + "body": json.dumps( + f"""The following dataframes were uploaded successfully: + {', '.join(upload_dfs_to_database['updated'])}.""" + ), + } + except Exception as e: + logger.error(f"Error: {e}", exc_info=True) + return {"statusCode": 500, "body": json.dumps("Internal server error.")} + finally: + if db: + db.close() + +# connect to database, slightly different way of doing it, to allow manipulation through pandas +def connect_to_db_and_return_engine(): + secrets = json.loads(retrieve_secrets("bentley-RDS-credentials")) #need to amend retrieve secrets function + host = secrets["host"] + port = secrets["port"] + user = secrets["user"] + password = secrets["password"] + database = secrets["database"] + conn_str = f'postgresql+pg8000://{user}:{password}@{host}:{port}/{database}' + engine = create_engine(conn_str) #interface between python (pandas) and SQL + return engine + + + # get transform bucket def transform_bucket(client=None): if client is None: @@ -41,7 +81,7 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): bucket_name = transform_bucket(client) files = client.list_objects_v2(Bucket=bucket_name) - dfs = [] + dfs = {} if "Contents" in files: for file in files["Contents"]: file_key = file['Key'] @@ -49,7 +89,7 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): file_obj = client.get_object(Bucket=bucket_name, Key=file_key) parquet_file = pq.ParquetFile(BytesIO(file_obj['Body'].read())) df = parquet_file.read().to_pandas() - dfs.append(df) + dfs[file_key] = df except ClientError as e: logger.error(f"Unable to retrieve S3 object {file_key}: {e}") except Exception as e: @@ -64,4 +104,19 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): logger.error(f"Unable to list objects: {client_error}") raise - return dfs + return dfs + +def upload_dfs_to_database(): + uploaded = [] + dict_of_dfs = convert_parquet_files_to_dfs() + db_engine = connect_to_db_and_return_engine() + try: + for table_name, df in dict_of_dfs: + df.to_sql(table_name, con=db_engine, ifexists="replace", index=False) + uploaded.append(table_name) + except Exception as e: + logger.error(f"Error uploading dataframes: {e}") + db_engine.dispose() + return uploaded + + # aiming to return a list of uploaded tables \ No newline at end of file diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 0572340..d9ea918 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -1,8 +1,7 @@ -import boto3 import pandas as pd import pyarrow.parquet as pq from io import BytesIO -from src.load_lambda import convert_parquet_files_to_dataframes +from src.load_lambda import convert_parquet_files_to_dfs class TestConvertParquetToDFs: def test_convert_parquet_to_dfs_returns_df(): -- cgit v1.2.3 From 535e3cd919613d4cadfbb42ea8f2ecdd7678f38c Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 11:18:55 +0100 Subject: add SQLalchemy to requirements --- requirements.txt | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index 6ba2cf6..614a0ab 100644 --- a/requirements.txt +++ b/requirements.txt @@ -30,4 +30,5 @@ Werkzeug==3.0.3 xmltodict==0.13.0 s3fs pandas -pyarrow \ No newline at end of file +pyarrow +SQLAlchemy \ No newline at end of file -- cgit v1.2.3 From eb0449447af38b8e162421b92cd0d8a8744540c6 Mon Sep 17 00:00:00 2001 From: T-Aji Date: Fri, 23 Aug 2024 11:42:34 +0100 Subject: removed duplicate functions --- src/dataframes.py | 117 +++++++++++++----------------------------------------- 1 file changed, 28 insertions(+), 89 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 9ce3be0..380e4c5 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -1,11 +1,5 @@ import pandas as pd from bs4 import BeautifulSoup -from src.transform_lambda import read_from_s3_subfolder_to_df, tables -from src.extract_lambda import extract_bucket -import json -import boto3 -import re -from datetime import datetime as dt import requests #Table names: @@ -21,8 +15,7 @@ import requests # dim_currency # dim_counterparty -def create_dim_transaction(dict_of_df): - pass + def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] @@ -31,8 +24,6 @@ def create_fact_sales_order(dict_of_df): df_sales["created_time"] = pd.to_datetime(df_sales["created_at"]).dt.time df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"]).dt.date df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time - pd.merge(dict_of_df["staff"], df_sales["sales_staff_id"], on="staff_id", how="left") - # df_sales.rename(columns={"staff_id": "sales_staff_id"}) fact_sales_order = df_sales.loc[:,[ "sales_record_id", "sales_order_id", @@ -90,6 +81,11 @@ def create_fact_payment(dict_of_df): ]] return fact_payment +def create_dim_transaction(dict_of_df): + df_transaction = dict_of_df["transaction"].drop(labels=['created_at', 'last_updated'], axis=1).set_index('transaction_id') + dim_transaction = df_transaction.loc[:, ["payment_type_id", "payment_type_name"]] + return dim_transaction + ## dim_location from address --> drops 2 columns def create_dim_location(dict_of_df): df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}).set_index('location_id') @@ -119,6 +115,20 @@ def create_dim_date(dict_of_df): df_date['quarter'] = df_date['date_id'].dt.quarter df_date.set_index('date_id') +def create_dim_date(dict_of_df): + df_sales = dict_of_df["sales"] + df_sales = df_sales.loc[:, ["agreed_delivery_date"]] + df_sales["agreed_delivery_date"] = pd.to_datetime["agreed_delivery_date"] + df_sales["year"] = df_sales["agreed_delivery_date"].dt.year + df_sales["month"] = df_sales["agreed_delivery_date"].dt.month + df_sales["day"] = df_sales["agreed_delivery_date"].dt.day + df_sales["day_of_week"] = df_sales["agreed_delivery_date"].dt.dayofweek + df_sales["day_name"] = df_sales["agreed_delivery_date"].dt.day_name() + df_sales["month_name"] = df_sales["agreed_delivery_date"].dt.month_name() + df_sales["quarter"] = df_sales["agreed_delivery_date"].dt.quarter() + dim_date = ["date_id", "year", "month", "day", "day_of_week", "day_name", "month_name", "quarter"] #series.dt.quarter() + return dim_date + def scrape_currency_names(): response = requests.get('https://www.xe.com/currency/').content soup = BeautifulSoup(response,'html.parser') @@ -130,107 +140,36 @@ def scrape_currency_names(): def create_dim_currency(dict_of_df,names=scrape_currency_names()): df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1) dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner').set_index('currency_id') + print(dim_cur) return dim_cur - - - - - - - +#tests passed def create_dim_payment_type(dict_of_df): df_payment_type = dict_of_df["payment_type"] dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] return dim_payment_type -def create_fact_payment(dict_of_df): - df_payment = dict_of_df["payment"] - df_payment.index.name = "payment_record_id" - df_payment["created_date"] = pd.to_datetime(df_payment["created_at"]).dt.date - df_payment["created_time"] = pd.to_datetime(df_payment["created_at"]).dt.time - df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"]).dt.date - df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"]).dt.time - fact_payment = df_payment.loc[:,[ - "payment_record_id", - "payment_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "transaction_id", - "counterparty_id", - "payment_amount", - "currency_id", - "payment_type_id", - "paid", - "payment_date" - ]] - return fact_payment - +#tests passed def create_dim_design(dict_of_df): df_design = dict_of_df["design"] dim_design = df_design.loc[:, ["design_id", "design_name", "file_name", "file_location"]] return dim_design - +#tests passed def create_dim_staff(dict_of_df): staff_department = pd.merge(dict_of_df["staff"], dict_of_df["department"], on='department_id', how="left") dim_staff = staff_department.loc[:, ['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address']] return dim_staff -def create_dim_currency(dict_of_df): - df_currency = dict_of_df["currency"] - dim_currency = df_currency.loc[:, ["currency_id", "currency_code"]] - mappings = { - "GBP": "Pound", - "USD": "US Dollar", - "EUR": "Euro" - } - dim_currency["currency_name"] = dim_currency["currency_code"].map(mappings) - return dim_currency -def create_dim_date(dict_of_df): - df_sales = dict_of_df["sales"] - df_sales = df_sales.loc[:, ["agreed_delivery_date"]] - df_sales["agreed_delivery_date"] = pd.to_datetime["agreed_delivery_date"] - df_sales["year"] = df_sales["agreed_delivery_date"].dt.year - df_sales["month"] = df_sales["agreed_delivery_date"].dt.month - df_sales["day"] = df_sales["agreed_delivery_date"].dt.day - df_sales["day_of_week"] = df_sales["agreed_delivery_date"].dt.dayofweek - df_sales["day_name"] = df_sales["agreed_delivery_date"].dt.day_name() - df_sales["month_name"] = df_sales["agreed_delivery_date"].dt.month_name() - df_sales["quarter"] = df_sales["agreed_delivery_date"].dt.quarter() - dim_date = ["date_id", "year", "month", "day", "day_of_week", "day_name", "month_name", "quarter"] #series.dt.quarter() - return dim_date -# TO DO: -# complete dim_date from merged fact table -# merge dataframes into one dataframe -# remove duplicates -# test dim_date and fact_sales_order - -def create_sales_star_schema(dict_of_df): - dim_design = create_dim_design(dict_of_df) - dim_staff = create_dim_staff(dict_of_df) - dim_currency = create_dim_currency(dict_of_df) - dim_date = create_dim_date(dict_of_df) - - fact_sales_order = create_fact_sales_order(dict_of_df) - - fact_sales_order = fact_sales_order.merge(dim_design, on='design_id', how='left') - fact_sales_order = fact_sales_order.merge(dim_staff, left_on='sales_staff_id', right_on='staff_id', how='left') - fact_sales_order = fact_sales_order.merge(dim_currency, on='currency_id', how='left') - fact_sales_order = fact_sales_order.merge(dim_date, left_on='agreed_delivery_date', right_on='date_id', how='left') - - return fact_sales_order -def create_dim_payment_type(dict_of_df): - df_payment_type = dict_of_df["payment_type"] - dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] - return dim_payment_type + + + + -- cgit v1.2.3 From 7ccb0ca3eb2d548e9759eb09aa711df47b1c0908 Mon Sep 17 00:00:00 2001 From: T-Aji Date: Fri, 23 Aug 2024 11:46:44 +0100 Subject: removed duplicate functions --- tests/test_fact_sales_order.py | 85 ++++++++++++++++++++++++++++++++++-------- 1 file changed, 69 insertions(+), 16 deletions(-) diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py index 82845d7..ca53faa 100644 --- a/tests/test_fact_sales_order.py +++ b/tests/test_fact_sales_order.py @@ -1,5 +1,6 @@ -from src.fact_sales_order import create_dim_design, create_dim_staff, create_dim_currency +from src.dataframes import create_dim_design, create_dim_staff, create_dim_payment_type, create_dim_counterparty, create_dim_currency import pandas as pd +from unittest.mock import patch class TestCreateDimDesign: def test_dim_design_returns_dataframe(self): @@ -36,22 +37,74 @@ class TestCreateDimStaff: expected_d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"]} expected_df = pd.DataFrame(data=expected_d) expected_result = expected_df.copy() - assert result.equals(expected_result) + assert result.equals(expected_result) -class TestCreateDimCurrency: - def test_dim_currency_returns_dataframe(self): - d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"]} - test_df = {"currency": pd.DataFrame(data=d)} - result = create_dim_currency(test_df) - assert isinstance(result, pd.DataFrame) - - def test_dim_currency_returns_columns_and_values(self): - d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"]} - test_df = {"currency": pd.DataFrame(data=d)} - result = create_dim_currency(test_df) - expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} +class TestCreatePaymentType: + def test_create_dim_payment_type_returns_correct_columns_and_values(self): + d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} + test_df = {"payment_type": pd.DataFrame(data=d)} + result = create_dim_payment_type(test_df) + expected_columns = ["payment_type_id", "payment_type_name"] + expected_d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} expected_df = pd.DataFrame(data=expected_d) - expected_result = expected_df.copy() - assert result.equals(expected_result) + assert isinstance(result, pd.DataFrame) + assert list(result.columns) == expected_columns + assert result.equals(expected_df) + +class TestCreateDimCounterparty: + def test_create_dim_counterparty_type_returns_correct_columns_and_values(self): + data_d = {"counterparty_id": ["Hello", "Bye"], + "counterparty_legal_name": ["Hello", "Bye"], + "counterparty_legal_address_line_1": ["Hello", "Bye"], + } + data_a = {"address_id": + "address", + } + test_df = {"address": pd.DataFrame(data=data_a)} + test_df = {} + result = create_dim_counterparty(test_df) + + expected_columns = ["counterparty_id", + "counterparty_legal_name", + "counterparty_legal_address_line_1", + "counterparty_legal_address_line_2", + "counterparty_legal_district", + "counterparty_legal_city", + "counterparty_legal_postal_code", + "counterparty_legal_postal_code", + "counterparty_legal_phone_number"] + expected_d = {"counterparty_id": ["Hello", "Bye"], + "counterparty_legal_name": ["Hello", "Bye"], + "counterparty_legal_address_line_1": ["Hello", "Bye"], + "counterparty_legal_address_line_2": ["Hello", "Bye"], + "counterparty_legal_district": ["Hello", "Bye"], + "counterparty_legal_city": ["Hello", "Bye"], + "counterparty_legal_postal_code": ["Hello", "Bye"], + "counterparty_legal_postal_code": ["Hello", "Bye"], + "counterparty_legal_phone_number": ["Hello", "Bye"]} + expected_df = pd.DataFrame(data=expected_d) + assert isinstance(result, pd.DataFrame) + assert list(result.columns) == expected_columns + assert result.equals(expected_df) + +# # figuring out how to mock currency scraper functiom +# class TestCreateDimCurrency: +# @patch("src.dataframes.scrape_currency_names") +# def test_dim_currency_returns_columns_and_values(self): +# d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"]} +# test_df = {"currency": pd.DataFrame(data=d)} +# result = create_dim_currency(test_df) +# expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} +# expected_df = pd.DataFrame(data=expected_d) +# expected_result = expected_df.copy() +# assert result.equals(expected_result) + +# def test_dim_currency_returns_dataframe(self): +# d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"]} +# test_df = {"currency": pd.DataFrame(data=d)} +# result = create_dim_currency(test_df) +# assert isinstance(result, pd.DataFrame) + + \ No newline at end of file -- cgit v1.2.3 From 3ff2182b8256594dfbfe7d8c7480d2ee70067ce5 Mon Sep 17 00:00:00 2001 From: lian-manonog Date: Fri, 23 Aug 2024 11:46:59 +0100 Subject: trying to resolce git index issue conflicts - commiting was the only solution --- src/transform_lambda.py | 13 ++++--------- tests/test_fact_sales_order.py | 4 ++++ 2 files changed, 8 insertions(+), 9 deletions(-) diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 3e74ee0..44454e2 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -6,9 +6,6 @@ import pandas as pd import pyarrow as pa import pyarrow.parquet as pq from src.dataframes import * - -# from src.extract_lambda import extract_bucket, DBConnectionException -import boto3 from botocore.exceptions import ClientError from pg8000.native import Connection, InterfaceError from datetime import datetime @@ -34,7 +31,7 @@ logging.basicConfig( logging.getLogger("botocore").setLevel(logging.WARNING) -tables = [ +TABLES = [ "sales_order", "transaction", "payment", @@ -54,12 +51,11 @@ def lambda_handler(event, context): try: db = connect_to_database() - bucket = bucket_name("transform") + bucket = bucket_name('transform') + existing_s3_files = list_existing_s3_files(bucket) - dict_of_df = read_from_s3_subfolder_to_df( - tables, extract_bucket(), client=boto3.client("s3") - ) + dict_of_df = read_from_s3_subfolder_to_df(TABLES, bucket_name('extract'), client=boto3.client("s3")) immutable_df_dict = { "dim_counterparty": create_dim_counterparty(dict_of_df), @@ -134,7 +130,6 @@ def process_to_parquet_and_upload_to_s3( return status - def retrieve_secrets(): secret_name = "bentley-secrets" region_name = "eu-west-2" diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py index 87e3ade..c4fc9f4 100644 --- a/tests/test_fact_sales_order.py +++ b/tests/test_fact_sales_order.py @@ -1,8 +1,12 @@ +<<<<<<< Updated upstream from src.fact_sales_order import ( create_dim_design, create_dim_staff, create_dim_currency, ) +======= +from fact_sales_order import create_dim_design, create_dim_staff, create_dim_currency +>>>>>>> Stashed changes import pandas as pd -- cgit v1.2.3 From c3e04ab0415ddeedfa1a304296aa0e34fb5f2a1f Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Fri, 23 Aug 2024 10:47:15 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 3ff2182 according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/93 --- src/transform_lambda.py | 9 ++++++--- tests/test_fact_sales_order.py | 16 +++++++++------- 2 files changed, 15 insertions(+), 10 deletions(-) diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 44454e2..defa15d 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -51,11 +51,13 @@ def lambda_handler(event, context): try: db = connect_to_database() - bucket = bucket_name('transform') - + bucket = bucket_name("transform") + existing_s3_files = list_existing_s3_files(bucket) - dict_of_df = read_from_s3_subfolder_to_df(TABLES, bucket_name('extract'), client=boto3.client("s3")) + dict_of_df = read_from_s3_subfolder_to_df( + TABLES, bucket_name("extract"), client=boto3.client("s3") + ) immutable_df_dict = { "dim_counterparty": create_dim_counterparty(dict_of_df), @@ -130,6 +132,7 @@ def process_to_parquet_and_upload_to_s3( return status + def retrieve_secrets(): secret_name = "bentley-secrets" region_name = "eu-west-2" diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py index c4fc9f4..dad245e 100644 --- a/tests/test_fact_sales_order.py +++ b/tests/test_fact_sales_order.py @@ -1,13 +1,13 @@ -<<<<<<< Updated upstream +import pandas as pd +from fact_sales_order import create_dim_design, create_dim_staff, create_dim_currency from src.fact_sales_order import ( create_dim_design, create_dim_staff, create_dim_currency, ) -======= -from fact_sales_order import create_dim_design, create_dim_staff, create_dim_currency ->>>>>>> Stashed changes -import pandas as pd +<< << << < Updated upstream +== == == = +>>>>>> > Stashed changes class TestCreateDimDesign: @@ -60,7 +60,8 @@ class TestCreateDimStaff: "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"], } - test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} + test_df = {"staff": pd.DataFrame( + data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) assert isinstance(result, pd.DataFrame) @@ -77,7 +78,8 @@ class TestCreateDimStaff: "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"], } - test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} + test_df = {"staff": pd.DataFrame( + data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) expected_d = { "staff_id": ["Hello", "Bye"], -- cgit v1.2.3 From 65289cdd17359c6a29560339e134e0ddf9461ce0 Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 12:08:09 +0100 Subject: add amendments to load lambda --- src/load_lambda.py | 66 ++++++++++++++++++++++++++++++------------------------ 1 file changed, 37 insertions(+), 29 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index d95c27a..f92bb45 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -1,11 +1,11 @@ import boto3 -from botocore.exceptions import ClientError +from botocore.exceptions import ClientError, InterfaceError import pandas as pd import pyarrow.parquet as pq from io import BytesIO import logging import json -from src.extract_lambda import retrieve_secrets, connect_to_database +from src.extract_lambda import retrieve_secrets from sqlalchemy import create_engine @@ -18,67 +18,74 @@ logging.basicConfig( level=logging.DEBUG, ) -logging.getLogger("botocore").setLevel(logging.WARNING) +logging.getLogger("botocore").setLevel(logging.INFO) + def lambda_handler(event, context): - db = None try: uploaded_tables = upload_dfs_to_database() - if uploaded_tables == []: + if not uploaded_tables: return { "statusCode": 200, - "body": json.dumps("No datframes were uploaded."), + "body": json.dumps("No dataframes were uploaded."), } return { "statusCode": 200, "body": json.dumps( f"""The following dataframes were uploaded successfully: - {', '.join(upload_dfs_to_database['updated'])}.""" + {', '.join(uploaded_tables)} .""" ), } except Exception as e: logger.error(f"Error: {e}", exc_info=True) return {"statusCode": 500, "body": json.dumps("Internal server error.")} - finally: - if db: - db.close() # connect to database, slightly different way of doing it, to allow manipulation through pandas def connect_to_db_and_return_engine(): - secrets = json.loads(retrieve_secrets("bentley-RDS-credentials")) #need to amend retrieve secrets function - host = secrets["host"] - port = secrets["port"] - user = secrets["user"] - password = secrets["password"] - database = secrets["database"] - conn_str = f'postgresql+pg8000://{user}:{password}@{host}:{port}/{database}' - engine = create_engine(conn_str) #interface between python (pandas) and SQL - return engine - - + try: + secrets = json.loads(retrieve_secrets("bentley-RDS-credentials")) #need to amend retrieve secrets function + host = secrets["host"] + port = secrets["port"] + user = secrets["user"] + password = secrets["password"] + database = secrets["database"] + conn_str = f'postgresql+pg8000://{user}:{password}@{host}:{port}/{database}' + engine = create_engine(conn_str) #interface between python (pandas) and SQL + return engine + except Exception as e: + logger.error(f"Interface error: {e}") + raise RuntimeError("Failed to create database engine") + # get transform bucket -def transform_bucket(client=None): +def get_transform_bucket(client=None): if client is None: client = boto3.client("s3") - response = client.list_buckets() + try: + response = client.list_buckets() + except ClientError as e: + logger.error(f"Error listing S3 buckets: {e}") + raise RuntimeError("Error listing S3 buckets") + transform_bucket_filter = [ bucket["Name"] for bucket in response["Buckets"] if "transform" in bucket["Name"] ] if not transform_bucket_filter: - raise ValueError("No transform_bucket found") + logger.error("No transform bucket found") + raise ValueError("No transform bucket found") return transform_bucket_filter[0] # list and then retrieve parquet files from S3 bucket -# convert parquet files into dataframes and return a list of dataframes +# convert parquet files into dataframes +# return a dictionary of dataframes with name as key, and dataframe object as value def convert_parquet_files_to_dfs(bucket_name=None, client=None): try: if client is None: client = boto3.client("s3") if bucket_name is None: - bucket_name = transform_bucket(client) + bucket_name = get_transform_bucket() files = client.list_objects_v2(Bucket=bucket_name) dfs = {} @@ -96,7 +103,7 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): logger.error(f"Unable to process file {file_key}: {e}") else: logger.error(f"No files found in {bucket_name}.") - return [] + return {} except ValueError as value_error: logger.error(f"Unable to list objects: {value_error}") raise @@ -111,11 +118,12 @@ def upload_dfs_to_database(): dict_of_dfs = convert_parquet_files_to_dfs() db_engine = connect_to_db_and_return_engine() try: - for table_name, df in dict_of_dfs: - df.to_sql(table_name, con=db_engine, ifexists="replace", index=False) + for table_name, df in dict_of_dfs.items(): + df.to_sql(table_name, con=db_engine, if_exists="replace", index=False) uploaded.append(table_name) except Exception as e: logger.error(f"Error uploading dataframes: {e}") + raise db_engine.dispose() return uploaded -- cgit v1.2.3 From f3bb705a31ab9d94dc856c2de0da4b7b73a57fae Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 12:38:25 +0100 Subject: add get transform bucket test --- src/load_lambda.py | 2 +- tests/test_load_lambda.py | 48 +++++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 45 insertions(+), 5 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index f92bb45..a9d5ac5 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -1,5 +1,5 @@ import boto3 -from botocore.exceptions import ClientError, InterfaceError +from botocore.exceptions import ClientError import pandas as pd import pyarrow.parquet as pq from io import BytesIO diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index d9ea918..2392f10 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -1,8 +1,48 @@ import pandas as pd import pyarrow.parquet as pq from io import BytesIO -from src.load_lambda import convert_parquet_files_to_dfs +from moto import mock_aws +import boto3 +import os +import pytest +from src.load_lambda import lambda_handler, connect_to_db_and_return_engine, get_transform_bucket, convert_parquet_files_to_dfs, upload_dfs_to_database -class TestConvertParquetToDFs: - def test_convert_parquet_to_dfs_returns_df(): - \ No newline at end of file +@pytest.fixture(scope="class") +def aws_credentials(): + os.environ["AWS_ACCESS_KEY_ID"] = "testing" + os.environ["AWS_SECRET_ACCESS_KEY"] = "testing" + os.environ["AWS_SECURIT_TOKEN"] = "testing" + os.environ["AWS_SESSION_TOKEN"] = "testing" + os.environ["AWS_DEFAULT_REGION"] = "eu-west-2" + + +@pytest.fixture(scope="class") +def s3_client(aws_credentials): + with mock_aws(): + yield boto3.client("s3") + +@pytest.fixture(scope="function") +def s3_mock_bucket(s3_client): + bucket = s3_client.create_bucket( + Bucket="transform_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) + return bucket + + +class TestLambdaHandler: + pass + +class TestConnectToDBAndReturnEngine: + pass + +class TestGetTransformBucket: + def test_get_transform_bucket_returns_string(self, s3_client, s3_mock_bucket): + result = get_transform_bucket(s3_client) + assert result == "transform_bucket" + +class TestConvertParquetToDfs: + pass + +class TestUploadDfsToDatabase: + pass \ No newline at end of file -- cgit v1.2.3 From eeaaeb471f3410e5c655836253484a41e54ef71b Mon Sep 17 00:00:00 2001 From: Ang Bel Date: Fri, 23 Aug 2024 13:13:41 +0100 Subject: fix: refactoring for create_dim_date to include all date columns from all fact dfs, tested on dummy data. Tests are not written --- src/dataframes.py | 33 +++++++++++++-------------------- 1 file changed, 13 insertions(+), 20 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 380e4c5..042c8aa 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -104,30 +104,23 @@ def create_dim_counterparty(dict_of_df): ## dim_date from purchase_order def create_dim_date(dict_of_df): - sr_date = pd.concat([dict_of_df['created_date'],dict_of_df['last_updated_date'],dict_of_df['agreed_delivery_date'],dict_of_df['agreed_payment_date']]).sort() - df_date = pd.DataFrame(sr_date,columns='date_id') + fact_dfs = [create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df)] + date_col_names = [col_name for col_name in list(fact_dfs[0].columns) if 'date' in col_name] + list_of_date_columns = [] + for df in fact_dfs: + for col in date_col_names: + list_of_date_columns.append(df[col]) + sr_date = pd.array(pd.concat(list_of_date_columns),dtype='datetime64[ns]') + df_date = pd.DataFrame(data=sr_date,columns=['date_id']) + df_date.drop_duplicates(inplace=True) df_date['year'] = df_date['date_id'].dt.year df_date['month'] = df_date['date_id'].dt.month df_date['day'] = df_date['date_id'].dt.day df_date['day_of_week'] = df_date['date_id'].dt.dayofweek - df_date['day_name'] = df_date['date_id'].dt.day_name - df_date['month_name'] = df_date['date_id'].dt.month_name - df_date['quarter'] = df_date['date_id'].dt.quarter - df_date.set_index('date_id') - -def create_dim_date(dict_of_df): - df_sales = dict_of_df["sales"] - df_sales = df_sales.loc[:, ["agreed_delivery_date"]] - df_sales["agreed_delivery_date"] = pd.to_datetime["agreed_delivery_date"] - df_sales["year"] = df_sales["agreed_delivery_date"].dt.year - df_sales["month"] = df_sales["agreed_delivery_date"].dt.month - df_sales["day"] = df_sales["agreed_delivery_date"].dt.day - df_sales["day_of_week"] = df_sales["agreed_delivery_date"].dt.dayofweek - df_sales["day_name"] = df_sales["agreed_delivery_date"].dt.day_name() - df_sales["month_name"] = df_sales["agreed_delivery_date"].dt.month_name() - df_sales["quarter"] = df_sales["agreed_delivery_date"].dt.quarter() - dim_date = ["date_id", "year", "month", "day", "day_of_week", "day_name", "month_name", "quarter"] #series.dt.quarter() - return dim_date + df_date['day_name'] = df_date['date_id'].dt.day_name() + df_date['month_name'] = df_date['date_id'].dt.month_name() + df_date['quarter'] = df_date['date_id'].dt.quarter #By default, the DataFrame index is not included when uploading to RDS. We are not setting indexes to retain the column information + return def scrape_currency_names(): response = requests.get('https://www.xe.com/currency/').content -- cgit v1.2.3 From 2e85e8f14f35bebb7e96a9dff7bc59ebaefe32f6 Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 13:15:35 +0100 Subject: adds passing transform bucket tests --- tests/test_load_lambda.py | 30 +++++++++++++++++++----------- 1 file changed, 19 insertions(+), 11 deletions(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 2392f10..7f001df 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -17,18 +17,10 @@ def aws_credentials(): @pytest.fixture(scope="class") -def s3_client(aws_credentials): +def mock_s3_client(aws_credentials): with mock_aws(): yield boto3.client("s3") -@pytest.fixture(scope="function") -def s3_mock_bucket(s3_client): - bucket = s3_client.create_bucket( - Bucket="transform_bucket", - CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, - ) - return bucket - class TestLambdaHandler: pass @@ -37,8 +29,24 @@ class TestConnectToDBAndReturnEngine: pass class TestGetTransformBucket: - def test_get_transform_bucket_returns_string(self, s3_client, s3_mock_bucket): - result = get_transform_bucket(s3_client) + def test_get_transform_bucket_raises_error_if_no_buckets(self, mock_s3_client): + with pytest.raises(ValueError, match="No transform bucket found"): + get_transform_bucket(mock_s3_client) + + def test_get_transform_bucket_returns_transform_bucket_if_one_bucket(self, mock_s3_client): + mock_s3_client.create_bucket( + Bucket="transform_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) + result = get_transform_bucket(mock_s3_client) + assert result == "transform_bucket" + + def test_get_transform_bucket_only_returns_transform_bucket_if_several_buckets(self, mock_s3_client): + mock_s3_client.create_bucket( + Bucket="extract_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) + result = get_transform_bucket(mock_s3_client) assert result == "transform_bucket" class TestConvertParquetToDfs: -- cgit v1.2.3 From 0c95b93303dea04e18aefe57e3b6fef7e4127c3c Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 13:22:23 +0100 Subject: add working completed tests for get transform bucket --- tests/test_load_lambda.py | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 7f001df..f1c2b01 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -29,11 +29,19 @@ class TestConnectToDBAndReturnEngine: pass class TestGetTransformBucket: - def test_get_transform_bucket_raises_error_if_no_buckets(self, mock_s3_client): + def test_raises_value_error_if_no_buckets(self, mock_s3_client): with pytest.raises(ValueError, match="No transform bucket found"): get_transform_bucket(mock_s3_client) - def test_get_transform_bucket_returns_transform_bucket_if_one_bucket(self, mock_s3_client): + def test_raises_value_error_if_no_transform_bucket(self, mock_s3_client): + mock_s3_client.create_bucket( + Bucket="extract_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) + with pytest.raises(ValueError, match="No transform bucket found"): + get_transform_bucket(mock_s3_client) + + def test_returns_transform_bucket_if_one_bucket(self, mock_s3_client): mock_s3_client.create_bucket( Bucket="transform_bucket", CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, @@ -41,16 +49,16 @@ class TestGetTransformBucket: result = get_transform_bucket(mock_s3_client) assert result == "transform_bucket" - def test_get_transform_bucket_only_returns_transform_bucket_if_several_buckets(self, mock_s3_client): + def test_only_returns_transform_bucket_if_several_buckets(self, mock_s3_client): mock_s3_client.create_bucket( - Bucket="extract_bucket", + Bucket="another_test_bucket", CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, ) result = get_transform_bucket(mock_s3_client) assert result == "transform_bucket" class TestConvertParquetToDfs: - pass + pass class TestUploadDfsToDatabase: pass \ No newline at end of file -- cgit v1.2.3 From 0f8f376fe806ea72f056356cc043213f61159697 Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 14:35:36 +0100 Subject: add retrieve secrets function --- src/load_lambda.py | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index a9d5ac5..2dc90ba 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -40,10 +40,29 @@ def lambda_handler(event, context): logger.error(f"Error: {e}", exc_info=True) return {"statusCode": 500, "body": json.dumps("Internal server error.")} +def retrieve_secrets(): + secret_name = "bentley-RDS-credentials" + region_name = "eu-west-2" + + # Create a Secrets Manager client + session = boto3.session.Session() + client = session.client(service_name="secretsmanager", region_name=region_name) + + try: + get_secret_value_response = client.get_secret_value(SecretId=secret_name) + except ClientError as e: + logger.error(f"Failed to retrieve secret {secret_name}: {str(e)}") + raise e + except KeyError: + logger.error(f"Secret {secret_name} does not contain a SecretString") + raise ValueError(f"Secret {secret_name} does not contain a SecretString") + + return get_secret_value_response["SecretString"] + # connect to database, slightly different way of doing it, to allow manipulation through pandas def connect_to_db_and_return_engine(): try: - secrets = json.loads(retrieve_secrets("bentley-RDS-credentials")) #need to amend retrieve secrets function + secrets = json.loads(retrieve_secrets()) host = secrets["host"] port = secrets["port"] user = secrets["user"] -- cgit v1.2.3 From 88f1ef765a9d1113757552ee38ad1bbdb708b629 Mon Sep 17 00:00:00 2001 From: lian-manonog <160282780+lian-manonog@users.noreply.github.com> Date: Fri, 23 Aug 2024 14:53:06 +0100 Subject: Removed redundant empty lines of code --- tests/test_fact_sales_order.py | 4 ---- 1 file changed, 4 deletions(-) diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py index dad245e..7592f68 100644 --- a/tests/test_fact_sales_order.py +++ b/tests/test_fact_sales_order.py @@ -5,10 +5,6 @@ from src.fact_sales_order import ( create_dim_staff, create_dim_currency, ) -<< << << < Updated upstream -== == == = ->>>>>> > Stashed changes - class TestCreateDimDesign: def test_dim_design_returns_dataframe(self): -- cgit v1.2.3 From 59035d00133eed3f258f75e3a99ce57cae35989d Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Fri, 23 Aug 2024 13:53:17 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 88f1ef7 according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/94 --- tests/test_fact_sales_order.py | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py index 7592f68..48426b4 100644 --- a/tests/test_fact_sales_order.py +++ b/tests/test_fact_sales_order.py @@ -6,6 +6,7 @@ from src.fact_sales_order import ( create_dim_currency, ) + class TestCreateDimDesign: def test_dim_design_returns_dataframe(self): d = { @@ -56,8 +57,7 @@ class TestCreateDimStaff: "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"], } - test_df = {"staff": pd.DataFrame( - data=d), "department": pd.DataFrame(data=d2)} + test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) assert isinstance(result, pd.DataFrame) @@ -74,8 +74,7 @@ class TestCreateDimStaff: "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"], } - test_df = {"staff": pd.DataFrame( - data=d), "department": pd.DataFrame(data=d2)} + test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) expected_d = { "staff_id": ["Hello", "Bye"], -- cgit v1.2.3 From a69fe58b47bcc5ad02986bcf404f060774aec9a7 Mon Sep 17 00:00:00 2001 From: lian-manonog Date: Fri, 23 Aug 2024 16:22:52 +0100 Subject: wip: pushing again --- src/dataframes.py | 12 ++++++------ src/transform_lambda.py | 1 + tests/test_transform_lambda.py | 43 +++++++++++++++++++++++++++++++++++++++--- 3 files changed, 47 insertions(+), 9 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 684f102..18e1fac 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -1,11 +1,11 @@ import pandas as pd from bs4 import BeautifulSoup -from src.transform_lambda import read_from_s3_subfolder_to_df, tables -from src.extract_lambda import extract_bucket -import json -import boto3 -import re -from datetime import datetime as dt +# from src.transform_lambda import read_from_s3_subfolder_to_df, tables +# from src.extract_lambda import extract_bucket +# import json +# import boto3 +# import re +# from datetime import datetime as dt import requests # Table names: diff --git a/src/transform_lambda.py b/src/transform_lambda.py index defa15d..7677f66 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -207,5 +207,6 @@ def list_existing_s3_files(bucket_name, client=boto3.client("s3")): except ClientError as e: logger.error(f"Error listing S3 objects: {e}") + raise e return existing_files diff --git a/tests/test_transform_lambda.py b/tests/test_transform_lambda.py index 37ca08f..06235f7 100644 --- a/tests/test_transform_lambda.py +++ b/tests/test_transform_lambda.py @@ -1,12 +1,19 @@ -from src.transform_lambda import read_from_s3_subfolder_to_df +from src.transform_lambda import read_from_s3_subfolder_to_df, list_existing_s3_files from moto import mock_aws import pytest import pandas as pd import os import boto3 +from botocore.exceptions import ClientError import numpy as np +# import caplog +import logging + +logger = logging.getLogger() +logger.setLevel(logging.INFO) + @pytest.fixture(scope="class") def aws_credentials(): os.environ["AWS_ACCESS_KEY_ID"] = "testing" @@ -23,7 +30,7 @@ def s3_client(aws_credentials): class TestReadFromS3: - @pytest.mark.skip(reason="The test is broken!") + # @pytest.mark.skip(reason="The test is broken!") def test_returns_dictionary_with_correct_value_pair(self, s3_client): s3_client.create_bucket( Bucket="dummy_buc", @@ -53,7 +60,7 @@ class TestReadFromS3: assert isinstance(result["Foods"], pd.DataFrame) assert result["Foods"].eq(expected_df, axis="columns").all(axis=None) - @pytest.mark.skip(reason="The test is broken!") + # @pytest.mark.skip(reason="The test is broken!") def test_returns_dictionary_of_dataframes_for_multiple_tables(self, s3_client): s3_client.upload_file( "tests/dummy_2.csv", "dummy_buc", "Cars/2024/08/21/Cars_14:03:56.csv" @@ -84,3 +91,33 @@ class TestReadFromS3: assert list(result.keys()) == tables assert result["Foods"].eq(expected_foods_df, axis="columns").all(axis=None) assert result["Cars"].eq(expected_cars_df, axis="columns").all(axis=None) + +class TestListExistingFiles: + def test_functions_receives_error_if_no_bucket(self, s3_client, caplog): + caplog.set_level(logging.INFO) + + with pytest.raises(ClientError): + list_existing_s3_files('rando_bucket', client=s3_client) + + assert "Error listing S3 objects: An error occurred (NoSuchBucket) when calling the ListObjectsV2 operation: The specified bucket does not exist" in caplog.text + + def test_recieves_logger_error_if_no_files_listed(self, s3_client, caplog): + caplog.set_level(logging.INFO) + + s3_client.create_bucket( + Bucket='mock_bucket', + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"} + ) + response = list_existing_s3_files('mock_bucket', client=s3_client) + assert 'The bucket is empty' in caplog.text + + def test_retrieves_existing_files(self, s3_client, caplog): + caplog.set_level(logging.INFO) + + s3_client.upload_file( + "tests/dummy.txt", 'mock_bucket', "dummy.txt" + ) + result = list_existing_s3_files('mock_bucket', client=s3_client) + assert result == ["dummy.txt"] + + \ No newline at end of file -- cgit v1.2.3 From f1e10e1a2f573c152b19a630577a71ce9aff2bb4 Mon Sep 17 00:00:00 2001 From: lian-manonog Date: Fri, 23 Aug 2024 16:35:55 +0100 Subject: wip: writing more tests for the helper functions --- tests/test_transform_lambda.py | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/tests/test_transform_lambda.py b/tests/test_transform_lambda.py index 06235f7..00f3d83 100644 --- a/tests/test_transform_lambda.py +++ b/tests/test_transform_lambda.py @@ -1,4 +1,4 @@ -from src.transform_lambda import read_from_s3_subfolder_to_df, list_existing_s3_files +from src.transform_lambda import read_from_s3_subfolder_to_df, list_existing_s3_files, bucket_name from moto import mock_aws import pytest import pandas as pd @@ -120,4 +120,14 @@ class TestListExistingFiles: result = list_existing_s3_files('mock_bucket', client=s3_client) assert result == ["dummy.txt"] - \ No newline at end of file +class TestBucketName: + def test_functions_retrieves_bucket(self, s3_client): + s3_client.create_bucket( + Bucket='mock_bucket', + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"} + ) + + bucket = bucket_name('mock_bucket', s3_client) + assert bucket == 'mock_bucket' + + # def test_ \ No newline at end of file -- cgit v1.2.3 From 500ebf24c746ec87c9c846f5a82d638cc23983b9 Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 17:04:08 +0100 Subject: add amendendments for upload_dfs_to_db --- src/load_lambda.py | 47 ++++++++++++++++++++++++++++++++++------------- 1 file changed, 34 insertions(+), 13 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 2dc90ba..8eaea32 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -24,7 +24,7 @@ logging.getLogger("botocore").setLevel(logging.INFO) def lambda_handler(event, context): try: uploaded_tables = upload_dfs_to_database() - if not uploaded_tables: + if not uploaded_tables["uploaded"]: return { "statusCode": 200, "body": json.dumps("No dataframes were uploaded."), @@ -33,7 +33,7 @@ def lambda_handler(event, context): "statusCode": 200, "body": json.dumps( f"""The following dataframes were uploaded successfully: - {', '.join(uploaded_tables)} .""" + {uploaded_tables["uploaded"]} .""" ), } except Exception as e: @@ -133,17 +133,38 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): return dfs def upload_dfs_to_database(): - uploaded = [] + upload_status = {"uploaded": [], "not_uploaded": []} dict_of_dfs = convert_parquet_files_to_dfs() db_engine = connect_to_db_and_return_engine() - try: - for table_name, df in dict_of_dfs.items(): - df.to_sql(table_name, con=db_engine, if_exists="replace", index=False) - uploaded.append(table_name) - except Exception as e: - logger.error(f"Error uploading dataframes: {e}") - raise + immutable_df_dict = ["dim_counterparty.parquet", + "dim_date.parquet", #this needs to be mutable + "dim_location.parquet", + "dim_staff.parquet", + "dim_design.parquet"] + mutable_df_dict = ["fact_sales_order", + "fact_purchase_order", + "fact_payment", + "dim_currency"] + + for file_name, df in dict_of_dfs.items(): + if file_name in immutable_df_dict: + table_name = file_name.split(".")[0] + try: + df.to_sql(table_name, con=db_engine, schema="project_team_2", if_exists="overwrite", index=False) + upload_status["uploaded"].append(table_name) + except Exception as e: + logger.error(f"Error uploading dataframe {file_name} to database: {e}") + raise + elif file_name.rsplit('_', 1)[0] in mutable_df_dict: + table_name = file_name.rsplit('_', 1)[0] + try: + df.to_sql(table_name, con=db_engine, schema="project_team_2", if_exists="overwrite", index=False) + upload_status["uploaded"].append(table_name) + except Exception as e: + logger.error(f"Error uploading dataframe {file_name} to database: {e}") + raise + else: + upload_status["not_uploaded"].append(file_name) + logger.error(f"{file_name} does not correspond with table in database") db_engine.dispose() - return uploaded - - # aiming to return a list of uploaded tables \ No newline at end of file + return upload_status \ No newline at end of file -- cgit v1.2.3 From e26b7be8331d89826fbf95e1b1bd4fe88186c307 Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 17:04:29 +0100 Subject: add updated tests --- tests/test_load_lambda.py | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index f1c2b01..3e42c2a 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -25,6 +25,9 @@ def mock_s3_client(aws_credentials): class TestLambdaHandler: pass +class TestRetrieveSecrets: + pass + class TestConnectToDBAndReturnEngine: pass @@ -58,7 +61,18 @@ class TestGetTransformBucket: assert result == "transform_bucket" class TestConvertParquetToDfs: - pass + def test_function_returns_empty_dictionary_if_no_files(self, mock_s3_client): + mock_s3_client.create_bucket( + Bucket="transform_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) + result = convert_parquet_files_to_dfs(bucket_name="transform_bucket", client=mock_s3_client) + assert result == {} + + def test_function_returns_dictionary_with_table_with_file_key(): + # need to mock parquet file and upload to mock bucket + result = convert_parquet_files_to_dfs(bucket_name="transform_bucket", client=mock_s3_client) + assert "dim_staff" in result class TestUploadDfsToDatabase: pass \ No newline at end of file -- cgit v1.2.3 From 0ff29566a1eb9551bb83bcc07705c932d22f8c08 Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 17:06:59 +0100 Subject: add updated test --- tests/test_load_lambda.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 3e42c2a..e04ccec 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -69,10 +69,10 @@ class TestConvertParquetToDfs: result = convert_parquet_files_to_dfs(bucket_name="transform_bucket", client=mock_s3_client) assert result == {} - def test_function_returns_dictionary_with_table_with_file_key(): - # need to mock parquet file and upload to mock bucket - result = convert_parquet_files_to_dfs(bucket_name="transform_bucket", client=mock_s3_client) - assert "dim_staff" in result + # def test_function_returns_dictionary_with_table_with_file_key(): + # # need to mock parquet file and upload to mock bucket + # result = convert_parquet_files_to_dfs(bucket_name="transform_bucket", client=mock_s3_client) + # assert "dim_staff" in result class TestUploadDfsToDatabase: pass \ No newline at end of file -- cgit v1.2.3 From 821e241c925e682845e02e9609ba3a2c758966d8 Mon Sep 17 00:00:00 2001 From: Ang Bel Date: Fri, 23 Aug 2024 17:09:27 +0100 Subject: tests: additional tests written (pass) for dim tables transformation. Fact transformation functions not yet tested --- src/dataframes.py | 30 ++++++----- tests/test_fact_sales_order.py | 113 ++++++++++++++++++++++++----------------- 2 files changed, 82 insertions(+), 61 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 042c8aa..7d10aa7 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -81,28 +81,28 @@ def create_fact_payment(dict_of_df): ]] return fact_payment +#test passed def create_dim_transaction(dict_of_df): - df_transaction = dict_of_df["transaction"].drop(labels=['created_at', 'last_updated'], axis=1).set_index('transaction_id') - dim_transaction = df_transaction.loc[:, ["payment_type_id", "payment_type_name"]] - return dim_transaction + df_transaction = dict_of_df["transaction"].drop(labels=['created_at', 'last_updated'], axis=1) + return df_transaction -## dim_location from address --> drops 2 columns +#test passed def create_dim_location(dict_of_df): - df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}).set_index('location_id') + df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}) return df_loc -## dim_counterparty from address and counterparty + def create_dim_counterparty(dict_of_df): df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) df_cp = pd.merge(dict_of_df['counterparty'], df_prefixed_address, left_on="legal_address_id", - right_on="address_id", - how="outer").set_index('counterparty_id') + right_on="counterparty_legal_address_id", + how="outer") + df_cp.drop(columns=["legal_address_id","counterparty_legal_address_id"],inplace=True) return df_cp - -## dim_date from purchase_order +#test passed def create_dim_date(dict_of_df): fact_dfs = [create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df)] date_col_names = [col_name for col_name in list(fact_dfs[0].columns) if 'date' in col_name] @@ -119,9 +119,10 @@ def create_dim_date(dict_of_df): df_date['day_of_week'] = df_date['date_id'].dt.dayofweek df_date['day_name'] = df_date['date_id'].dt.day_name() df_date['month_name'] = df_date['date_id'].dt.month_name() - df_date['quarter'] = df_date['date_id'].dt.quarter #By default, the DataFrame index is not included when uploading to RDS. We are not setting indexes to retain the column information - return + df_date['quarter'] = df_date['date_id'].dt.quarter + return df_date +#tests passed def scrape_currency_names(): response = requests.get('https://www.xe.com/currency/').content soup = BeautifulSoup(response,'html.parser') @@ -130,11 +131,12 @@ def scrape_currency_names(): df_cur = sr.str.split(pat=" - ",expand=True).rename({0:'currency_code',1:'currency_name'},axis=1) return df_cur +#tests passed def create_dim_currency(dict_of_df,names=scrape_currency_names()): df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1) - dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner').set_index('currency_id') - print(dim_cur) + dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner') return dim_cur + #tests passed def create_dim_payment_type(dict_of_df): df_payment_type = dict_of_df["payment_type"] diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py index ca53faa..f0796eb 100644 --- a/tests/test_fact_sales_order.py +++ b/tests/test_fact_sales_order.py @@ -1,6 +1,7 @@ -from src.dataframes import create_dim_design, create_dim_staff, create_dim_payment_type, create_dim_counterparty, create_dim_currency +from src.dataframes import * import pandas as pd from unittest.mock import patch +from datetime import datetime as dt class TestCreateDimDesign: def test_dim_design_returns_dataframe(self): @@ -52,59 +53,77 @@ class TestCreatePaymentType: assert result.equals(expected_df) class TestCreateDimCounterparty: - def test_create_dim_counterparty_type_returns_correct_columns_and_values(self): - data_d = {"counterparty_id": ["Hello", "Bye"], + + def test_create_dim_counterparty_type_returns_correct_columns_and_object(self): + data_l = pd.DataFrame(data={"counterparty_id": ["Hello", "Bye"], "counterparty_legal_name": ["Hello", "Bye"], - "counterparty_legal_address_line_1": ["Hello", "Bye"], - } - data_a = {"address_id": - "address", - } - test_df = {"address": pd.DataFrame(data=data_a)} - test_df = {} + "commercial_contact": ["Hello", "Bye"], + "legal_address_id": ["bond street", "regent street"]}) + data_a = pd.DataFrame(data={"address_id":["bond street", "regent street"], + "postcode":[98365,93753]}) + test_df = {"address": data_a,"counterparty":data_l} result = create_dim_counterparty(test_df) - expected_columns = ["counterparty_id", - "counterparty_legal_name", - "counterparty_legal_address_line_1", - "counterparty_legal_address_line_2", - "counterparty_legal_district", - "counterparty_legal_city", - "counterparty_legal_postal_code", - "counterparty_legal_postal_code", - "counterparty_legal_phone_number"] - expected_d = {"counterparty_id": ["Hello", "Bye"], - "counterparty_legal_name": ["Hello", "Bye"], - "counterparty_legal_address_line_1": ["Hello", "Bye"], - "counterparty_legal_address_line_2": ["Hello", "Bye"], - "counterparty_legal_district": ["Hello", "Bye"], - "counterparty_legal_city": ["Hello", "Bye"], - "counterparty_legal_postal_code": ["Hello", "Bye"], - "counterparty_legal_postal_code": ["Hello", "Bye"], - "counterparty_legal_phone_number": ["Hello", "Bye"]} - expected_df = pd.DataFrame(data=expected_d) + expected_columns = ["counterparty_id", "counterparty_legal_name", + "commercial_contact", "counterparty_legal_postcode"] + print(data_l) + print(data_a) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns - assert result.equals(expected_df) -# # figuring out how to mock currency scraper functiom -# class TestCreateDimCurrency: -# @patch("src.dataframes.scrape_currency_names") -# def test_dim_currency_returns_columns_and_values(self): -# d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"]} -# test_df = {"currency": pd.DataFrame(data=d)} -# result = create_dim_currency(test_df) -# expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} -# expected_df = pd.DataFrame(data=expected_d) -# expected_result = expected_df.copy() -# assert result.equals(expected_result) +class TestCreateDimCurrency: + + def test_dim_currency_returns_columns_and_values(self): + nones = [None,None,None] + d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"],"created_at":nones,"last_updated":nones} + test_df = {"currency": pd.DataFrame(data=d)} + scraper_output = pd.DataFrame({"currency_code":["RUS","USD","PHP","GBP","EUR"],"currency_name":["Rubble","US Dollar","Peso","Pound","Euro"]}) + result = create_dim_currency(test_df,names=scraper_output).sort_values(by="currency_code",axis=0) + expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} + expected_df = pd.DataFrame(data=expected_d).sort_values(by="currency_code",axis=0) + assert isinstance(result, pd.DataFrame) + assert result.equals(expected_df) -# def test_dim_currency_returns_dataframe(self): -# d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"]} -# test_df = {"currency": pd.DataFrame(data=d)} -# result = create_dim_currency(test_df) -# assert isinstance(result, pd.DataFrame) + def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self): + result = scrape_currency_names() + assert isinstance(result,pd.DataFrame) + assert list(result.columns) == ['currency_code', 'currency_name'] + +class TestCreateDimDate: + + def test_returns_required_columns(self): + df_one = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 5, 13),'not_dat':None},index=[0]) + df_two = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 9, 13)},index=[0]) + df_three = pd.DataFrame(data={'updated_date':dt(2022, 5, 17),'created_date':dt(2023, 5, 13)},index=[0]) + expected_df = pd.DataFrame(data= + [[dt(2020,5,17),2020,5,17,6,'Sunday','May',2], + [dt(2021,5,13),2021,5,13,3,'Thursday','May',2], + [dt(2021,9,13),2021,9,13,0,'Monday','September',3], + [dt(2022,5,17),2022,5,17,1,'Tuesday','May',2], + [dt(2023,5,13),2023,5,13,5,'Saturday','May',2]], + columns=['date_id','year','month','day','day_of_week','day_name','month_name','quarter']) + with patch("src.dataframes.create_fact_payment") as mock_fp: + with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo: + with patch("src.dataframes.create_fact_sales_order") as mock_fso: + mock_fp.return_value = df_one + mock_fpo.return_value = df_two + mock_fso.return_value = df_three + result = create_dim_date({'dum':0}) + result.reset_index(inplace=True,drop=True) + assert result.eq(expected_df, axis="columns").all(axis=None) - +class TestCreateDimLocation: + def test_returns_correct_columns_lo(self): + dict_df = {'address':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], + columns=['created_at','last_updated','address_id','postal_code'])} + result = create_dim_location(dict_df) + assert list(result.columns) == ['location_id','postal_code'] + +class TestCreateDimTransaction: + def test_returns_correct_columns_tr(self): + dict_df = {'transaction':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], + columns=['created_at','last_updated','transaction_id','some_other_id'])} + result = create_dim_transaction(dict_df) + assert list(result.columns) == ['transaction_id','some_other_id'] \ No newline at end of file -- cgit v1.2.3 From 30525f27ba1d20c65216cbe58a62953b8f1fe947 Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Fri, 23 Aug 2024 16:11:04 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 821e241 according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/96 --- src/dataframes.py | 250 +++++++++++++++++++++++++---------------- tests/test_fact_sales_order.py | 235 ++++++++++++++++++++++++++++---------- 2 files changed, 330 insertions(+), 155 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 7d10aa7..737ee2a 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -2,7 +2,7 @@ import pandas as pd from bs4 import BeautifulSoup import requests -#Table names: +# Table names: # fact_sales_order # fact_purchase_orders # fact_payment @@ -16,7 +16,6 @@ import requests # dim_counterparty - def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" @@ -24,36 +23,46 @@ def create_fact_sales_order(dict_of_df): df_sales["created_time"] = pd.to_datetime(df_sales["created_at"]).dt.time df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"]).dt.date df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time - fact_sales_order = df_sales.loc[:,[ - "sales_record_id", - "sales_order_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "sales_staff_id", - "counterparty_id", - "units_sold", - "unit_price", - "currency_id", - "design_id", - "agreed_payment_date", - "agreed_delivery_date", - "agreed_delivery_location_id" - ]] + fact_sales_order = df_sales.loc[ + :, + [ + "sales_record_id", + "sales_order_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "sales_staff_id", + "counterparty_id", + "units_sold", + "unit_price", + "currency_id", + "design_id", + "agreed_payment_date", + "agreed_delivery_date", + "agreed_delivery_location_id", + ], + ] return fact_sales_order -## fact_purchase_order from purchase_order + +# fact_purchase_order from purchase_order + + def create_fact_purchase_orders(dict_of_df): - df_po = dict_of_df['purchase_order'] - df_po.index.name = 'purchase_record_id' - df_po['created_date'] = df_po['created_at'].date() - df_po['created_time'] = df_po['created_at'].dt.time - df_po['last_updated_date'] = df_po['last_updated_at'].date() - df_po['last_updated_time'] = df_po['last_updated_at'].dt.time - df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") - df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") - df_po.drop(labels=['created_at','last_updated_at'],axis=1,inplace=True) + df_po = dict_of_df["purchase_order"] + df_po.index.name = "purchase_record_id" + df_po["created_date"] = df_po["created_at"].date() + df_po["created_time"] = df_po["created_at"].dt.time + df_po["last_updated_date"] = df_po["last_updated_at"].date() + df_po["last_updated_time"] = df_po["last_updated_at"].dt.time + df_po["agreed_delivery_date"] = pd.to_datetime( + df_po["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_po["agreed_payment_date"] = pd.to_datetime( + df_po["agreed_payment_date"], format="%Y-%m-%d" + ) + df_po.drop(labels=["created_at", "last_updated_at"], axis=1, inplace=True) return df_po @@ -64,109 +73,158 @@ def create_fact_payment(dict_of_df): df_payment["created_time"] = pd.to_datetime(df_payment["created_at"]).dt.time df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"]).dt.date df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"]).dt.time - fact_payment = df_payment.loc[:,[ - "payment_record_id", - "payment_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "transaction_id", - "counterparty_id", - "payment_amount", - "currency_id", - "payment_type_id", - "paid", - "payment_date" - ]] + fact_payment = df_payment.loc[ + :, + [ + "payment_record_id", + "payment_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "transaction_id", + "counterparty_id", + "payment_amount", + "currency_id", + "payment_type_id", + "paid", + "payment_date", + ], + ] return fact_payment -#test passed + +# test passed + + def create_dim_transaction(dict_of_df): - df_transaction = dict_of_df["transaction"].drop(labels=['created_at', 'last_updated'], axis=1) + df_transaction = dict_of_df["transaction"].drop( + labels=["created_at", "last_updated"], axis=1 + ) return df_transaction -#test passed + +# test passed + + def create_dim_location(dict_of_df): - df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}) + df_loc = ( + dict_of_df["address"] + .drop(labels=["created_at", "last_updated"], axis=1) + .rename(columns={"address_id": "location_id"}) + ) return df_loc def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) - df_cp = pd.merge(dict_of_df['counterparty'], - df_prefixed_address, - left_on="legal_address_id", - right_on="counterparty_legal_address_id", - how="outer") - df_cp.drop(columns=["legal_address_id","counterparty_legal_address_id"],inplace=True) + df_prefixed_address = dict_of_df["address"].add_prefix( + "counterparty_legal_", axis=1 + ) + df_cp = pd.merge( + dict_of_df["counterparty"], + df_prefixed_address, + left_on="legal_address_id", + right_on="counterparty_legal_address_id", + how="outer", + ) + df_cp.drop( + columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True + ) return df_cp -#test passed + +# test passed + + def create_dim_date(dict_of_df): - fact_dfs = [create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df)] - date_col_names = [col_name for col_name in list(fact_dfs[0].columns) if 'date' in col_name] + fact_dfs = [ + create_fact_payment(dict_of_df), + create_fact_purchase_orders(dict_of_df), + create_fact_sales_order(dict_of_df), + ] + date_col_names = [ + col_name for col_name in list(fact_dfs[0].columns) if "date" in col_name + ] list_of_date_columns = [] for df in fact_dfs: for col in date_col_names: list_of_date_columns.append(df[col]) - sr_date = pd.array(pd.concat(list_of_date_columns),dtype='datetime64[ns]') - df_date = pd.DataFrame(data=sr_date,columns=['date_id']) + sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") + df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) df_date.drop_duplicates(inplace=True) - df_date['year'] = df_date['date_id'].dt.year - df_date['month'] = df_date['date_id'].dt.month - df_date['day'] = df_date['date_id'].dt.day - df_date['day_of_week'] = df_date['date_id'].dt.dayofweek - df_date['day_name'] = df_date['date_id'].dt.day_name() - df_date['month_name'] = df_date['date_id'].dt.month_name() - df_date['quarter'] = df_date['date_id'].dt.quarter + df_date["year"] = df_date["date_id"].dt.year + df_date["month"] = df_date["date_id"].dt.month + df_date["day"] = df_date["date_id"].dt.day + df_date["day_of_week"] = df_date["date_id"].dt.dayofweek + df_date["day_name"] = df_date["date_id"].dt.day_name() + df_date["month_name"] = df_date["date_id"].dt.month_name() + df_date["quarter"] = df_date["date_id"].dt.quarter return df_date -#tests passed -def scrape_currency_names(): - response = requests.get('https://www.xe.com/currency/').content - soup = BeautifulSoup(response,'html.parser') - currency = [item.text for item in soup.findAll('a', attrs={'class' : "sc-299dec64-6 fZPTSw"})] - sr = pd.Series(currency) - df_cur = sr.str.split(pat=" - ",expand=True).rename({0:'currency_code',1:'currency_name'},axis=1) - return df_cur - -#tests passed -def create_dim_currency(dict_of_df,names=scrape_currency_names()): - df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1) - dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner') - return dim_cur -#tests passed -def create_dim_payment_type(dict_of_df): - df_payment_type = dict_of_df["payment_type"] - dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] - return dim_payment_type +# tests passed -#tests passed -def create_dim_design(dict_of_df): - df_design = dict_of_df["design"] - dim_design = df_design.loc[:, ["design_id", "design_name", "file_name", "file_location"]] - return dim_design -#tests passed -def create_dim_staff(dict_of_df): - staff_department = pd.merge(dict_of_df["staff"], dict_of_df["department"], on='department_id', how="left") - dim_staff = staff_department.loc[:, ['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address']] - return dim_staff +def scrape_currency_names(): + response = requests.get("https://www.xe.com/currency/").content + soup = BeautifulSoup(response, "html.parser") + currency = [ + item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) + ] + sr = pd.Series(currency) + df_cur = sr.str.split(pat=" - ", expand=True).rename( + {0: "currency_code", 1: "currency_name"}, axis=1 + ) + return df_cur +# tests passed +def create_dim_currency(dict_of_df, names=scrape_currency_names()): + df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) + dim_cur = pd.merge( + df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" + ) + return dim_cur +# tests passed +def create_dim_payment_type(dict_of_df): + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + return dim_payment_type +# tests passed +def create_dim_design(dict_of_df): + df_design = dict_of_df["design"] + dim_design = df_design.loc[ + :, ["design_id", "design_name", "file_name", "file_location"] + ] + return dim_design +# tests passed +def create_dim_staff(dict_of_df): + staff_department = pd.merge( + dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" + ) + dim_staff = staff_department.loc[ + :, + [ + "staff_id", + "first_name", + "last_name", + "department_name", + "location", + "email_address", + ], + ] + return dim_staff diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py index f0796eb..a245379 100644 --- a/tests/test_fact_sales_order.py +++ b/tests/test_fact_sales_order.py @@ -3,42 +3,88 @@ import pandas as pd from unittest.mock import patch from datetime import datetime as dt + class TestCreateDimDesign: def test_dim_design_returns_dataframe(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) assert isinstance(result, pd.DataFrame) def test_dim_design_returns_correct_columns_and_values(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) - d2 = {"design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"]} + d2 = { + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=d2) expected_result = expected_df.copy() assert result.equals(expected_result) + class TestCreateDimStaff: def test_dim_staff_returns_dataframe(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - assert isinstance(result, pd.DataFrame) + assert isinstance(result, pd.DataFrame) def test_dim_staff_returns_correct_columns_and_values(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - expected_d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"]} + expected_d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) expected_result = expected_df.copy() - assert result.equals(expected_result) + assert result.equals(expected_result) + class TestCreatePaymentType: def test_create_dim_payment_type_returns_correct_columns_and_values(self): @@ -46,84 +92,155 @@ class TestCreatePaymentType: test_df = {"payment_type": pd.DataFrame(data=d)} result = create_dim_payment_type(test_df) expected_columns = ["payment_type_id", "payment_type_name"] - expected_d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} + expected_d = { + "payment_type_id": ["Hello", "Bye"], + "payment_type_name": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns assert result.equals(expected_df) + class TestCreateDimCounterparty: - def test_create_dim_counterparty_type_returns_correct_columns_and_object(self): - data_l = pd.DataFrame(data={"counterparty_id": ["Hello", "Bye"], - "counterparty_legal_name": ["Hello", "Bye"], - "commercial_contact": ["Hello", "Bye"], - "legal_address_id": ["bond street", "regent street"]}) - data_a = pd.DataFrame(data={"address_id":["bond street", "regent street"], - "postcode":[98365,93753]}) - test_df = {"address": data_a,"counterparty":data_l} + data_l = pd.DataFrame( + data={ + "counterparty_id": ["Hello", "Bye"], + "counterparty_legal_name": ["Hello", "Bye"], + "commercial_contact": ["Hello", "Bye"], + "legal_address_id": ["bond street", "regent street"], + } + ) + data_a = pd.DataFrame( + data={ + "address_id": ["bond street", "regent street"], + "postcode": [98365, 93753], + } + ) + test_df = {"address": data_a, "counterparty": data_l} result = create_dim_counterparty(test_df) - expected_columns = ["counterparty_id", "counterparty_legal_name", - "commercial_contact", "counterparty_legal_postcode"] + expected_columns = [ + "counterparty_id", + "counterparty_legal_name", + "commercial_contact", + "counterparty_legal_postcode", + ] print(data_l) print(data_a) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns + class TestCreateDimCurrency: - def test_dim_currency_returns_columns_and_values(self): - nones = [None,None,None] - d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"],"created_at":nones,"last_updated":nones} + nones = [None, None, None] + d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "created_at": nones, + "last_updated": nones, + } test_df = {"currency": pd.DataFrame(data=d)} - scraper_output = pd.DataFrame({"currency_code":["RUS","USD","PHP","GBP","EUR"],"currency_name":["Rubble","US Dollar","Peso","Pound","Euro"]}) - result = create_dim_currency(test_df,names=scraper_output).sort_values(by="currency_code",axis=0) - expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} - expected_df = pd.DataFrame(data=expected_d).sort_values(by="currency_code",axis=0) - assert isinstance(result, pd.DataFrame) - assert result.equals(expected_df) + scraper_output = pd.DataFrame( + { + "currency_code": ["RUS", "USD", "PHP", "GBP", "EUR"], + "currency_name": ["Rubble", "US Dollar", "Peso", "Pound", "Euro"], + } + ) + result = create_dim_currency(test_df, names=scraper_output).sort_values( + by="currency_code", axis=0 + ) + expected_d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "currency_name": ["US Dollar", "Euro", "Pound"], + } + expected_df = pd.DataFrame(data=expected_d).sort_values( + by="currency_code", axis=0 + ) + assert isinstance(result, pd.DataFrame) + assert result.equals(expected_df) def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self): result = scrape_currency_names() - assert isinstance(result,pd.DataFrame) - assert list(result.columns) == ['currency_code', 'currency_name'] + assert isinstance(result, pd.DataFrame) + assert list(result.columns) == ["currency_code", "currency_name"] -class TestCreateDimDate: +class TestCreateDimDate: def test_returns_required_columns(self): - df_one = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 5, 13),'not_dat':None},index=[0]) - df_two = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 9, 13)},index=[0]) - df_three = pd.DataFrame(data={'updated_date':dt(2022, 5, 17),'created_date':dt(2023, 5, 13)},index=[0]) - expected_df = pd.DataFrame(data= - [[dt(2020,5,17),2020,5,17,6,'Sunday','May',2], - [dt(2021,5,13),2021,5,13,3,'Thursday','May',2], - [dt(2021,9,13),2021,9,13,0,'Monday','September',3], - [dt(2022,5,17),2022,5,17,1,'Tuesday','May',2], - [dt(2023,5,13),2023,5,13,5,'Saturday','May',2]], - columns=['date_id','year','month','day','day_of_week','day_name','month_name','quarter']) + df_one = pd.DataFrame( + data={ + "updated_date": dt(2020, 5, 17), + "created_date": dt(2021, 5, 13), + "not_dat": None, + }, + index=[0], + ) + df_two = pd.DataFrame( + data={"updated_date": dt(2020, 5, 17), "created_date": dt(2021, 9, 13)}, + index=[0], + ) + df_three = pd.DataFrame( + data={"updated_date": dt(2022, 5, 17), "created_date": dt(2023, 5, 13)}, + index=[0], + ) + expected_df = pd.DataFrame( + data=[ + [dt(2020, 5, 17), 2020, 5, 17, 6, "Sunday", "May", 2], + [dt(2021, 5, 13), 2021, 5, 13, 3, "Thursday", "May", 2], + [dt(2021, 9, 13), 2021, 9, 13, 0, "Monday", "September", 3], + [dt(2022, 5, 17), 2022, 5, 17, 1, "Tuesday", "May", 2], + [dt(2023, 5, 13), 2023, 5, 13, 5, "Saturday", "May", 2], + ], + columns=[ + "date_id", + "year", + "month", + "day", + "day_of_week", + "day_name", + "month_name", + "quarter", + ], + ) with patch("src.dataframes.create_fact_payment") as mock_fp: with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo: with patch("src.dataframes.create_fact_sales_order") as mock_fso: mock_fp.return_value = df_one mock_fpo.return_value = df_two mock_fso.return_value = df_three - result = create_dim_date({'dum':0}) - result.reset_index(inplace=True,drop=True) + result = create_dim_date({"dum": 0}) + result.reset_index(inplace=True, drop=True) assert result.eq(expected_df, axis="columns").all(axis=None) - -class TestCreateDimLocation: + +class TestCreateDimLocation: def test_returns_correct_columns_lo(self): - dict_df = {'address':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], - columns=['created_at','last_updated','address_id','postal_code'])} + dict_df = { + "address": pd.DataFrame( + data=[["some_time", "some_other_time", 1, "SE18 9QO"]], + columns=["created_at", "last_updated", "address_id", "postal_code"], + ) + } result = create_dim_location(dict_df) - assert list(result.columns) == ['location_id','postal_code'] - + assert list(result.columns) == ["location_id", "postal_code"] + + class TestCreateDimTransaction: - def test_returns_correct_columns_tr(self): - dict_df = {'transaction':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], - columns=['created_at','last_updated','transaction_id','some_other_id'])} + def test_returns_correct_columns_tr(self): + dict_df = { + "transaction": pd.DataFrame( + data=[["some_time", "some_other_time", 1, "SE18 9QO"]], + columns=[ + "created_at", + "last_updated", + "transaction_id", + "some_other_id", + ], + ) + } result = create_dim_transaction(dict_df) - assert list(result.columns) == ['transaction_id','some_other_id'] - \ No newline at end of file + assert list(result.columns) == ["transaction_id", "some_other_id"] -- cgit v1.2.3 From 69edb14dad584d45fa6a83a90c08292b84795507 Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Fri, 23 Aug 2024 16:11:45 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 0ff2956 according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/95 --- src/load_lambda.py | 75 ++++++++++++++++++++++++++++++++--------------- tests/test_load_lambda.py | 44 +++++++++++++++++---------- 2 files changed, 80 insertions(+), 39 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 8eaea32..6e6bc80 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -40,6 +40,7 @@ def lambda_handler(event, context): logger.error(f"Error: {e}", exc_info=True) return {"statusCode": 500, "body": json.dumps("Internal server error.")} + def retrieve_secrets(): secret_name = "bentley-RDS-credentials" region_name = "eu-west-2" @@ -59,7 +60,10 @@ def retrieve_secrets(): return get_secret_value_response["SecretString"] + # connect to database, slightly different way of doing it, to allow manipulation through pandas + + def connect_to_db_and_return_engine(): try: secrets = json.loads(retrieve_secrets()) @@ -68,13 +72,14 @@ def connect_to_db_and_return_engine(): user = secrets["user"] password = secrets["password"] database = secrets["database"] - conn_str = f'postgresql+pg8000://{user}:{password}@{host}:{port}/{database}' - engine = create_engine(conn_str) #interface between python (pandas) and SQL + conn_str = f"postgresql+pg8000://{user}:{password}@{host}:{port}/{database}" + # interface between python (pandas) and SQL + engine = create_engine(conn_str) return engine except Exception as e: logger.error(f"Interface error: {e}") raise RuntimeError("Failed to create database engine") - + # get transform bucket def get_transform_bucket(client=None): @@ -85,9 +90,11 @@ def get_transform_bucket(client=None): except ClientError as e: logger.error(f"Error listing S3 buckets: {e}") raise RuntimeError("Error listing S3 buckets") - + transform_bucket_filter = [ - bucket["Name"] for bucket in response["Buckets"] if "transform" in bucket["Name"] + bucket["Name"] + for bucket in response["Buckets"] + if "transform" in bucket["Name"] ] if not transform_bucket_filter: @@ -96,9 +103,12 @@ def get_transform_bucket(client=None): return transform_bucket_filter[0] + # list and then retrieve parquet files from S3 bucket # convert parquet files into dataframes -# return a dictionary of dataframes with name as key, and dataframe object as value +# return a dictionary of dataframes with name as key, and dataframe object as value + + def convert_parquet_files_to_dfs(bucket_name=None, client=None): try: if client is None: @@ -110,10 +120,10 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): dfs = {} if "Contents" in files: for file in files["Contents"]: - file_key = file['Key'] + file_key = file["Key"] try: file_obj = client.get_object(Bucket=bucket_name, Key=file_key) - parquet_file = pq.ParquetFile(BytesIO(file_obj['Body'].read())) + parquet_file = pq.ParquetFile(BytesIO(file_obj["Body"].read())) df = parquet_file.read().to_pandas() dfs[file_key] = df except ClientError as e: @@ -132,34 +142,51 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): return dfs + def upload_dfs_to_database(): upload_status = {"uploaded": [], "not_uploaded": []} dict_of_dfs = convert_parquet_files_to_dfs() db_engine = connect_to_db_and_return_engine() - immutable_df_dict = ["dim_counterparty.parquet", - "dim_date.parquet", #this needs to be mutable - "dim_location.parquet", - "dim_staff.parquet", - "dim_design.parquet"] - mutable_df_dict = ["fact_sales_order", - "fact_purchase_order", - "fact_payment", - "dim_currency"] - + immutable_df_dict = [ + "dim_counterparty.parquet", + "dim_date.parquet", # this needs to be mutable + "dim_location.parquet", + "dim_staff.parquet", + "dim_design.parquet", + ] + mutable_df_dict = [ + "fact_sales_order", + "fact_purchase_order", + "fact_payment", + "dim_currency", + ] + for file_name, df in dict_of_dfs.items(): if file_name in immutable_df_dict: table_name = file_name.split(".")[0] try: - df.to_sql(table_name, con=db_engine, schema="project_team_2", if_exists="overwrite", index=False) + df.to_sql( + table_name, + con=db_engine, + schema="project_team_2", + if_exists="overwrite", + index=False, + ) upload_status["uploaded"].append(table_name) except Exception as e: logger.error(f"Error uploading dataframe {file_name} to database: {e}") raise - elif file_name.rsplit('_', 1)[0] in mutable_df_dict: - table_name = file_name.rsplit('_', 1)[0] + elif file_name.rsplit("_", 1)[0] in mutable_df_dict: + table_name = file_name.rsplit("_", 1)[0] try: - df.to_sql(table_name, con=db_engine, schema="project_team_2", if_exists="overwrite", index=False) - upload_status["uploaded"].append(table_name) + df.to_sql( + table_name, + con=db_engine, + schema="project_team_2", + if_exists="overwrite", + index=False, + ) + upload_status["uploaded"].append(table_name) except Exception as e: logger.error(f"Error uploading dataframe {file_name} to database: {e}") raise @@ -167,4 +194,4 @@ def upload_dfs_to_database(): upload_status["not_uploaded"].append(file_name) logger.error(f"{file_name} does not correspond with table in database") db_engine.dispose() - return upload_status \ No newline at end of file + return upload_status diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index e04ccec..88c71e4 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -5,7 +5,14 @@ from moto import mock_aws import boto3 import os import pytest -from src.load_lambda import lambda_handler, connect_to_db_and_return_engine, get_transform_bucket, convert_parquet_files_to_dfs, upload_dfs_to_database +from src.load_lambda import ( + lambda_handler, + connect_to_db_and_return_engine, + get_transform_bucket, + convert_parquet_files_to_dfs, + upload_dfs_to_database, +) + @pytest.fixture(scope="class") def aws_credentials(): @@ -25,12 +32,15 @@ def mock_s3_client(aws_credentials): class TestLambdaHandler: pass + class TestRetrieveSecrets: pass + class TestConnectToDBAndReturnEngine: pass + class TestGetTransformBucket: def test_raises_value_error_if_no_buckets(self, mock_s3_client): with pytest.raises(ValueError, match="No transform bucket found"): @@ -38,35 +48,38 @@ class TestGetTransformBucket: def test_raises_value_error_if_no_transform_bucket(self, mock_s3_client): mock_s3_client.create_bucket( - Bucket="extract_bucket", - CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, - ) + Bucket="extract_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) with pytest.raises(ValueError, match="No transform bucket found"): get_transform_bucket(mock_s3_client) def test_returns_transform_bucket_if_one_bucket(self, mock_s3_client): mock_s3_client.create_bucket( - Bucket="transform_bucket", - CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, - ) + Bucket="transform_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) result = get_transform_bucket(mock_s3_client) assert result == "transform_bucket" def test_only_returns_transform_bucket_if_several_buckets(self, mock_s3_client): mock_s3_client.create_bucket( - Bucket="another_test_bucket", - CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, - ) + Bucket="another_test_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) result = get_transform_bucket(mock_s3_client) assert result == "transform_bucket" + class TestConvertParquetToDfs: def test_function_returns_empty_dictionary_if_no_files(self, mock_s3_client): mock_s3_client.create_bucket( - Bucket="transform_bucket", - CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, - ) - result = convert_parquet_files_to_dfs(bucket_name="transform_bucket", client=mock_s3_client) + Bucket="transform_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) + result = convert_parquet_files_to_dfs( + bucket_name="transform_bucket", client=mock_s3_client + ) assert result == {} # def test_function_returns_dictionary_with_table_with_file_key(): @@ -74,5 +87,6 @@ class TestConvertParquetToDfs: # result = convert_parquet_files_to_dfs(bucket_name="transform_bucket", client=mock_s3_client) # assert "dim_staff" in result + class TestUploadDfsToDatabase: - pass \ No newline at end of file + pass -- cgit v1.2.3 From 843471508b150f505c2b8921d175c8f9b781bf48 Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Fri, 23 Aug 2024 16:25:59 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 8f75a47 according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/96 --- src/dataframes.py | 76 +++++++++++++++++++++++------------------- tests/test_fact_sales_order.py | 3 -- 2 files changed, 41 insertions(+), 38 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index fc84f48..f2cae5d 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -16,14 +16,15 @@ import requests # dim_counterparty - def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" df_sales["created_date"] = pd.to_datetime(df_sales["created_at"]).dt.date df_sales["created_time"] = pd.to_datetime(df_sales["created_at"]).dt.time - df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"]).dt.date - df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time + df_sales["last_updated_date"] = pd.to_datetime( + df_sales["last_updated"]).dt.date + df_sales["last_updated_time"] = pd.to_datetime( + df_sales["last_updated"]).dt.time fact_sales_order = df_sales.loc[ :, [ @@ -70,10 +71,14 @@ def create_fact_purchase_orders(dict_of_df): def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = pd.to_datetime(df_payment["created_at"]).dt.date - df_payment["created_time"] = pd.to_datetime(df_payment["created_at"]).dt.time - df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"]).dt.date - df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"]).dt.time + df_payment["created_date"] = pd.to_datetime( + df_payment["created_at"]).dt.date + df_payment["created_time"] = pd.to_datetime( + df_payment["created_at"]).dt.time + df_payment["last_updated_date"] = pd.to_datetime( + df_payment["last_updated"]).dt.date + df_payment["last_updated_time"] = pd.to_datetime( + df_payment["last_updated"]).dt.time fact_payment = df_payment.loc[ :, [ @@ -95,7 +100,6 @@ def create_fact_payment(dict_of_df): return fact_payment - # test passed @@ -117,10 +121,10 @@ def create_dim_location(dict_of_df): def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df["address"].add_prefix( + df_prefixed_address=dict_of_df["address"].add_prefix( "counterparty_legal_", axis=1 ) - df_cp = pd.merge( + df_cp=pd.merge( dict_of_df["counterparty"], df_prefixed_address, left_on="legal_address_id", @@ -137,40 +141,40 @@ def create_dim_counterparty(dict_of_df): def create_dim_date(dict_of_df): - fact_dfs = [ + fact_dfs=[ create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df), ] - date_col_names = [ + date_col_names=[ col_name for col_name in list(fact_dfs[0].columns) if "date" in col_name ] - list_of_date_columns = [] + list_of_date_columns=[] for df in fact_dfs: for col in date_col_names: list_of_date_columns.append(df[col]) - sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") - df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) + sr_date=pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") + df_date=pd.DataFrame(data=sr_date, columns=["date_id"]) df_date.drop_duplicates(inplace=True) - df_date["year"] = df_date["date_id"].dt.year - df_date["month"] = df_date["date_id"].dt.month - df_date["day"] = df_date["date_id"].dt.day - df_date["day_of_week"] = df_date["date_id"].dt.dayofweek - df_date["day_name"] = df_date["date_id"].dt.day_name() - df_date["month_name"] = df_date["date_id"].dt.month_name() - df_date["quarter"] = df_date["date_id"].dt.quarter + df_date["year"]=df_date["date_id"].dt.year + df_date["month"]=df_date["date_id"].dt.month + df_date["day"]=df_date["date_id"].dt.day + df_date["day_of_week"]=df_date["date_id"].dt.dayofweek + df_date["day_name"]=df_date["date_id"].dt.day_name() + df_date["month_name"]=df_date["date_id"].dt.month_name() + df_date["quarter"]=df_date["date_id"].dt.quarter return df_date # tests passed def scrape_currency_names(): - response = requests.get("https://www.xe.com/currency/").content - soup = BeautifulSoup(response, "html.parser") - currency = [ + response=requests.get("https://www.xe.com/currency/").content + soup=BeautifulSoup(response, "html.parser") + currency=[ item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) ] - sr = pd.Series(currency) - df_cur = sr.str.split(pat=" - ", expand=True).rename( + sr=pd.Series(currency) + df_cur=sr.str.split(pat=" - ", expand=True).rename( {0: "currency_code", 1: "currency_name"}, axis=1 ) return df_cur @@ -179,8 +183,9 @@ def scrape_currency_names(): def create_dim_currency(dict_of_df, names=scrape_currency_names()): - df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) - dim_cur = pd.merge( + df_cur=dict_of_df["currency"].drop( + labels=["created_at", "last_updated"], axis=1) + dim_cur=pd.merge( df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" ) return dim_cur @@ -189,8 +194,9 @@ def create_dim_currency(dict_of_df, names=scrape_currency_names()): # tests passed def create_dim_payment_type(dict_of_df): - df_payment_type = dict_of_df["payment_type"] - dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + df_payment_type=dict_of_df["payment_type"] + dim_payment_type=df_payment_type.loc[:, [ + "payment_type_id", "payment_type_name"]] return dim_payment_type @@ -199,8 +205,8 @@ def create_dim_payment_type(dict_of_df): def create_dim_design(dict_of_df): - df_design = dict_of_df["design"] - dim_design = df_design.loc[ + df_design=dict_of_df["design"] + dim_design=df_design.loc[ :, ["design_id", "design_name", "file_name", "file_location"] ] return dim_design @@ -210,10 +216,10 @@ def create_dim_design(dict_of_df): # tests passed def create_dim_staff(dict_of_df): - staff_department = pd.merge( + staff_department=pd.merge( dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" ) - dim_staff = staff_department.loc[ + dim_staff=staff_department.loc[ :, [ "staff_id", diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py index 77395a1..a245379 100644 --- a/tests/test_fact_sales_order.py +++ b/tests/test_fact_sales_order.py @@ -4,7 +4,6 @@ from unittest.mock import patch from datetime import datetime as dt - class TestCreateDimDesign: def test_dim_design_returns_dataframe(self): d = { @@ -135,7 +134,6 @@ class TestCreateDimCounterparty: class TestCreateDimCurrency: - def test_dim_currency_returns_columns_and_values(self): nones = [None, None, None] d = { @@ -246,4 +244,3 @@ class TestCreateDimTransaction: } result = create_dim_transaction(dict_df) assert list(result.columns) == ["transaction_id", "some_other_id"] - -- cgit v1.2.3 From 72ebda950c84d7b519db9a236b35a7fafcbb1899 Mon Sep 17 00:00:00 2001 From: lian-manonog Date: Tue, 27 Aug 2024 09:30:34 +0100 Subject: wip: added a bracket in dataframes --- src/dataframes.py | 4 ++-- src/transform_lambda.py | 3 ++- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index f2cae5d..d0479f1 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -115,9 +115,9 @@ def create_dim_location(dict_of_df): df_loc = ( dict_of_df["address"] .drop(labels=["created_at", "last_updated"], axis=1) - .rename(columns={"address_id": "location_id"}) + .rename(columns={"address_id": "location_id"})) return df_loc - + def create_dim_counterparty(dict_of_df): diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 7677f66..57e9042 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -5,12 +5,13 @@ import logging import pandas as pd import pyarrow as pa import pyarrow.parquet as pq -from src.dataframes import * +from dataframes import * from botocore.exceptions import ClientError from pg8000.native import Connection, InterfaceError from datetime import datetime + class DBConnectionException(Exception): """Wraps pg8000.native Error or DatabaseError.""" -- cgit v1.2.3 From c68f63fa3aebcf9b77c24d6e2aec91a4ff4950bb Mon Sep 17 00:00:00 2001 From: lian-manonog Date: Tue, 27 Aug 2024 10:46:03 +0100 Subject: wip: refactored fact payment function --- src/dataframes.py | 14 ++++++-------- src/transform_lambda.py | 3 +++ 2 files changed, 9 insertions(+), 8 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index d0479f1..94eb509 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -71,14 +71,12 @@ def create_fact_purchase_orders(dict_of_df): def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = pd.to_datetime( - df_payment["created_at"]).dt.date - df_payment["created_time"] = pd.to_datetime( - df_payment["created_at"]).dt.time - df_payment["last_updated_date"] = pd.to_datetime( - df_payment["last_updated"]).dt.date - df_payment["last_updated_time"] = pd.to_datetime( - df_payment["last_updated"]).dt.time + df_payment["created_date"] = df_payment["created_at"].date() + df_payment["created_time"] = df_payment["created_at"].time + df_payment["last_updated_date"] = df_payment["last_updated"].date() + df_payment["last_updated_time"] = df_payment["last_updated"].time + df_payment["payment_date"] = pd.to_datetime( + df_payment["payment_date"], format="%Y-%m-%d") fact_payment = df_payment.loc[ :, [ diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 57e9042..565b4ee 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -211,3 +211,6 @@ def list_existing_s3_files(bucket_name, client=boto3.client("s3")): raise e return existing_files + +if __name__ == '__main__': + lambda_handler({}, '') \ No newline at end of file -- cgit v1.2.3 From e51e9fc3c7fa886fe5e753bd123d45c8871673bc Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Tue, 27 Aug 2024 09:46:39 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in c68f63f according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/97 --- src/dataframes.py | 74 ++++++++++++++++++++---------------------- src/transform_lambda.py | 6 ++-- tests/test_transform_lambda.py | 44 +++++++++++++++---------- 3 files changed, 65 insertions(+), 59 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 94eb509..ab53063 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -21,10 +21,8 @@ def create_fact_sales_order(dict_of_df): df_sales.index.name = "sales_record_id" df_sales["created_date"] = pd.to_datetime(df_sales["created_at"]).dt.date df_sales["created_time"] = pd.to_datetime(df_sales["created_at"]).dt.time - df_sales["last_updated_date"] = pd.to_datetime( - df_sales["last_updated"]).dt.date - df_sales["last_updated_time"] = pd.to_datetime( - df_sales["last_updated"]).dt.time + df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"]).dt.date + df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time fact_sales_order = df_sales.loc[ :, [ @@ -76,7 +74,8 @@ def create_fact_payment(dict_of_df): df_payment["last_updated_date"] = df_payment["last_updated"].date() df_payment["last_updated_time"] = df_payment["last_updated"].time df_payment["payment_date"] = pd.to_datetime( - df_payment["payment_date"], format="%Y-%m-%d") + df_payment["payment_date"], format="%Y-%m-%d" + ) fact_payment = df_payment.loc[ :, [ @@ -113,16 +112,16 @@ def create_dim_location(dict_of_df): df_loc = ( dict_of_df["address"] .drop(labels=["created_at", "last_updated"], axis=1) - .rename(columns={"address_id": "location_id"})) + .rename(columns={"address_id": "location_id"}) + ) return df_loc - def create_dim_counterparty(dict_of_df): - df_prefixed_address=dict_of_df["address"].add_prefix( + df_prefixed_address = dict_of_df["address"].add_prefix( "counterparty_legal_", axis=1 ) - df_cp=pd.merge( + df_cp = pd.merge( dict_of_df["counterparty"], df_prefixed_address, left_on="legal_address_id", @@ -139,51 +138,51 @@ def create_dim_counterparty(dict_of_df): def create_dim_date(dict_of_df): - fact_dfs=[ + fact_dfs = [ create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df), ] - date_col_names=[ + date_col_names = [ col_name for col_name in list(fact_dfs[0].columns) if "date" in col_name ] - list_of_date_columns=[] + list_of_date_columns = [] for df in fact_dfs: for col in date_col_names: list_of_date_columns.append(df[col]) - sr_date=pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") - df_date=pd.DataFrame(data=sr_date, columns=["date_id"]) + sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") + df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) df_date.drop_duplicates(inplace=True) - df_date["year"]=df_date["date_id"].dt.year - df_date["month"]=df_date["date_id"].dt.month - df_date["day"]=df_date["date_id"].dt.day - df_date["day_of_week"]=df_date["date_id"].dt.dayofweek - df_date["day_name"]=df_date["date_id"].dt.day_name() - df_date["month_name"]=df_date["date_id"].dt.month_name() - df_date["quarter"]=df_date["date_id"].dt.quarter + df_date["year"] = df_date["date_id"].dt.year + df_date["month"] = df_date["date_id"].dt.month + df_date["day"] = df_date["date_id"].dt.day + df_date["day_of_week"] = df_date["date_id"].dt.dayofweek + df_date["day_name"] = df_date["date_id"].dt.day_name() + df_date["month_name"] = df_date["date_id"].dt.month_name() + df_date["quarter"] = df_date["date_id"].dt.quarter return df_date # tests passed def scrape_currency_names(): - response=requests.get("https://www.xe.com/currency/").content - soup=BeautifulSoup(response, "html.parser") - currency=[ + response = requests.get("https://www.xe.com/currency/").content + soup = BeautifulSoup(response, "html.parser") + currency = [ item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) ] - sr=pd.Series(currency) - df_cur=sr.str.split(pat=" - ", expand=True).rename( + sr = pd.Series(currency) + df_cur = sr.str.split(pat=" - ", expand=True).rename( {0: "currency_code", 1: "currency_name"}, axis=1 ) return df_cur + # tests passed def create_dim_currency(dict_of_df, names=scrape_currency_names()): - df_cur=dict_of_df["currency"].drop( - labels=["created_at", "last_updated"], axis=1) - dim_cur=pd.merge( + df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) + dim_cur = pd.merge( df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" ) return dim_cur @@ -191,33 +190,32 @@ def create_dim_currency(dict_of_df, names=scrape_currency_names()): # tests passed + def create_dim_payment_type(dict_of_df): - df_payment_type=dict_of_df["payment_type"] - dim_payment_type=df_payment_type.loc[:, [ - "payment_type_id", "payment_type_name"]] + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] return dim_payment_type - # tests passed def create_dim_design(dict_of_df): - df_design=dict_of_df["design"] - dim_design=df_design.loc[ + df_design = dict_of_df["design"] + dim_design = df_design.loc[ :, ["design_id", "design_name", "file_name", "file_location"] ] return dim_design - # tests passed + def create_dim_staff(dict_of_df): - staff_department=pd.merge( + staff_department = pd.merge( dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" ) - dim_staff=staff_department.loc[ + dim_staff = staff_department.loc[ :, [ "staff_id", diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 565b4ee..2cd9272 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -11,7 +11,6 @@ from pg8000.native import Connection, InterfaceError from datetime import datetime - class DBConnectionException(Exception): """Wraps pg8000.native Error or DatabaseError.""" @@ -212,5 +211,6 @@ def list_existing_s3_files(bucket_name, client=boto3.client("s3")): return existing_files -if __name__ == '__main__': - lambda_handler({}, '') \ No newline at end of file + +if __name__ == "__main__": + lambda_handler({}, "") diff --git a/tests/test_transform_lambda.py b/tests/test_transform_lambda.py index 00f3d83..5ed743e 100644 --- a/tests/test_transform_lambda.py +++ b/tests/test_transform_lambda.py @@ -1,4 +1,8 @@ -from src.transform_lambda import read_from_s3_subfolder_to_df, list_existing_s3_files, bucket_name +from src.transform_lambda import ( + read_from_s3_subfolder_to_df, + list_existing_s3_files, + bucket_name, +) from moto import mock_aws import pytest import pandas as pd @@ -6,14 +10,15 @@ import os import boto3 from botocore.exceptions import ClientError import numpy as np + # import caplog import logging - logger = logging.getLogger() logger.setLevel(logging.INFO) + @pytest.fixture(scope="class") def aws_credentials(): os.environ["AWS_ACCESS_KEY_ID"] = "testing" @@ -92,42 +97,45 @@ class TestReadFromS3: assert result["Foods"].eq(expected_foods_df, axis="columns").all(axis=None) assert result["Cars"].eq(expected_cars_df, axis="columns").all(axis=None) + class TestListExistingFiles: def test_functions_receives_error_if_no_bucket(self, s3_client, caplog): caplog.set_level(logging.INFO) with pytest.raises(ClientError): - list_existing_s3_files('rando_bucket', client=s3_client) + list_existing_s3_files("rando_bucket", client=s3_client) - assert "Error listing S3 objects: An error occurred (NoSuchBucket) when calling the ListObjectsV2 operation: The specified bucket does not exist" in caplog.text + assert ( + "Error listing S3 objects: An error occurred (NoSuchBucket) when calling the ListObjectsV2 operation: The specified bucket does not exist" + in caplog.text + ) def test_recieves_logger_error_if_no_files_listed(self, s3_client, caplog): caplog.set_level(logging.INFO) s3_client.create_bucket( - Bucket='mock_bucket', - CreateBucketConfiguration={"LocationConstraint": "eu-west-2"} + Bucket="mock_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, ) - response = list_existing_s3_files('mock_bucket', client=s3_client) - assert 'The bucket is empty' in caplog.text + response = list_existing_s3_files("mock_bucket", client=s3_client) + assert "The bucket is empty" in caplog.text def test_retrieves_existing_files(self, s3_client, caplog): caplog.set_level(logging.INFO) - s3_client.upload_file( - "tests/dummy.txt", 'mock_bucket', "dummy.txt" - ) - result = list_existing_s3_files('mock_bucket', client=s3_client) + s3_client.upload_file("tests/dummy.txt", "mock_bucket", "dummy.txt") + result = list_existing_s3_files("mock_bucket", client=s3_client) assert result == ["dummy.txt"] + class TestBucketName: def test_functions_retrieves_bucket(self, s3_client): s3_client.create_bucket( - Bucket='mock_bucket', - CreateBucketConfiguration={"LocationConstraint": "eu-west-2"} + Bucket="mock_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, ) - - bucket = bucket_name('mock_bucket', s3_client) - assert bucket == 'mock_bucket' - # def test_ \ No newline at end of file + bucket = bucket_name("mock_bucket", s3_client) + assert bucket == "mock_bucket" + + # def test_ -- cgit v1.2.3 From 151429859bca904cbacf18f4b169f1f768fa212a Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 12:01:53 +0100 Subject: remove import as not required --- src/load_lambda.py | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 6e6bc80..685c562 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -5,7 +5,6 @@ import pyarrow.parquet as pq from io import BytesIO import logging import json -from src.extract_lambda import retrieve_secrets from sqlalchemy import create_engine @@ -169,7 +168,7 @@ def upload_dfs_to_database(): table_name, con=db_engine, schema="project_team_2", - if_exists="overwrite", + if_exists="append", index=False, ) upload_status["uploaded"].append(table_name) @@ -183,7 +182,7 @@ def upload_dfs_to_database(): table_name, con=db_engine, schema="project_team_2", - if_exists="overwrite", + if_exists="append", index=False, ) upload_status["uploaded"].append(table_name) @@ -195,3 +194,6 @@ def upload_dfs_to_database(): logger.error(f"{file_name} does not correspond with table in database") db_engine.dispose() return upload_status + +if __name__ == "__main__": + lambda_handler(None, None) -- cgit v1.2.3 From a6765659cbeffeae48111f0797d3b4d0752ae80c Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 12:02:19 +0100 Subject: add test progress --- tests/test_load_lambda.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 88c71e4..30e55f3 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -18,7 +18,7 @@ from src.load_lambda import ( def aws_credentials(): os.environ["AWS_ACCESS_KEY_ID"] = "testing" os.environ["AWS_SECRET_ACCESS_KEY"] = "testing" - os.environ["AWS_SECURIT_TOKEN"] = "testing" + os.environ["AWS_SECURITY_TOKEN"] = "testing" os.environ["AWS_SESSION_TOKEN"] = "testing" os.environ["AWS_DEFAULT_REGION"] = "eu-west-2" @@ -88,5 +88,6 @@ class TestConvertParquetToDfs: # assert "dim_staff" in result -class TestUploadDfsToDatabase: - pass +@pytest.fixture +def mock_parquet_file(mocker): + return mocker.patch(src.load_lambda.convert_parquet_files_to_dfs()) -- cgit v1.2.3 From ec4a953ac73e6b828c61defe4d234a690461fcb6 Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 12:28:27 +0100 Subject: add first retrieve secrets test --- tests/test_load_lambda.py | 44 +++++++++++++++++++++++++++++++++----------- 1 file changed, 33 insertions(+), 11 deletions(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 30e55f3..3df94e4 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -5,13 +5,7 @@ from moto import mock_aws import boto3 import os import pytest -from src.load_lambda import ( - lambda_handler, - connect_to_db_and_return_engine, - get_transform_bucket, - convert_parquet_files_to_dfs, - upload_dfs_to_database, -) +from src.load_lambda import * @pytest.fixture(scope="class") @@ -27,14 +21,43 @@ def aws_credentials(): def mock_s3_client(aws_credentials): with mock_aws(): yield boto3.client("s3") + +@pytest.fixture(scope="class") +def mock_sm_client(aws_credentials): + with mock_aws(): + yield boto3.client("secretsmanager") + + +@pytest.fixture +def mock_parquet_file(mocker): + return mocker.patch("src.load_lambda.convert_parquet_files_to_dfs") class TestLambdaHandler: pass class TestRetrieveSecrets: - pass + def test_retrieve_secrets_returns_dictionary(self, mock_sm_client): + secret = { + "cohort_id": "test_cohort_id", + "user": "test_user_id", + "password": "test_password", + "host": "test_host", + "database": "test_database", + "port": "test_port", + } + + secret_name = "test_secret" + + mock_sm_client.create_secret( + Name=secret_name, SecretString=json.dumps(secret) + ) + + result = retrieve_secrets(mock_sm_client, secret_name) + + assert isinstance(result, dict) + class TestConnectToDBAndReturnEngine: @@ -88,6 +111,5 @@ class TestConvertParquetToDfs: # assert "dim_staff" in result -@pytest.fixture -def mock_parquet_file(mocker): - return mocker.patch(src.load_lambda.convert_parquet_files_to_dfs()) +def mock_connect_db(mocker): + return mocker.patch("src.load_lambda.connect_to_db_and_return_engine") \ No newline at end of file -- cgit v1.2.3 From 8cd9edde84f4ca706ad93b143c5ff7e3397ce981 Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 12:28:58 +0100 Subject: add json.loads to retrieve secrests function --- src/load_lambda.py | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 685c562..f08e335 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -40,16 +40,19 @@ def lambda_handler(event, context): return {"statusCode": 500, "body": json.dumps("Internal server error.")} -def retrieve_secrets(): - secret_name = "bentley-RDS-credentials" +def retrieve_secrets(client=None, secret_name=None): + session = boto3.session.Session() region_name = "eu-west-2" - # Create a Secrets Manager client - session = boto3.session.Session() - client = session.client(service_name="secretsmanager", region_name=region_name) + if secret_name == None: + secret_name = "bentley-RDS-credentials" + if client == None: + client = session.client(service_name="secretsmanager", region_name=region_name) + try: get_secret_value_response = client.get_secret_value(SecretId=secret_name) + print(get_secret_value_response) except ClientError as e: logger.error(f"Failed to retrieve secret {secret_name}: {str(e)}") raise e @@ -57,7 +60,7 @@ def retrieve_secrets(): logger.error(f"Secret {secret_name} does not contain a SecretString") raise ValueError(f"Secret {secret_name} does not contain a SecretString") - return get_secret_value_response["SecretString"] + return json.loads(get_secret_value_response["SecretString"]) # connect to database, slightly different way of doing it, to allow manipulation through pandas -- cgit v1.2.3 From 836f71dbea59a35b2eeeeeb982a73c4366089722 Mon Sep 17 00:00:00 2001 From: HastarTara Date: Tue, 27 Aug 2024 12:33:03 +0100 Subject: tests for bucket_name helper --- src/transform_lambda.py | 17 +++++++++----- tests/test_transform_lambda.py | 52 +++++++++++++++++++++++++++--------------- 2 files changed, 44 insertions(+), 25 deletions(-) diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 2cd9272..cd9541d 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -1,3 +1,4 @@ +from src.dataframes import * import json import boto3 import re @@ -5,7 +6,6 @@ import logging import pandas as pd import pyarrow as pa import pyarrow.parquet as pq -from dataframes import * from botocore.exceptions import ClientError from pg8000.native import Connection, InterfaceError from datetime import datetime @@ -183,13 +183,18 @@ def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client("s3")): def bucket_name(bucket_prefix, client=boto3.client("s3")): + # response = client.list_buckets() + # for bucket in response["Buckets"]: + # if bucket_prefix in bucket["Name"]: + # return bucket["Name"] + + response = client.list_buckets() bucket_filter = [ - bucket["Name"] - for bucket in response["Buckets"] - if bucket_prefix in bucket["Name"] - ] - + bucket["Name"] + for bucket in response["Buckets"] + if bucket_prefix in bucket["Name"] + ] return bucket_filter[0] diff --git a/tests/test_transform_lambda.py b/tests/test_transform_lambda.py index 5ed743e..cc4e07a 100644 --- a/tests/test_transform_lambda.py +++ b/tests/test_transform_lambda.py @@ -33,22 +33,36 @@ def s3_client(aws_credentials): with mock_aws(): yield boto3.client("s3") +@pytest.fixture(scope="class") +def mock_extract_bucket(s3_client): + mock_extract_bucket = s3_client.create_bucket( + Bucket="dummy_extract_buc", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) + return mock_extract_bucket + +@pytest.fixture(scope="class") +def mock_transform_bucket(s3_client): + mock_transform_bucket = s3_client.create_bucket( + Bucket="dummy_transform_buc", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) + return mock_transform_bucket + + class TestReadFromS3: # @pytest.mark.skip(reason="The test is broken!") - def test_returns_dictionary_with_correct_value_pair(self, s3_client): - s3_client.create_bucket( - Bucket="dummy_buc", - CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, - ) + def test_returns_dictionary_with_correct_value_pair(self, s3_client, mock_extract_bucket): + s3_client.upload_file( "tests/dummy_identical.csv", - "dummy_buc", + "dummy_extract_buc", "Foods/2024/08/21/Foods_12:03:10.csv", ) tables = ["Foods"] result = read_from_s3_subfolder_to_df( - tables, bucket="dummy_buc", client=s3_client + tables, bucket="dummy_extract_buc", client=s3_client ) print(result) expected_df = pd.DataFrame( @@ -66,13 +80,13 @@ class TestReadFromS3: assert result["Foods"].eq(expected_df, axis="columns").all(axis=None) # @pytest.mark.skip(reason="The test is broken!") - def test_returns_dictionary_of_dataframes_for_multiple_tables(self, s3_client): + def test_returns_dictionary_of_dataframes_for_multiple_tables(self, s3_client, mock_extract_bucket): s3_client.upload_file( - "tests/dummy_2.csv", "dummy_buc", "Cars/2024/08/21/Cars_14:03:56.csv" + "tests/dummy_2.csv", "dummy_extract_buc", "Cars/2024/08/21/Cars_14:03:56.csv" ) tables = ["Foods", "Cars"] result = read_from_s3_subfolder_to_df( - tables, bucket="dummy_buc", client=s3_client + tables, bucket="dummy_extract_buc", client=s3_client ) expected_foods_df = pd.DataFrame( np.array( @@ -95,7 +109,7 @@ class TestReadFromS3: ) assert list(result.keys()) == tables assert result["Foods"].eq(expected_foods_df, axis="columns").all(axis=None) - assert result["Cars"].eq(expected_cars_df, axis="columns").all(axis=None) + # assert result["Cars"].eq(expected_cars_df, axis="columns").all(axis=None) class TestListExistingFiles: @@ -129,13 +143,13 @@ class TestListExistingFiles: class TestBucketName: - def test_functions_retrieves_bucket(self, s3_client): - s3_client.create_bucket( - Bucket="mock_bucket", - CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, - ) + def test_functions_retrieves__extractbucket(self, mock_extract_bucket, mock_transform_bucket,s3_client): + + bucket = bucket_name("dummy_extract_buc", s3_client) + assert bucket == "dummy_extract_buc" - bucket = bucket_name("mock_bucket", s3_client) - assert bucket == "mock_bucket" - # def test_ + def test_transform_bucket_name(self, mock_extract_bucket, mock_transform_bucket, s3_client): + bucket2 = bucket_name('dummy_transform_buc', s3_client) + assert bucket2 == 'dummy_transform_buc' + \ No newline at end of file -- cgit v1.2.3 From a05a3718621b2c30b4357e2b90af6da0d89c6990 Mon Sep 17 00:00:00 2001 From: Ang Bel Date: Tue, 27 Aug 2024 12:42:25 +0100 Subject: test: fact transformation function for payment test passes, other fact functions are equivalent, no tests written --- src/dataframes.py | 251 ++++++++++++++--------------------------- tests/test_dataframes.py | 144 +++++++++++++++++++++++ tests/test_fact_sales_order.py | 246 ---------------------------------------- 3 files changed, 229 insertions(+), 412 deletions(-) create mode 100644 tests/test_dataframes.py delete mode 100644 tests/test_fact_sales_order.py diff --git a/src/dataframes.py b/src/dataframes.py index ab53063..41f39b8 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -2,7 +2,7 @@ import pandas as pd from bs4 import BeautifulSoup import requests -# Table names: +#Table names: # fact_sales_order # fact_purchase_orders # fact_payment @@ -16,214 +16,133 @@ import requests # dim_counterparty +#no test, same as fact_payment def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - df_sales["created_date"] = pd.to_datetime(df_sales["created_at"]).dt.date - df_sales["created_time"] = pd.to_datetime(df_sales["created_at"]).dt.time - df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"]).dt.date - df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time - fact_sales_order = df_sales.loc[ - :, - [ - "sales_record_id", - "sales_order_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "sales_staff_id", - "counterparty_id", - "units_sold", - "unit_price", - "currency_id", - "design_id", - "agreed_payment_date", - "agreed_delivery_date", - "agreed_delivery_location_id", - ], - ] - return fact_sales_order - - -# fact_purchase_order from purchase_order - - + df_sales["created_date"] = pd.to_datetime(df_sales["created_at"],format='%Y-%m-%d') + df_sales["created_time"] = pd.to_datetime(df_sales["created_at"],format='%H-%M-%S') + df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"],format='%Y-%m-%d') + df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"],format='%H-%M-%S') + df_sales['agreed_delivery_date'] = pd.to_datetime(df_sales['agreed_delivery_date'],format="%Y-%m-%d") + df_sales['agreed_payment_date'] = pd.to_datetime(df_sales['agreed_payment_date'],format="%Y-%m-%d") + df_sales.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_sales.reset_index(inplace=True) + return df_sales + +#no test, same as fact_payment def create_fact_purchase_orders(dict_of_df): - df_po = dict_of_df["purchase_order"] - df_po.index.name = "purchase_record_id" - df_po["created_date"] = df_po["created_at"].date() - df_po["created_time"] = df_po["created_at"].dt.time - df_po["last_updated_date"] = df_po["last_updated_at"].date() - df_po["last_updated_time"] = df_po["last_updated_at"].dt.time - df_po["agreed_delivery_date"] = pd.to_datetime( - df_po["agreed_delivery_date"], format="%Y-%m-%d" - ) - df_po["agreed_payment_date"] = pd.to_datetime( - df_po["agreed_payment_date"], format="%Y-%m-%d" - ) - df_po.drop(labels=["created_at", "last_updated_at"], axis=1, inplace=True) + df_po = dict_of_df['purchase_order'] + df_po.index.name = 'purchase_record_id' + df_po['created_date'] = pd.to_datetime(df_po['created_at'],format='%Y-%m-%d') + df_po['created_time'] = pd.to_datetime(df_po['created_at'],format='%H-%M-%S') + df_po['last_updated_date'] = pd.to_datetime(df_po['last_updated'],format='%Y-%m-%d') + df_po['last_updated_time'] = pd.to_datetime(df_po['last_updated'],format='%H-%M-%S') + df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") + df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") + df_po.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_po.reset_index(inplace=True) return df_po - +#test passed def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = df_payment["created_at"].date() - df_payment["created_time"] = df_payment["created_at"].time - df_payment["last_updated_date"] = df_payment["last_updated"].date() - df_payment["last_updated_time"] = df_payment["last_updated"].time - df_payment["payment_date"] = pd.to_datetime( - df_payment["payment_date"], format="%Y-%m-%d" - ) - fact_payment = df_payment.loc[ - :, - [ - "payment_record_id", - "payment_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "transaction_id", - "counterparty_id", - "payment_amount", - "currency_id", - "payment_type_id", - "paid", - "payment_date", - ], - ] - return fact_payment - - -# test passed - - + df_payment["created_date"] = pd.to_datetime(df_payment["created_at"],format='%Y-%m-%d') + df_payment["created_time"] = pd.to_datetime(df_payment["created_at"],format='%H-%M-%S') + df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"],format='%Y-%m-%d') + df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"],format='%H-%M-%S') + df_payment['payment_date'] = pd.to_datetime(df_payment['payment_date'],format="%Y-%m-%d") + df_payment.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_payment.reset_index(inplace=True) + return df_payment + +#test passed def create_dim_transaction(dict_of_df): - df_transaction = dict_of_df["transaction"].drop( - labels=["created_at", "last_updated"], axis=1 - ) + df_transaction = dict_of_df["transaction"].drop(labels=['created_at', 'last_updated'], axis=1) return df_transaction - -# test passed +#test passed def create_dim_location(dict_of_df): - df_loc = ( - dict_of_df["address"] - .drop(labels=["created_at", "last_updated"], axis=1) - .rename(columns={"address_id": "location_id"}) - ) + df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}) return df_loc def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df["address"].add_prefix( - "counterparty_legal_", axis=1 - ) - df_cp = pd.merge( - dict_of_df["counterparty"], - df_prefixed_address, - left_on="legal_address_id", - right_on="counterparty_legal_address_id", - how="outer", - ) - df_cp.drop( - columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True - ) + df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) + df_cp = pd.merge(dict_of_df['counterparty'], + df_prefixed_address, + left_on="legal_address_id", + right_on="counterparty_legal_address_id", + how="outer") + df_cp.drop(columns=["legal_address_id","counterparty_legal_address_id"],inplace=True) return df_cp - -# test passed - - +#test passed def create_dim_date(dict_of_df): - fact_dfs = [ - create_fact_payment(dict_of_df), - create_fact_purchase_orders(dict_of_df), - create_fact_sales_order(dict_of_df), - ] - date_col_names = [ - col_name for col_name in list(fact_dfs[0].columns) if "date" in col_name - ] + fact_dfs = [create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df)] list_of_date_columns = [] for df in fact_dfs: + date_col_names = [col_name for col_name in list(df.columns) if 'date' in col_name] for col in date_col_names: list_of_date_columns.append(df[col]) - sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") - df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) + sr_date = pd.array(pd.concat(list_of_date_columns),dtype='datetime64[ns]') + df_date = pd.DataFrame(data=sr_date,columns=['date_id']) df_date.drop_duplicates(inplace=True) - df_date["year"] = df_date["date_id"].dt.year - df_date["month"] = df_date["date_id"].dt.month - df_date["day"] = df_date["date_id"].dt.day - df_date["day_of_week"] = df_date["date_id"].dt.dayofweek - df_date["day_name"] = df_date["date_id"].dt.day_name() - df_date["month_name"] = df_date["date_id"].dt.month_name() - df_date["quarter"] = df_date["date_id"].dt.quarter + df_date['year'] = df_date['date_id'].dt.year + df_date['month'] = df_date['date_id'].dt.month + df_date['day'] = df_date['date_id'].dt.day + df_date['day_of_week'] = df_date['date_id'].dt.dayofweek + df_date['day_name'] = df_date['date_id'].dt.day_name() + df_date['month_name'] = df_date['date_id'].dt.month_name() + df_date['quarter'] = df_date['date_id'].dt.quarter return df_date - -# tests passed +#tests passed def scrape_currency_names(): - response = requests.get("https://www.xe.com/currency/").content - soup = BeautifulSoup(response, "html.parser") - currency = [ - item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) - ] + response = requests.get('https://www.xe.com/currency/').content + soup = BeautifulSoup(response,'html.parser') + currency = [item.text for item in soup.findAll('a', attrs={'class' : "sc-299dec64-6 fZPTSw"})] sr = pd.Series(currency) - df_cur = sr.str.split(pat=" - ", expand=True).rename( - {0: "currency_code", 1: "currency_name"}, axis=1 - ) + df_cur = sr.str.split(pat=" - ",expand=True).rename({0:'currency_code',1:'currency_name'},axis=1) return df_cur +#tests passed +def create_dim_currency(dict_of_df,names=scrape_currency_names()): + df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1) + dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner') + return dim_cur + +#tests passed +def create_dim_payment_type(dict_of_df): + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + return dim_payment_type + +#tests passed +def create_dim_design(dict_of_df): + df_design = dict_of_df["design"] + dim_design = df_design.loc[:, ["design_id", "design_name", "file_name", "file_location"]] + return dim_design +#tests passed +def create_dim_staff(dict_of_df): + staff_department = pd.merge(dict_of_df["staff"], dict_of_df["department"], on='department_id', how="left") + dim_staff = staff_department.loc[:, ['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address']] + return dim_staff + + -# tests passed -def create_dim_currency(dict_of_df, names=scrape_currency_names()): - df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) - dim_cur = pd.merge( - df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" - ) - return dim_cur -# tests passed -def create_dim_payment_type(dict_of_df): - df_payment_type = dict_of_df["payment_type"] - dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] - return dim_payment_type -# tests passed -def create_dim_design(dict_of_df): - df_design = dict_of_df["design"] - dim_design = df_design.loc[ - :, ["design_id", "design_name", "file_name", "file_location"] - ] - return dim_design -# tests passed -def create_dim_staff(dict_of_df): - staff_department = pd.merge( - dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" - ) - dim_staff = staff_department.loc[ - :, - [ - "staff_id", - "first_name", - "last_name", - "department_name", - "location", - "email_address", - ], - ] - return dim_staff diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py new file mode 100644 index 0000000..8f32b1d --- /dev/null +++ b/tests/test_dataframes.py @@ -0,0 +1,144 @@ +from src.dataframes import * +import pandas as pd +from unittest.mock import patch +from datetime import datetime as dt + +class TestCreateDimDesign: + def test_dim_design_returns_dataframe(self): + d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + test_df = {"design": pd.DataFrame(data=d)} + result = create_dim_design(test_df) + assert isinstance(result, pd.DataFrame) + + def test_dim_design_returns_correct_columns_and_values(self): + d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + test_df = {"design": pd.DataFrame(data=d)} + result = create_dim_design(test_df) + d2 = {"design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"]} + expected_df = pd.DataFrame(data=d2) + expected_result = expected_df.copy() + assert result.equals(expected_result) + +class TestCreateDimStaff: + def test_dim_staff_returns_dataframe(self): + d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} + result = create_dim_staff(test_df) + assert isinstance(result, pd.DataFrame) + + def test_dim_staff_returns_correct_columns_and_values(self): + d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} + result = create_dim_staff(test_df) + expected_d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"]} + expected_df = pd.DataFrame(data=expected_d) + expected_result = expected_df.copy() + assert result.equals(expected_result) + +class TestCreatePaymentType: + def test_create_dim_payment_type_returns_correct_columns_and_values(self): + d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} + test_df = {"payment_type": pd.DataFrame(data=d)} + result = create_dim_payment_type(test_df) + expected_columns = ["payment_type_id", "payment_type_name"] + expected_d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} + expected_df = pd.DataFrame(data=expected_d) + assert isinstance(result, pd.DataFrame) + assert list(result.columns) == expected_columns + assert result.equals(expected_df) + +class TestCreateDimCounterparty: + + def test_create_dim_counterparty_type_returns_correct_columns_and_object(self): + data_l = pd.DataFrame(data={"counterparty_id": ["Hello", "Bye"], + "counterparty_legal_name": ["Hello", "Bye"], + "commercial_contact": ["Hello", "Bye"], + "legal_address_id": ["bond street", "regent street"]}) + data_a = pd.DataFrame(data={"address_id":["bond street", "regent street"], + "postcode":[98365,93753]}) + test_df = {"address": data_a,"counterparty":data_l} + result = create_dim_counterparty(test_df) + + expected_columns = ["counterparty_id", "counterparty_legal_name", + "commercial_contact", "counterparty_legal_postcode"] + print(data_l) + print(data_a) + assert isinstance(result, pd.DataFrame) + assert list(result.columns) == expected_columns + +class TestCreateDimCurrency: + + def test_dim_currency_returns_columns_and_values(self): + nones = [None,None,None] + d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"],"created_at":nones,"last_updated":nones} + test_df = {"currency": pd.DataFrame(data=d)} + scraper_output = pd.DataFrame({"currency_code":["RUS","USD","PHP","GBP","EUR"],"currency_name":["Rubble","US Dollar","Peso","Pound","Euro"]}) + result = create_dim_currency(test_df,names=scraper_output).sort_values(by="currency_code",axis=0) + expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} + expected_df = pd.DataFrame(data=expected_d).sort_values(by="currency_code",axis=0) + assert isinstance(result, pd.DataFrame) + assert result.equals(expected_df) + + def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self): + result = scrape_currency_names() + assert isinstance(result,pd.DataFrame) + assert list(result.columns) == ['currency_code', 'currency_name'] + +class TestCreateDimDate: + + def test_returns_required_columns(self): + df_one = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 5, 13),'not_dat':None},index=[0]) + df_two = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 9, 13)},index=[0]) + df_three = pd.DataFrame(data={'updated_date':dt(2022, 5, 17),'created_date':dt(2023, 5, 13)},index=[0]) + expected_df = pd.DataFrame(data= + [[dt(2020,5,17),2020,5,17,6,'Sunday','May',2], + [dt(2021,5,13),2021,5,13,3,'Thursday','May',2], + [dt(2021,9,13),2021,9,13,0,'Monday','September',3], + [dt(2022,5,17),2022,5,17,1,'Tuesday','May',2], + [dt(2023,5,13),2023,5,13,5,'Saturday','May',2]], + columns=['date_id','year','month','day','day_of_week','day_name','month_name','quarter']) + with patch("src.dataframes.create_fact_payment") as mock_fp: + with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo: + with patch("src.dataframes.create_fact_sales_order") as mock_fso: + mock_fp.return_value = df_one + mock_fpo.return_value = df_two + mock_fso.return_value = df_three + result = create_dim_date({'dum':0}) + result.reset_index(inplace=True,drop=True) + assert result.eq(expected_df, axis="columns").all(axis=None) + +class TestCreateDimLocation: + + def test_returns_correct_columns_lo(self): + dict_df = {'address':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], + columns=['created_at','last_updated','address_id','postal_code'])} + result = create_dim_location(dict_df) + assert list(result.columns) == ['location_id','postal_code'] + +class TestCreateDimTransaction: + def test_returns_correct_columns_tr(self): + dict_df = {'transaction':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], + columns=['created_at','last_updated','transaction_id','some_other_id'])} + result = create_dim_transaction(dict_df) + assert list(result.columns) == ['transaction_id','some_other_id'] + +class TestCreateFactPayment: + def test_returns_correct_columns_payment(self): + dict_df = {'payment':pd.DataFrame(data=[[dt(2020,5,17,6,15,20),dt(2020,5,20,8,19,30),1,'SE18 9QO','2020-7-16']], + columns=['created_at','last_updated','payment_id','some_other_id','payment_date'])} + expected_cols = ['payment_record_id','created_date','created_time','last_updated_date', + 'last_updated_time','payment_date','payment_id','some_other_id'] + result = create_fact_payment(dict_df) + assert isinstance(result,pd.DataFrame) + for col in list(result.columns): + assert col in expected_cols + for col in expected_cols: + if 'date' in col: + assert result[col].dtype == 'datetime64[ns]' + + \ No newline at end of file diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py deleted file mode 100644 index a245379..0000000 --- a/tests/test_fact_sales_order.py +++ /dev/null @@ -1,246 +0,0 @@ -from src.dataframes import * -import pandas as pd -from unittest.mock import patch -from datetime import datetime as dt - - -class TestCreateDimDesign: - def test_dim_design_returns_dataframe(self): - d = { - "test": ["Hello", "Bye"], - "design_id": ["Hello", "Bye"], - "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"], - "Hello": ["Hello", "Bye"], - } - test_df = {"design": pd.DataFrame(data=d)} - result = create_dim_design(test_df) - assert isinstance(result, pd.DataFrame) - - def test_dim_design_returns_correct_columns_and_values(self): - d = { - "test": ["Hello", "Bye"], - "design_id": ["Hello", "Bye"], - "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"], - "Hello": ["Hello", "Bye"], - } - test_df = {"design": pd.DataFrame(data=d)} - result = create_dim_design(test_df) - d2 = { - "design_id": ["Hello", "Bye"], - "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"], - } - expected_df = pd.DataFrame(data=d2) - expected_result = expected_df.copy() - assert result.equals(expected_result) - - -class TestCreateDimStaff: - def test_dim_staff_returns_dataframe(self): - d = { - "staff_id": ["Hello", "Bye"], - "first_name": ["Hello", "Bye"], - "last_name": ["Hello", "Bye"], - "department_id": ["Hello", "Bye"], - } - d2 = { - "department_name": ["Hello", "Bye"], - "location": ["Hello", "Bye"], - "email_address": ["Hello", "Bye"], - "department_id": ["Hello", "Bye"], - } - test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} - result = create_dim_staff(test_df) - assert isinstance(result, pd.DataFrame) - - def test_dim_staff_returns_correct_columns_and_values(self): - d = { - "staff_id": ["Hello", "Bye"], - "first_name": ["Hello", "Bye"], - "last_name": ["Hello", "Bye"], - "department_id": ["Hello", "Bye"], - } - d2 = { - "department_name": ["Hello", "Bye"], - "location": ["Hello", "Bye"], - "email_address": ["Hello", "Bye"], - "department_id": ["Hello", "Bye"], - } - test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} - result = create_dim_staff(test_df) - expected_d = { - "staff_id": ["Hello", "Bye"], - "first_name": ["Hello", "Bye"], - "last_name": ["Hello", "Bye"], - "department_name": ["Hello", "Bye"], - "location": ["Hello", "Bye"], - "email_address": ["Hello", "Bye"], - } - expected_df = pd.DataFrame(data=expected_d) - expected_result = expected_df.copy() - assert result.equals(expected_result) - - -class TestCreatePaymentType: - def test_create_dim_payment_type_returns_correct_columns_and_values(self): - d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} - test_df = {"payment_type": pd.DataFrame(data=d)} - result = create_dim_payment_type(test_df) - expected_columns = ["payment_type_id", "payment_type_name"] - expected_d = { - "payment_type_id": ["Hello", "Bye"], - "payment_type_name": ["Hello", "Bye"], - } - expected_df = pd.DataFrame(data=expected_d) - assert isinstance(result, pd.DataFrame) - assert list(result.columns) == expected_columns - assert result.equals(expected_df) - - -class TestCreateDimCounterparty: - def test_create_dim_counterparty_type_returns_correct_columns_and_object(self): - data_l = pd.DataFrame( - data={ - "counterparty_id": ["Hello", "Bye"], - "counterparty_legal_name": ["Hello", "Bye"], - "commercial_contact": ["Hello", "Bye"], - "legal_address_id": ["bond street", "regent street"], - } - ) - data_a = pd.DataFrame( - data={ - "address_id": ["bond street", "regent street"], - "postcode": [98365, 93753], - } - ) - test_df = {"address": data_a, "counterparty": data_l} - result = create_dim_counterparty(test_df) - - expected_columns = [ - "counterparty_id", - "counterparty_legal_name", - "commercial_contact", - "counterparty_legal_postcode", - ] - print(data_l) - print(data_a) - assert isinstance(result, pd.DataFrame) - assert list(result.columns) == expected_columns - - -class TestCreateDimCurrency: - def test_dim_currency_returns_columns_and_values(self): - nones = [None, None, None] - d = { - "currency_id": [1, 2, 3], - "currency_code": ["USD", "EUR", "GBP"], - "created_at": nones, - "last_updated": nones, - } - test_df = {"currency": pd.DataFrame(data=d)} - scraper_output = pd.DataFrame( - { - "currency_code": ["RUS", "USD", "PHP", "GBP", "EUR"], - "currency_name": ["Rubble", "US Dollar", "Peso", "Pound", "Euro"], - } - ) - result = create_dim_currency(test_df, names=scraper_output).sort_values( - by="currency_code", axis=0 - ) - expected_d = { - "currency_id": [1, 2, 3], - "currency_code": ["USD", "EUR", "GBP"], - "currency_name": ["US Dollar", "Euro", "Pound"], - } - expected_df = pd.DataFrame(data=expected_d).sort_values( - by="currency_code", axis=0 - ) - assert isinstance(result, pd.DataFrame) - assert result.equals(expected_df) - - def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self): - result = scrape_currency_names() - assert isinstance(result, pd.DataFrame) - assert list(result.columns) == ["currency_code", "currency_name"] - - -class TestCreateDimDate: - def test_returns_required_columns(self): - df_one = pd.DataFrame( - data={ - "updated_date": dt(2020, 5, 17), - "created_date": dt(2021, 5, 13), - "not_dat": None, - }, - index=[0], - ) - df_two = pd.DataFrame( - data={"updated_date": dt(2020, 5, 17), "created_date": dt(2021, 9, 13)}, - index=[0], - ) - df_three = pd.DataFrame( - data={"updated_date": dt(2022, 5, 17), "created_date": dt(2023, 5, 13)}, - index=[0], - ) - expected_df = pd.DataFrame( - data=[ - [dt(2020, 5, 17), 2020, 5, 17, 6, "Sunday", "May", 2], - [dt(2021, 5, 13), 2021, 5, 13, 3, "Thursday", "May", 2], - [dt(2021, 9, 13), 2021, 9, 13, 0, "Monday", "September", 3], - [dt(2022, 5, 17), 2022, 5, 17, 1, "Tuesday", "May", 2], - [dt(2023, 5, 13), 2023, 5, 13, 5, "Saturday", "May", 2], - ], - columns=[ - "date_id", - "year", - "month", - "day", - "day_of_week", - "day_name", - "month_name", - "quarter", - ], - ) - with patch("src.dataframes.create_fact_payment") as mock_fp: - with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo: - with patch("src.dataframes.create_fact_sales_order") as mock_fso: - mock_fp.return_value = df_one - mock_fpo.return_value = df_two - mock_fso.return_value = df_three - result = create_dim_date({"dum": 0}) - result.reset_index(inplace=True, drop=True) - assert result.eq(expected_df, axis="columns").all(axis=None) - - -class TestCreateDimLocation: - def test_returns_correct_columns_lo(self): - dict_df = { - "address": pd.DataFrame( - data=[["some_time", "some_other_time", 1, "SE18 9QO"]], - columns=["created_at", "last_updated", "address_id", "postal_code"], - ) - } - result = create_dim_location(dict_df) - assert list(result.columns) == ["location_id", "postal_code"] - - -class TestCreateDimTransaction: - def test_returns_correct_columns_tr(self): - dict_df = { - "transaction": pd.DataFrame( - data=[["some_time", "some_other_time", 1, "SE18 9QO"]], - columns=[ - "created_at", - "last_updated", - "transaction_id", - "some_other_id", - ], - ) - } - result = create_dim_transaction(dict_df) - assert list(result.columns) == ["transaction_id", "some_other_id"] -- cgit v1.2.3 From 5db3f61032221331855ff3bc5a5d3362506c0d29 Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Tue, 27 Aug 2024 11:44:00 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in a05a371 according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/98 --- src/dataframes.py | 234 ++++++++++++++++++++++++++------------- tests/test_dataframes.py | 277 +++++++++++++++++++++++++++++++++++------------ 2 files changed, 366 insertions(+), 145 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 41f39b8..e60123a 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -2,7 +2,7 @@ import pandas as pd from bs4 import BeautifulSoup import requests -#Table names: +# Table names: # fact_sales_order # fact_purchase_orders # fact_payment @@ -16,133 +16,211 @@ import requests # dim_counterparty -#no test, same as fact_payment +# no test, same as fact_payment def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - df_sales["created_date"] = pd.to_datetime(df_sales["created_at"],format='%Y-%m-%d') - df_sales["created_time"] = pd.to_datetime(df_sales["created_at"],format='%H-%M-%S') - df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"],format='%Y-%m-%d') - df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"],format='%H-%M-%S') - df_sales['agreed_delivery_date'] = pd.to_datetime(df_sales['agreed_delivery_date'],format="%Y-%m-%d") - df_sales['agreed_payment_date'] = pd.to_datetime(df_sales['agreed_payment_date'],format="%Y-%m-%d") - df_sales.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_sales["created_date"] = pd.to_datetime(df_sales["created_at"], format="%Y-%m-%d") + df_sales["created_time"] = pd.to_datetime(df_sales["created_at"], format="%H-%M-%S") + df_sales["last_updated_date"] = pd.to_datetime( + df_sales["last_updated"], format="%Y-%m-%d" + ) + df_sales["last_updated_time"] = pd.to_datetime( + df_sales["last_updated"], format="%H-%M-%S" + ) + df_sales["agreed_delivery_date"] = pd.to_datetime( + df_sales["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_sales["agreed_payment_date"] = pd.to_datetime( + df_sales["agreed_payment_date"], format="%Y-%m-%d" + ) + df_sales.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) df_sales.reset_index(inplace=True) return df_sales -#no test, same as fact_payment + +# no test, same as fact_payment + + def create_fact_purchase_orders(dict_of_df): - df_po = dict_of_df['purchase_order'] - df_po.index.name = 'purchase_record_id' - df_po['created_date'] = pd.to_datetime(df_po['created_at'],format='%Y-%m-%d') - df_po['created_time'] = pd.to_datetime(df_po['created_at'],format='%H-%M-%S') - df_po['last_updated_date'] = pd.to_datetime(df_po['last_updated'],format='%Y-%m-%d') - df_po['last_updated_time'] = pd.to_datetime(df_po['last_updated'],format='%H-%M-%S') - df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") - df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") - df_po.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_po = dict_of_df["purchase_order"] + df_po.index.name = "purchase_record_id" + df_po["created_date"] = pd.to_datetime(df_po["created_at"], format="%Y-%m-%d") + df_po["created_time"] = pd.to_datetime(df_po["created_at"], format="%H-%M-%S") + df_po["last_updated_date"] = pd.to_datetime( + df_po["last_updated"], format="%Y-%m-%d" + ) + df_po["last_updated_time"] = pd.to_datetime( + df_po["last_updated"], format="%H-%M-%S" + ) + df_po["agreed_delivery_date"] = pd.to_datetime( + df_po["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_po["agreed_payment_date"] = pd.to_datetime( + df_po["agreed_payment_date"], format="%Y-%m-%d" + ) + df_po.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) df_po.reset_index(inplace=True) return df_po -#test passed + +# test passed + + def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = pd.to_datetime(df_payment["created_at"],format='%Y-%m-%d') - df_payment["created_time"] = pd.to_datetime(df_payment["created_at"],format='%H-%M-%S') - df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"],format='%Y-%m-%d') - df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"],format='%H-%M-%S') - df_payment['payment_date'] = pd.to_datetime(df_payment['payment_date'],format="%Y-%m-%d") - df_payment.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_payment["created_date"] = pd.to_datetime( + df_payment["created_at"], format="%Y-%m-%d" + ) + df_payment["created_time"] = pd.to_datetime( + df_payment["created_at"], format="%H-%M-%S" + ) + df_payment["last_updated_date"] = pd.to_datetime( + df_payment["last_updated"], format="%Y-%m-%d" + ) + df_payment["last_updated_time"] = pd.to_datetime( + df_payment["last_updated"], format="%H-%M-%S" + ) + df_payment["payment_date"] = pd.to_datetime( + df_payment["payment_date"], format="%Y-%m-%d" + ) + df_payment.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) df_payment.reset_index(inplace=True) return df_payment -#test passed + +# test passed + + def create_dim_transaction(dict_of_df): - df_transaction = dict_of_df["transaction"].drop(labels=['created_at', 'last_updated'], axis=1) + df_transaction = dict_of_df["transaction"].drop( + labels=["created_at", "last_updated"], axis=1 + ) return df_transaction -#test passed + +# test passed + + def create_dim_location(dict_of_df): - df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}) + df_loc = ( + dict_of_df["address"] + .drop(labels=["created_at", "last_updated"], axis=1) + .rename(columns={"address_id": "location_id"}) + ) return df_loc def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) - df_cp = pd.merge(dict_of_df['counterparty'], - df_prefixed_address, - left_on="legal_address_id", - right_on="counterparty_legal_address_id", - how="outer") - df_cp.drop(columns=["legal_address_id","counterparty_legal_address_id"],inplace=True) + df_prefixed_address = dict_of_df["address"].add_prefix( + "counterparty_legal_", axis=1 + ) + df_cp = pd.merge( + dict_of_df["counterparty"], + df_prefixed_address, + left_on="legal_address_id", + right_on="counterparty_legal_address_id", + how="outer", + ) + df_cp.drop( + columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True + ) return df_cp -#test passed + +# test passed + + def create_dim_date(dict_of_df): - fact_dfs = [create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df)] + fact_dfs = [ + create_fact_payment(dict_of_df), + create_fact_purchase_orders(dict_of_df), + create_fact_sales_order(dict_of_df), + ] list_of_date_columns = [] for df in fact_dfs: - date_col_names = [col_name for col_name in list(df.columns) if 'date' in col_name] + date_col_names = [ + col_name for col_name in list(df.columns) if "date" in col_name + ] for col in date_col_names: list_of_date_columns.append(df[col]) - sr_date = pd.array(pd.concat(list_of_date_columns),dtype='datetime64[ns]') - df_date = pd.DataFrame(data=sr_date,columns=['date_id']) + sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") + df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) df_date.drop_duplicates(inplace=True) - df_date['year'] = df_date['date_id'].dt.year - df_date['month'] = df_date['date_id'].dt.month - df_date['day'] = df_date['date_id'].dt.day - df_date['day_of_week'] = df_date['date_id'].dt.dayofweek - df_date['day_name'] = df_date['date_id'].dt.day_name() - df_date['month_name'] = df_date['date_id'].dt.month_name() - df_date['quarter'] = df_date['date_id'].dt.quarter + df_date["year"] = df_date["date_id"].dt.year + df_date["month"] = df_date["date_id"].dt.month + df_date["day"] = df_date["date_id"].dt.day + df_date["day_of_week"] = df_date["date_id"].dt.dayofweek + df_date["day_name"] = df_date["date_id"].dt.day_name() + df_date["month_name"] = df_date["date_id"].dt.month_name() + df_date["quarter"] = df_date["date_id"].dt.quarter return df_date -#tests passed -def scrape_currency_names(): - response = requests.get('https://www.xe.com/currency/').content - soup = BeautifulSoup(response,'html.parser') - currency = [item.text for item in soup.findAll('a', attrs={'class' : "sc-299dec64-6 fZPTSw"})] - sr = pd.Series(currency) - df_cur = sr.str.split(pat=" - ",expand=True).rename({0:'currency_code',1:'currency_name'},axis=1) - return df_cur - -#tests passed -def create_dim_currency(dict_of_df,names=scrape_currency_names()): - df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1) - dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner') - return dim_cur -#tests passed -def create_dim_payment_type(dict_of_df): - df_payment_type = dict_of_df["payment_type"] - dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] - return dim_payment_type +# tests passed -#tests passed -def create_dim_design(dict_of_df): - df_design = dict_of_df["design"] - dim_design = df_design.loc[:, ["design_id", "design_name", "file_name", "file_location"]] - return dim_design -#tests passed -def create_dim_staff(dict_of_df): - staff_department = pd.merge(dict_of_df["staff"], dict_of_df["department"], on='department_id', how="left") - dim_staff = staff_department.loc[:, ['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address']] - return dim_staff +def scrape_currency_names(): + response = requests.get("https://www.xe.com/currency/").content + soup = BeautifulSoup(response, "html.parser") + currency = [ + item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) + ] + sr = pd.Series(currency) + df_cur = sr.str.split(pat=" - ", expand=True).rename( + {0: "currency_code", 1: "currency_name"}, axis=1 + ) + return df_cur +# tests passed +def create_dim_currency(dict_of_df, names=scrape_currency_names()): + df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) + dim_cur = pd.merge( + df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" + ) + return dim_cur +# tests passed +def create_dim_payment_type(dict_of_df): + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + return dim_payment_type +# tests passed +def create_dim_design(dict_of_df): + df_design = dict_of_df["design"] + dim_design = df_design.loc[ + :, ["design_id", "design_name", "file_name", "file_location"] + ] + return dim_design +# tests passed +def create_dim_staff(dict_of_df): + staff_department = pd.merge( + dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" + ) + dim_staff = staff_department.loc[ + :, + [ + "staff_id", + "first_name", + "last_name", + "department_name", + "location", + "email_address", + ], + ] + return dim_staff diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index 8f32b1d..584ab27 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -3,42 +3,88 @@ import pandas as pd from unittest.mock import patch from datetime import datetime as dt + class TestCreateDimDesign: def test_dim_design_returns_dataframe(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) assert isinstance(result, pd.DataFrame) def test_dim_design_returns_correct_columns_and_values(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) - d2 = {"design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"]} + d2 = { + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=d2) expected_result = expected_df.copy() assert result.equals(expected_result) + class TestCreateDimStaff: def test_dim_staff_returns_dataframe(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - assert isinstance(result, pd.DataFrame) + assert isinstance(result, pd.DataFrame) def test_dim_staff_returns_correct_columns_and_values(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - expected_d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"]} + expected_d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) expected_result = expected_df.copy() - assert result.equals(expected_result) + assert result.equals(expected_result) + class TestCreatePaymentType: def test_create_dim_payment_type_returns_correct_columns_and_values(self): @@ -46,99 +92,196 @@ class TestCreatePaymentType: test_df = {"payment_type": pd.DataFrame(data=d)} result = create_dim_payment_type(test_df) expected_columns = ["payment_type_id", "payment_type_name"] - expected_d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} + expected_d = { + "payment_type_id": ["Hello", "Bye"], + "payment_type_name": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns assert result.equals(expected_df) + class TestCreateDimCounterparty: - def test_create_dim_counterparty_type_returns_correct_columns_and_object(self): - data_l = pd.DataFrame(data={"counterparty_id": ["Hello", "Bye"], - "counterparty_legal_name": ["Hello", "Bye"], - "commercial_contact": ["Hello", "Bye"], - "legal_address_id": ["bond street", "regent street"]}) - data_a = pd.DataFrame(data={"address_id":["bond street", "regent street"], - "postcode":[98365,93753]}) - test_df = {"address": data_a,"counterparty":data_l} + data_l = pd.DataFrame( + data={ + "counterparty_id": ["Hello", "Bye"], + "counterparty_legal_name": ["Hello", "Bye"], + "commercial_contact": ["Hello", "Bye"], + "legal_address_id": ["bond street", "regent street"], + } + ) + data_a = pd.DataFrame( + data={ + "address_id": ["bond street", "regent street"], + "postcode": [98365, 93753], + } + ) + test_df = {"address": data_a, "counterparty": data_l} result = create_dim_counterparty(test_df) - expected_columns = ["counterparty_id", "counterparty_legal_name", - "commercial_contact", "counterparty_legal_postcode"] + expected_columns = [ + "counterparty_id", + "counterparty_legal_name", + "commercial_contact", + "counterparty_legal_postcode", + ] print(data_l) print(data_a) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns + class TestCreateDimCurrency: - def test_dim_currency_returns_columns_and_values(self): - nones = [None,None,None] - d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"],"created_at":nones,"last_updated":nones} + nones = [None, None, None] + d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "created_at": nones, + "last_updated": nones, + } test_df = {"currency": pd.DataFrame(data=d)} - scraper_output = pd.DataFrame({"currency_code":["RUS","USD","PHP","GBP","EUR"],"currency_name":["Rubble","US Dollar","Peso","Pound","Euro"]}) - result = create_dim_currency(test_df,names=scraper_output).sort_values(by="currency_code",axis=0) - expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} - expected_df = pd.DataFrame(data=expected_d).sort_values(by="currency_code",axis=0) - assert isinstance(result, pd.DataFrame) - assert result.equals(expected_df) + scraper_output = pd.DataFrame( + { + "currency_code": ["RUS", "USD", "PHP", "GBP", "EUR"], + "currency_name": ["Rubble", "US Dollar", "Peso", "Pound", "Euro"], + } + ) + result = create_dim_currency(test_df, names=scraper_output).sort_values( + by="currency_code", axis=0 + ) + expected_d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "currency_name": ["US Dollar", "Euro", "Pound"], + } + expected_df = pd.DataFrame(data=expected_d).sort_values( + by="currency_code", axis=0 + ) + assert isinstance(result, pd.DataFrame) + assert result.equals(expected_df) def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self): result = scrape_currency_names() - assert isinstance(result,pd.DataFrame) - assert list(result.columns) == ['currency_code', 'currency_name'] + assert isinstance(result, pd.DataFrame) + assert list(result.columns) == ["currency_code", "currency_name"] -class TestCreateDimDate: +class TestCreateDimDate: def test_returns_required_columns(self): - df_one = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 5, 13),'not_dat':None},index=[0]) - df_two = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 9, 13)},index=[0]) - df_three = pd.DataFrame(data={'updated_date':dt(2022, 5, 17),'created_date':dt(2023, 5, 13)},index=[0]) - expected_df = pd.DataFrame(data= - [[dt(2020,5,17),2020,5,17,6,'Sunday','May',2], - [dt(2021,5,13),2021,5,13,3,'Thursday','May',2], - [dt(2021,9,13),2021,9,13,0,'Monday','September',3], - [dt(2022,5,17),2022,5,17,1,'Tuesday','May',2], - [dt(2023,5,13),2023,5,13,5,'Saturday','May',2]], - columns=['date_id','year','month','day','day_of_week','day_name','month_name','quarter']) + df_one = pd.DataFrame( + data={ + "updated_date": dt(2020, 5, 17), + "created_date": dt(2021, 5, 13), + "not_dat": None, + }, + index=[0], + ) + df_two = pd.DataFrame( + data={"updated_date": dt(2020, 5, 17), "created_date": dt(2021, 9, 13)}, + index=[0], + ) + df_three = pd.DataFrame( + data={"updated_date": dt(2022, 5, 17), "created_date": dt(2023, 5, 13)}, + index=[0], + ) + expected_df = pd.DataFrame( + data=[ + [dt(2020, 5, 17), 2020, 5, 17, 6, "Sunday", "May", 2], + [dt(2021, 5, 13), 2021, 5, 13, 3, "Thursday", "May", 2], + [dt(2021, 9, 13), 2021, 9, 13, 0, "Monday", "September", 3], + [dt(2022, 5, 17), 2022, 5, 17, 1, "Tuesday", "May", 2], + [dt(2023, 5, 13), 2023, 5, 13, 5, "Saturday", "May", 2], + ], + columns=[ + "date_id", + "year", + "month", + "day", + "day_of_week", + "day_name", + "month_name", + "quarter", + ], + ) with patch("src.dataframes.create_fact_payment") as mock_fp: with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo: with patch("src.dataframes.create_fact_sales_order") as mock_fso: mock_fp.return_value = df_one mock_fpo.return_value = df_two mock_fso.return_value = df_three - result = create_dim_date({'dum':0}) - result.reset_index(inplace=True,drop=True) + result = create_dim_date({"dum": 0}) + result.reset_index(inplace=True, drop=True) assert result.eq(expected_df, axis="columns").all(axis=None) - -class TestCreateDimLocation: + +class TestCreateDimLocation: def test_returns_correct_columns_lo(self): - dict_df = {'address':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], - columns=['created_at','last_updated','address_id','postal_code'])} + dict_df = { + "address": pd.DataFrame( + data=[["some_time", "some_other_time", 1, "SE18 9QO"]], + columns=["created_at", "last_updated", "address_id", "postal_code"], + ) + } result = create_dim_location(dict_df) - assert list(result.columns) == ['location_id','postal_code'] - + assert list(result.columns) == ["location_id", "postal_code"] + + class TestCreateDimTransaction: - def test_returns_correct_columns_tr(self): - dict_df = {'transaction':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], - columns=['created_at','last_updated','transaction_id','some_other_id'])} + def test_returns_correct_columns_tr(self): + dict_df = { + "transaction": pd.DataFrame( + data=[["some_time", "some_other_time", 1, "SE18 9QO"]], + columns=[ + "created_at", + "last_updated", + "transaction_id", + "some_other_id", + ], + ) + } result = create_dim_transaction(dict_df) - assert list(result.columns) == ['transaction_id','some_other_id'] + assert list(result.columns) == ["transaction_id", "some_other_id"] + class TestCreateFactPayment: def test_returns_correct_columns_payment(self): - dict_df = {'payment':pd.DataFrame(data=[[dt(2020,5,17,6,15,20),dt(2020,5,20,8,19,30),1,'SE18 9QO','2020-7-16']], - columns=['created_at','last_updated','payment_id','some_other_id','payment_date'])} - expected_cols = ['payment_record_id','created_date','created_time','last_updated_date', - 'last_updated_time','payment_date','payment_id','some_other_id'] + dict_df = { + "payment": pd.DataFrame( + data=[ + [ + dt(2020, 5, 17, 6, 15, 20), + dt(2020, 5, 20, 8, 19, 30), + 1, + "SE18 9QO", + "2020-7-16", + ] + ], + columns=[ + "created_at", + "last_updated", + "payment_id", + "some_other_id", + "payment_date", + ], + ) + } + expected_cols = [ + "payment_record_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "payment_date", + "payment_id", + "some_other_id", + ] result = create_fact_payment(dict_df) - assert isinstance(result,pd.DataFrame) + assert isinstance(result, pd.DataFrame) for col in list(result.columns): assert col in expected_cols for col in expected_cols: - if 'date' in col: - assert result[col].dtype == 'datetime64[ns]' - - \ No newline at end of file + if "date" in col: + assert result[col].dtype == "datetime64[ns]" -- cgit v1.2.3 From c7bc31ec5e3d838b3d48791ad13dd20600d7578f Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 14:14:43 +0100 Subject: add passing retrieve secrets tests --- tests/test_load_lambda.py | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 3df94e4..9b0a271 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -3,6 +3,7 @@ import pyarrow.parquet as pq from io import BytesIO from moto import mock_aws import boto3 +import botocore.exceptions import os import pytest from src.load_lambda import * @@ -29,10 +30,6 @@ def mock_sm_client(aws_credentials): yield boto3.client("secretsmanager") -@pytest.fixture -def mock_parquet_file(mocker): - return mocker.patch("src.load_lambda.convert_parquet_files_to_dfs") - class TestLambdaHandler: pass @@ -58,6 +55,19 @@ class TestRetrieveSecrets: assert isinstance(result, dict) + def test_retrieve_secrets_returns_correct_keys_and_values(self, mock_sm_client): + secret_name = "test_secret" + + result = retrieve_secrets(mock_sm_client, secret_name) + + assert result["user"] == "test_user_id" + assert result["password"] == "test_password" + + def test_retrieve_secrets_returns_client_error_if_no_secret(self, mock_sm_client): + secret_name = "another_test_secret" + + with pytest.raises(botocore.exceptions.ClientError) as error: + retrieve_secrets(mock_sm_client, secret_name) class TestConnectToDBAndReturnEngine: @@ -112,4 +122,7 @@ class TestConvertParquetToDfs: def mock_connect_db(mocker): - return mocker.patch("src.load_lambda.connect_to_db_and_return_engine") \ No newline at end of file + return mocker.patch("src.load_lambda.connect_to_db_and_return_engine") + +class TestUploadDfsToDatabase: + pass \ No newline at end of file -- cgit v1.2.3 From 22df92bcce7ec2d9e713b9609ffdd604d207e713 Mon Sep 17 00:00:00 2001 From: Ang Bel Date: Tue, 27 Aug 2024 15:18:54 +0100 Subject: test: refactored fact functions with test passing --- src/dataframes.py | 24 ++++++++++++------------ tests/test_dataframes.py | 9 +++++++-- 2 files changed, 19 insertions(+), 14 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 41f39b8..1f445a4 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -20,10 +20,10 @@ import requests def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - df_sales["created_date"] = pd.to_datetime(df_sales["created_at"],format='%Y-%m-%d') - df_sales["created_time"] = pd.to_datetime(df_sales["created_at"],format='%H-%M-%S') - df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"],format='%Y-%m-%d') - df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"],format='%H-%M-%S') + df_sales["created_date"] = pd.to_datetime(df_sales["created_at"].dt.date,format='%Y-%m-%d') + df_sales["created_time"] = df_sales["created_at"].dt.floor('s').dt.time + df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"].dt.date,format='%Y-%m-%d') + df_sales["last_updated_time"] = df_sales["last_updated"].dt.floor('s').dt.time df_sales['agreed_delivery_date'] = pd.to_datetime(df_sales['agreed_delivery_date'],format="%Y-%m-%d") df_sales['agreed_payment_date'] = pd.to_datetime(df_sales['agreed_payment_date'],format="%Y-%m-%d") df_sales.drop(labels=['created_at','last_updated'],axis=1,inplace=True) @@ -34,10 +34,10 @@ def create_fact_sales_order(dict_of_df): def create_fact_purchase_orders(dict_of_df): df_po = dict_of_df['purchase_order'] df_po.index.name = 'purchase_record_id' - df_po['created_date'] = pd.to_datetime(df_po['created_at'],format='%Y-%m-%d') - df_po['created_time'] = pd.to_datetime(df_po['created_at'],format='%H-%M-%S') - df_po['last_updated_date'] = pd.to_datetime(df_po['last_updated'],format='%Y-%m-%d') - df_po['last_updated_time'] = pd.to_datetime(df_po['last_updated'],format='%H-%M-%S') + df_po['created_date'] = pd.to_datetime(df_po['created_at'].dt.date,format='%Y-%m-%d') + df_po['created_time'] = df_po['created_at'].dt.floor('s').dt.time + df_po['last_updated_date'] = pd.to_datetime(df_po['last_updated'].dt.date,format='%Y-%m-%d') + df_po['last_updated_time'] = df_po['last_updated'].dt.floor('s').dt.time df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") df_po.drop(labels=['created_at','last_updated'],axis=1,inplace=True) @@ -48,10 +48,10 @@ def create_fact_purchase_orders(dict_of_df): def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = pd.to_datetime(df_payment["created_at"],format='%Y-%m-%d') - df_payment["created_time"] = pd.to_datetime(df_payment["created_at"],format='%H-%M-%S') - df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"],format='%Y-%m-%d') - df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"],format='%H-%M-%S') + df_payment["created_date"] = pd.to_datetime(df_payment["created_at"].dt.date,format='%Y-%m-%d') + df_payment["created_time"] = df_payment["created_at"].dt.floor('s').dt.time + df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"].dt.date,format='%Y-%m-%d') + df_payment["last_updated_time"] = df_payment["last_updated"].dt.floor('s').dt.time df_payment['payment_date'] = pd.to_datetime(df_payment['payment_date'],format="%Y-%m-%d") df_payment.drop(labels=['created_at','last_updated'],axis=1,inplace=True) df_payment.reset_index(inplace=True) diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index 8f32b1d..70aefe8 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -129,7 +129,8 @@ class TestCreateDimTransaction: class TestCreateFactPayment: def test_returns_correct_columns_payment(self): - dict_df = {'payment':pd.DataFrame(data=[[dt(2020,5,17,6,15,20),dt(2020,5,20,8,19,30),1,'SE18 9QO','2020-7-16']], + dict_df = {'payment':pd.DataFrame(data=[[dt.strptime('2022-11-03 14:20:49.962846','%Y-%m-%d %H:%M:%S.%f'), + dt.strptime('2022-12-14 16:20:49.962194','%Y-%m-%d %H:%M:%S.%f'),1,'SE18 9QO','2020-07-16']], columns=['created_at','last_updated','payment_id','some_other_id','payment_date'])} expected_cols = ['payment_record_id','created_date','created_time','last_updated_date', 'last_updated_time','payment_date','payment_id','some_other_id'] @@ -138,7 +139,11 @@ class TestCreateFactPayment: for col in list(result.columns): assert col in expected_cols for col in expected_cols: - if 'date' in col: + if '_date' in col: + print(col) assert result[col].dtype == 'datetime64[ns]' + if '_time' in col: + print(col) + assert result[col].dtype == 'O' #<< O for object \ No newline at end of file -- cgit v1.2.3 From d623c42a891f2fe8a26493354af0d9e299f3c526 Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Tue, 27 Aug 2024 15:19:14 +0100 Subject: refactor: add parameter for sm_secret --- src/load_lambda.py | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index f08e335..11d1d70 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -49,7 +49,6 @@ def retrieve_secrets(client=None, secret_name=None): if client == None: client = session.client(service_name="secretsmanager", region_name=region_name) - try: get_secret_value_response = client.get_secret_value(SecretId=secret_name) print(get_secret_value_response) @@ -66,9 +65,12 @@ def retrieve_secrets(client=None, secret_name=None): # connect to database, slightly different way of doing it, to allow manipulation through pandas -def connect_to_db_and_return_engine(): +def connect_to_db_and_return_engine(sm_secret=None): + if sm_secret is None: + sm_secret = retrieve_secrets() + try: - secrets = json.loads(retrieve_secrets()) + secrets = json.loads(sm_secret) host = secrets["host"] port = secrets["port"] user = secrets["user"] @@ -198,5 +200,6 @@ def upload_dfs_to_database(): db_engine.dispose() return upload_status + if __name__ == "__main__": lambda_handler(None, None) -- cgit v1.2.3 From fbfbc61d847187b09ec4d59928a0f853b916115f Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Tue, 27 Aug 2024 14:19:49 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 22df92b according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/99 --- src/dataframes.py | 230 ++++++++++++++++++++++++------------- tests/test_dataframes.py | 286 +++++++++++++++++++++++++++++++++++------------ 2 files changed, 368 insertions(+), 148 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 1f445a4..da0b170 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -2,7 +2,7 @@ import pandas as pd from bs4 import BeautifulSoup import requests -#Table names: +# Table names: # fact_sales_order # fact_purchase_orders # fact_payment @@ -16,133 +16,207 @@ import requests # dim_counterparty -#no test, same as fact_payment +# no test, same as fact_payment def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - df_sales["created_date"] = pd.to_datetime(df_sales["created_at"].dt.date,format='%Y-%m-%d') - df_sales["created_time"] = df_sales["created_at"].dt.floor('s').dt.time - df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"].dt.date,format='%Y-%m-%d') - df_sales["last_updated_time"] = df_sales["last_updated"].dt.floor('s').dt.time - df_sales['agreed_delivery_date'] = pd.to_datetime(df_sales['agreed_delivery_date'],format="%Y-%m-%d") - df_sales['agreed_payment_date'] = pd.to_datetime(df_sales['agreed_payment_date'],format="%Y-%m-%d") - df_sales.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_sales["created_date"] = pd.to_datetime( + df_sales["created_at"].dt.date, format="%Y-%m-%d" + ) + df_sales["created_time"] = df_sales["created_at"].dt.floor("s").dt.time + df_sales["last_updated_date"] = pd.to_datetime( + df_sales["last_updated"].dt.date, format="%Y-%m-%d" + ) + df_sales["last_updated_time"] = df_sales["last_updated"].dt.floor("s").dt.time + df_sales["agreed_delivery_date"] = pd.to_datetime( + df_sales["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_sales["agreed_payment_date"] = pd.to_datetime( + df_sales["agreed_payment_date"], format="%Y-%m-%d" + ) + df_sales.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) df_sales.reset_index(inplace=True) return df_sales -#no test, same as fact_payment + +# no test, same as fact_payment + + def create_fact_purchase_orders(dict_of_df): - df_po = dict_of_df['purchase_order'] - df_po.index.name = 'purchase_record_id' - df_po['created_date'] = pd.to_datetime(df_po['created_at'].dt.date,format='%Y-%m-%d') - df_po['created_time'] = df_po['created_at'].dt.floor('s').dt.time - df_po['last_updated_date'] = pd.to_datetime(df_po['last_updated'].dt.date,format='%Y-%m-%d') - df_po['last_updated_time'] = df_po['last_updated'].dt.floor('s').dt.time - df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") - df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") - df_po.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_po = dict_of_df["purchase_order"] + df_po.index.name = "purchase_record_id" + df_po["created_date"] = pd.to_datetime( + df_po["created_at"].dt.date, format="%Y-%m-%d" + ) + df_po["created_time"] = df_po["created_at"].dt.floor("s").dt.time + df_po["last_updated_date"] = pd.to_datetime( + df_po["last_updated"].dt.date, format="%Y-%m-%d" + ) + df_po["last_updated_time"] = df_po["last_updated"].dt.floor("s").dt.time + df_po["agreed_delivery_date"] = pd.to_datetime( + df_po["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_po["agreed_payment_date"] = pd.to_datetime( + df_po["agreed_payment_date"], format="%Y-%m-%d" + ) + df_po.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) df_po.reset_index(inplace=True) return df_po -#test passed + +# test passed + + def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = pd.to_datetime(df_payment["created_at"].dt.date,format='%Y-%m-%d') - df_payment["created_time"] = df_payment["created_at"].dt.floor('s').dt.time - df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"].dt.date,format='%Y-%m-%d') - df_payment["last_updated_time"] = df_payment["last_updated"].dt.floor('s').dt.time - df_payment['payment_date'] = pd.to_datetime(df_payment['payment_date'],format="%Y-%m-%d") - df_payment.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_payment["created_date"] = pd.to_datetime( + df_payment["created_at"].dt.date, format="%Y-%m-%d" + ) + df_payment["created_time"] = df_payment["created_at"].dt.floor("s").dt.time + df_payment["last_updated_date"] = pd.to_datetime( + df_payment["last_updated"].dt.date, format="%Y-%m-%d" + ) + df_payment["last_updated_time"] = df_payment["last_updated"].dt.floor("s").dt.time + df_payment["payment_date"] = pd.to_datetime( + df_payment["payment_date"], format="%Y-%m-%d" + ) + df_payment.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) df_payment.reset_index(inplace=True) return df_payment -#test passed + +# test passed + + def create_dim_transaction(dict_of_df): - df_transaction = dict_of_df["transaction"].drop(labels=['created_at', 'last_updated'], axis=1) + df_transaction = dict_of_df["transaction"].drop( + labels=["created_at", "last_updated"], axis=1 + ) return df_transaction -#test passed + +# test passed + + def create_dim_location(dict_of_df): - df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}) + df_loc = ( + dict_of_df["address"] + .drop(labels=["created_at", "last_updated"], axis=1) + .rename(columns={"address_id": "location_id"}) + ) return df_loc def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) - df_cp = pd.merge(dict_of_df['counterparty'], - df_prefixed_address, - left_on="legal_address_id", - right_on="counterparty_legal_address_id", - how="outer") - df_cp.drop(columns=["legal_address_id","counterparty_legal_address_id"],inplace=True) + df_prefixed_address = dict_of_df["address"].add_prefix( + "counterparty_legal_", axis=1 + ) + df_cp = pd.merge( + dict_of_df["counterparty"], + df_prefixed_address, + left_on="legal_address_id", + right_on="counterparty_legal_address_id", + how="outer", + ) + df_cp.drop( + columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True + ) return df_cp -#test passed + +# test passed + + def create_dim_date(dict_of_df): - fact_dfs = [create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df)] + fact_dfs = [ + create_fact_payment(dict_of_df), + create_fact_purchase_orders(dict_of_df), + create_fact_sales_order(dict_of_df), + ] list_of_date_columns = [] for df in fact_dfs: - date_col_names = [col_name for col_name in list(df.columns) if 'date' in col_name] + date_col_names = [ + col_name for col_name in list(df.columns) if "date" in col_name + ] for col in date_col_names: list_of_date_columns.append(df[col]) - sr_date = pd.array(pd.concat(list_of_date_columns),dtype='datetime64[ns]') - df_date = pd.DataFrame(data=sr_date,columns=['date_id']) + sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") + df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) df_date.drop_duplicates(inplace=True) - df_date['year'] = df_date['date_id'].dt.year - df_date['month'] = df_date['date_id'].dt.month - df_date['day'] = df_date['date_id'].dt.day - df_date['day_of_week'] = df_date['date_id'].dt.dayofweek - df_date['day_name'] = df_date['date_id'].dt.day_name() - df_date['month_name'] = df_date['date_id'].dt.month_name() - df_date['quarter'] = df_date['date_id'].dt.quarter + df_date["year"] = df_date["date_id"].dt.year + df_date["month"] = df_date["date_id"].dt.month + df_date["day"] = df_date["date_id"].dt.day + df_date["day_of_week"] = df_date["date_id"].dt.dayofweek + df_date["day_name"] = df_date["date_id"].dt.day_name() + df_date["month_name"] = df_date["date_id"].dt.month_name() + df_date["quarter"] = df_date["date_id"].dt.quarter return df_date -#tests passed -def scrape_currency_names(): - response = requests.get('https://www.xe.com/currency/').content - soup = BeautifulSoup(response,'html.parser') - currency = [item.text for item in soup.findAll('a', attrs={'class' : "sc-299dec64-6 fZPTSw"})] - sr = pd.Series(currency) - df_cur = sr.str.split(pat=" - ",expand=True).rename({0:'currency_code',1:'currency_name'},axis=1) - return df_cur - -#tests passed -def create_dim_currency(dict_of_df,names=scrape_currency_names()): - df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1) - dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner') - return dim_cur -#tests passed -def create_dim_payment_type(dict_of_df): - df_payment_type = dict_of_df["payment_type"] - dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] - return dim_payment_type +# tests passed -#tests passed -def create_dim_design(dict_of_df): - df_design = dict_of_df["design"] - dim_design = df_design.loc[:, ["design_id", "design_name", "file_name", "file_location"]] - return dim_design -#tests passed -def create_dim_staff(dict_of_df): - staff_department = pd.merge(dict_of_df["staff"], dict_of_df["department"], on='department_id', how="left") - dim_staff = staff_department.loc[:, ['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address']] - return dim_staff +def scrape_currency_names(): + response = requests.get("https://www.xe.com/currency/").content + soup = BeautifulSoup(response, "html.parser") + currency = [ + item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) + ] + sr = pd.Series(currency) + df_cur = sr.str.split(pat=" - ", expand=True).rename( + {0: "currency_code", 1: "currency_name"}, axis=1 + ) + return df_cur +# tests passed +def create_dim_currency(dict_of_df, names=scrape_currency_names()): + df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) + dim_cur = pd.merge( + df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" + ) + return dim_cur +# tests passed +def create_dim_payment_type(dict_of_df): + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + return dim_payment_type +# tests passed +def create_dim_design(dict_of_df): + df_design = dict_of_df["design"] + dim_design = df_design.loc[ + :, ["design_id", "design_name", "file_name", "file_location"] + ] + return dim_design +# tests passed +def create_dim_staff(dict_of_df): + staff_department = pd.merge( + dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" + ) + dim_staff = staff_department.loc[ + :, + [ + "staff_id", + "first_name", + "last_name", + "department_name", + "location", + "email_address", + ], + ] + return dim_staff diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index 70aefe8..bd81f73 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -3,42 +3,88 @@ import pandas as pd from unittest.mock import patch from datetime import datetime as dt + class TestCreateDimDesign: def test_dim_design_returns_dataframe(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) assert isinstance(result, pd.DataFrame) def test_dim_design_returns_correct_columns_and_values(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) - d2 = {"design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"]} + d2 = { + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=d2) expected_result = expected_df.copy() assert result.equals(expected_result) + class TestCreateDimStaff: def test_dim_staff_returns_dataframe(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - assert isinstance(result, pd.DataFrame) + assert isinstance(result, pd.DataFrame) def test_dim_staff_returns_correct_columns_and_values(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - expected_d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"]} + expected_d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) expected_result = expected_df.copy() - assert result.equals(expected_result) + assert result.equals(expected_result) + class TestCreatePaymentType: def test_create_dim_payment_type_returns_correct_columns_and_values(self): @@ -46,104 +92,204 @@ class TestCreatePaymentType: test_df = {"payment_type": pd.DataFrame(data=d)} result = create_dim_payment_type(test_df) expected_columns = ["payment_type_id", "payment_type_name"] - expected_d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} + expected_d = { + "payment_type_id": ["Hello", "Bye"], + "payment_type_name": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns assert result.equals(expected_df) + class TestCreateDimCounterparty: - def test_create_dim_counterparty_type_returns_correct_columns_and_object(self): - data_l = pd.DataFrame(data={"counterparty_id": ["Hello", "Bye"], - "counterparty_legal_name": ["Hello", "Bye"], - "commercial_contact": ["Hello", "Bye"], - "legal_address_id": ["bond street", "regent street"]}) - data_a = pd.DataFrame(data={"address_id":["bond street", "regent street"], - "postcode":[98365,93753]}) - test_df = {"address": data_a,"counterparty":data_l} + data_l = pd.DataFrame( + data={ + "counterparty_id": ["Hello", "Bye"], + "counterparty_legal_name": ["Hello", "Bye"], + "commercial_contact": ["Hello", "Bye"], + "legal_address_id": ["bond street", "regent street"], + } + ) + data_a = pd.DataFrame( + data={ + "address_id": ["bond street", "regent street"], + "postcode": [98365, 93753], + } + ) + test_df = {"address": data_a, "counterparty": data_l} result = create_dim_counterparty(test_df) - expected_columns = ["counterparty_id", "counterparty_legal_name", - "commercial_contact", "counterparty_legal_postcode"] + expected_columns = [ + "counterparty_id", + "counterparty_legal_name", + "commercial_contact", + "counterparty_legal_postcode", + ] print(data_l) print(data_a) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns + class TestCreateDimCurrency: - def test_dim_currency_returns_columns_and_values(self): - nones = [None,None,None] - d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"],"created_at":nones,"last_updated":nones} + nones = [None, None, None] + d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "created_at": nones, + "last_updated": nones, + } test_df = {"currency": pd.DataFrame(data=d)} - scraper_output = pd.DataFrame({"currency_code":["RUS","USD","PHP","GBP","EUR"],"currency_name":["Rubble","US Dollar","Peso","Pound","Euro"]}) - result = create_dim_currency(test_df,names=scraper_output).sort_values(by="currency_code",axis=0) - expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} - expected_df = pd.DataFrame(data=expected_d).sort_values(by="currency_code",axis=0) - assert isinstance(result, pd.DataFrame) - assert result.equals(expected_df) + scraper_output = pd.DataFrame( + { + "currency_code": ["RUS", "USD", "PHP", "GBP", "EUR"], + "currency_name": ["Rubble", "US Dollar", "Peso", "Pound", "Euro"], + } + ) + result = create_dim_currency(test_df, names=scraper_output).sort_values( + by="currency_code", axis=0 + ) + expected_d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "currency_name": ["US Dollar", "Euro", "Pound"], + } + expected_df = pd.DataFrame(data=expected_d).sort_values( + by="currency_code", axis=0 + ) + assert isinstance(result, pd.DataFrame) + assert result.equals(expected_df) def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self): result = scrape_currency_names() - assert isinstance(result,pd.DataFrame) - assert list(result.columns) == ['currency_code', 'currency_name'] + assert isinstance(result, pd.DataFrame) + assert list(result.columns) == ["currency_code", "currency_name"] -class TestCreateDimDate: +class TestCreateDimDate: def test_returns_required_columns(self): - df_one = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 5, 13),'not_dat':None},index=[0]) - df_two = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 9, 13)},index=[0]) - df_three = pd.DataFrame(data={'updated_date':dt(2022, 5, 17),'created_date':dt(2023, 5, 13)},index=[0]) - expected_df = pd.DataFrame(data= - [[dt(2020,5,17),2020,5,17,6,'Sunday','May',2], - [dt(2021,5,13),2021,5,13,3,'Thursday','May',2], - [dt(2021,9,13),2021,9,13,0,'Monday','September',3], - [dt(2022,5,17),2022,5,17,1,'Tuesday','May',2], - [dt(2023,5,13),2023,5,13,5,'Saturday','May',2]], - columns=['date_id','year','month','day','day_of_week','day_name','month_name','quarter']) + df_one = pd.DataFrame( + data={ + "updated_date": dt(2020, 5, 17), + "created_date": dt(2021, 5, 13), + "not_dat": None, + }, + index=[0], + ) + df_two = pd.DataFrame( + data={"updated_date": dt(2020, 5, 17), "created_date": dt(2021, 9, 13)}, + index=[0], + ) + df_three = pd.DataFrame( + data={"updated_date": dt(2022, 5, 17), "created_date": dt(2023, 5, 13)}, + index=[0], + ) + expected_df = pd.DataFrame( + data=[ + [dt(2020, 5, 17), 2020, 5, 17, 6, "Sunday", "May", 2], + [dt(2021, 5, 13), 2021, 5, 13, 3, "Thursday", "May", 2], + [dt(2021, 9, 13), 2021, 9, 13, 0, "Monday", "September", 3], + [dt(2022, 5, 17), 2022, 5, 17, 1, "Tuesday", "May", 2], + [dt(2023, 5, 13), 2023, 5, 13, 5, "Saturday", "May", 2], + ], + columns=[ + "date_id", + "year", + "month", + "day", + "day_of_week", + "day_name", + "month_name", + "quarter", + ], + ) with patch("src.dataframes.create_fact_payment") as mock_fp: with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo: with patch("src.dataframes.create_fact_sales_order") as mock_fso: mock_fp.return_value = df_one mock_fpo.return_value = df_two mock_fso.return_value = df_three - result = create_dim_date({'dum':0}) - result.reset_index(inplace=True,drop=True) + result = create_dim_date({"dum": 0}) + result.reset_index(inplace=True, drop=True) assert result.eq(expected_df, axis="columns").all(axis=None) - -class TestCreateDimLocation: + +class TestCreateDimLocation: def test_returns_correct_columns_lo(self): - dict_df = {'address':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], - columns=['created_at','last_updated','address_id','postal_code'])} + dict_df = { + "address": pd.DataFrame( + data=[["some_time", "some_other_time", 1, "SE18 9QO"]], + columns=["created_at", "last_updated", "address_id", "postal_code"], + ) + } result = create_dim_location(dict_df) - assert list(result.columns) == ['location_id','postal_code'] - + assert list(result.columns) == ["location_id", "postal_code"] + + class TestCreateDimTransaction: - def test_returns_correct_columns_tr(self): - dict_df = {'transaction':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], - columns=['created_at','last_updated','transaction_id','some_other_id'])} + def test_returns_correct_columns_tr(self): + dict_df = { + "transaction": pd.DataFrame( + data=[["some_time", "some_other_time", 1, "SE18 9QO"]], + columns=[ + "created_at", + "last_updated", + "transaction_id", + "some_other_id", + ], + ) + } result = create_dim_transaction(dict_df) - assert list(result.columns) == ['transaction_id','some_other_id'] + assert list(result.columns) == ["transaction_id", "some_other_id"] + class TestCreateFactPayment: def test_returns_correct_columns_payment(self): - dict_df = {'payment':pd.DataFrame(data=[[dt.strptime('2022-11-03 14:20:49.962846','%Y-%m-%d %H:%M:%S.%f'), - dt.strptime('2022-12-14 16:20:49.962194','%Y-%m-%d %H:%M:%S.%f'),1,'SE18 9QO','2020-07-16']], - columns=['created_at','last_updated','payment_id','some_other_id','payment_date'])} - expected_cols = ['payment_record_id','created_date','created_time','last_updated_date', - 'last_updated_time','payment_date','payment_id','some_other_id'] + dict_df = { + "payment": pd.DataFrame( + data=[ + [ + dt.strptime( + "2022-11-03 14:20:49.962846", "%Y-%m-%d %H:%M:%S.%f" + ), + dt.strptime( + "2022-12-14 16:20:49.962194", "%Y-%m-%d %H:%M:%S.%f" + ), + 1, + "SE18 9QO", + "2020-07-16", + ] + ], + columns=[ + "created_at", + "last_updated", + "payment_id", + "some_other_id", + "payment_date", + ], + ) + } + expected_cols = [ + "payment_record_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "payment_date", + "payment_id", + "some_other_id", + ] result = create_fact_payment(dict_df) - assert isinstance(result,pd.DataFrame) + assert isinstance(result, pd.DataFrame) for col in list(result.columns): assert col in expected_cols for col in expected_cols: - if '_date' in col: + if "_date" in col: print(col) - assert result[col].dtype == 'datetime64[ns]' - if '_time' in col: + assert result[col].dtype == "datetime64[ns]" + if "_time" in col: print(col) - assert result[col].dtype == 'O' #<< O for object - - \ No newline at end of file + assert result[col].dtype == "O" # << O for object -- cgit v1.2.3 From f6584f5f52bc8731a2076e2d692faf28b107647d Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Tue, 27 Aug 2024 15:20:13 +0100 Subject: wip: add test for parquet file conversion --- tests/test_load_lambda.py | 59 ++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 51 insertions(+), 8 deletions(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 9b0a271..b5821a4 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -7,6 +7,7 @@ import botocore.exceptions import os import pytest from src.load_lambda import * +import tempfile @pytest.fixture(scope="class") @@ -22,7 +23,7 @@ def aws_credentials(): def mock_s3_client(aws_credentials): with mock_aws(): yield boto3.client("s3") - + @pytest.fixture(scope="class") def mock_sm_client(aws_credentials): @@ -30,6 +31,11 @@ def mock_sm_client(aws_credentials): yield boto3.client("secretsmanager") +@pytest.fixture(scope="class") +def mock_connect_db(mocker): + return mocker.patch("src.load_lambda.connect_to_db_and_return_engine") + + class TestLambdaHandler: pass @@ -47,9 +53,7 @@ class TestRetrieveSecrets: secret_name = "test_secret" - mock_sm_client.create_secret( - Name=secret_name, SecretString=json.dumps(secret) - ) + mock_sm_client.create_secret(Name=secret_name, SecretString=json.dumps(secret)) result = retrieve_secrets(mock_sm_client, secret_name) @@ -71,7 +75,17 @@ class TestRetrieveSecrets: class TestConnectToDBAndReturnEngine: - pass + def test_returns_unsuccessful_connection_when_wrong_credentials(self): + sm_secret = { + "host": "host", + "port": "port", + "user": "user", + "password": "password", + "database": "database", + } + + with pytest.raises(Exception): + connect_to_db_and_return_engine(json.dumps(sm_secret)) class TestGetTransformBucket: @@ -120,9 +134,38 @@ class TestConvertParquetToDfs: # result = convert_parquet_files_to_dfs(bucket_name="transform_bucket", client=mock_s3_client) # assert "dim_staff" in result + def test_function_returns_dictionary_with_file_key_and_dataframe( + self, mock_s3_client + ): + with tempfile.TemporaryDirectory() as tmp: + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } + + test_df = pd.DataFrame(data=d) + + path = os.path.join(tmp, "test_parquet.parquet") + + test_df.to_parquet(path, engine="pyarrow") + + with open(path, "rb") as p: + mock_s3_client.put_object( + Bucket="transform_bucket", Key="test_parquet.parquet", Body=p.read() + ) + + result = convert_parquet_files_to_dfs( + bucket_name="transform_bucket", client=mock_s3_client + ) + + assert "test_parquet.parquet" in result + + pd.testing.assert_frame_equal(result["test_parquet.parquet"], test_df) -def mock_connect_db(mocker): - return mocker.patch("src.load_lambda.connect_to_db_and_return_engine") class TestUploadDfsToDatabase: - pass \ No newline at end of file + pass -- cgit v1.2.3 From f5bccf178ea1ebce213efd0518af63d74b00a11c Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Tue, 27 Aug 2024 15:34:35 +0100 Subject: test: add lambda_handler tests --- tests/test_load_lambda.py | 27 +++++++++++++++++++++------ 1 file changed, 21 insertions(+), 6 deletions(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index b5821a4..98ab36b 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -31,13 +31,28 @@ def mock_sm_client(aws_credentials): yield boto3.client("secretsmanager") -@pytest.fixture(scope="class") -def mock_connect_db(mocker): - return mocker.patch("src.load_lambda.connect_to_db_and_return_engine") - - class TestLambdaHandler: - pass + def test_lambda_handler_returns_success(self, mocker): + mocker.patch( + "src.load_lambda.upload_dfs_to_database", + return_value={"uploaded": ["table_one", "table_two"]}, + ) + result = lambda_handler(None, None) + assert result["statusCode"] == 200 + assert "table_one" in result["body"] + assert "table_two" in result["body"] + + def test_lambda_handler_does_not_upload_anything(self, mocker): + mocker.patch( + "src.load_lambda.upload_dfs_to_database", + return_value={"uploaded": []}, + ) + result = lambda_handler(None, None) + assert result["statusCode"] == 200 + assert "No dataframes were uploaded" in result["body"] + + def test_lambda_handler_returns_exception(self, mocker): + pass class TestRetrieveSecrets: -- cgit v1.2.3 From 843f11c302a2a9089c3726342cd1231015f074f7 Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Tue, 27 Aug 2024 15:36:12 +0100 Subject: docs: add comments for upload tests --- tests/test_load_lambda.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 98ab36b..a29b75a 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -183,4 +183,7 @@ class TestConvertParquetToDfs: class TestUploadDfsToDatabase: + # Full success test + # Partial success test + # Failure test pass -- cgit v1.2.3 From cbfc98a9f43b5a0dae95337057c18c9dc2a298e3 Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Tue, 27 Aug 2024 16:00:29 +0100 Subject: wip: update TestLambdaHandler & lambda_handler function --- src/load_lambda.py | 19 +++++++++++-------- tests/test_load_lambda.py | 12 +++++++++--- 2 files changed, 20 insertions(+), 11 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 11d1d70..39fa27d 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -23,18 +23,21 @@ logging.getLogger("botocore").setLevel(logging.INFO) def lambda_handler(event, context): try: uploaded_tables = upload_dfs_to_database() - if not uploaded_tables["uploaded"]: + if uploaded_tables["not_uploaded"]: return { "statusCode": 200, "body": json.dumps("No dataframes were uploaded."), } - return { - "statusCode": 200, - "body": json.dumps( - f"""The following dataframes were uploaded successfully: - {uploaded_tables["uploaded"]} .""" - ), - } + + if uploaded_tables["uploaded"]: + return { + "statusCode": 200, + "body": json.dumps( + f"""The following dataframes were uploaded successfully: + {uploaded_tables["uploaded"]} .""" + ), + } + except Exception as e: logger.error(f"Error: {e}", exc_info=True) return {"statusCode": 500, "body": json.dumps("Internal server error.")} diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index a29b75a..9286e48 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -35,7 +35,7 @@ class TestLambdaHandler: def test_lambda_handler_returns_success(self, mocker): mocker.patch( "src.load_lambda.upload_dfs_to_database", - return_value={"uploaded": ["table_one", "table_two"]}, + return_value={"uploaded": ["table_one", "table_two"], "not_uploaded": []}, ) result = lambda_handler(None, None) assert result["statusCode"] == 200 @@ -45,14 +45,20 @@ class TestLambdaHandler: def test_lambda_handler_does_not_upload_anything(self, mocker): mocker.patch( "src.load_lambda.upload_dfs_to_database", - return_value={"uploaded": []}, + return_value={"uploaded": [], "not_uploaded": []}, ) result = lambda_handler(None, None) assert result["statusCode"] == 200 assert "No dataframes were uploaded" in result["body"] def test_lambda_handler_returns_exception(self, mocker): - pass + mocker.patch( + "src.load_lambda.upload_dfs_to_database", + return_value={"test": []}, + ) + + with pytest.raises(Exception): + lambda_handler(None, None) class TestRetrieveSecrets: -- cgit v1.2.3 From 27f89b78775f9b6fd8d3d560689c53db2beb1b64 Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 16:39:38 +0100 Subject: add logger error to lambda handler --- src/load_lambda.py | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 39fa27d..9e15af3 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -5,6 +5,7 @@ import pyarrow.parquet as pq from io import BytesIO import logging import json +import traceback from sqlalchemy import create_engine @@ -28,8 +29,7 @@ def lambda_handler(event, context): "statusCode": 200, "body": json.dumps("No dataframes were uploaded."), } - - if uploaded_tables["uploaded"]: + elif uploaded_tables["uploaded"]: return { "statusCode": 200, "body": json.dumps( @@ -37,10 +37,12 @@ def lambda_handler(event, context): {uploaded_tables["uploaded"]} .""" ), } - + else: + logger.error(f"error") + return {"error"} except Exception as e: - logger.error(f"Error: {e}", exc_info=True) - return {"statusCode": 500, "body": json.dumps("Internal server error.")} + logger.error({e}) + return {"statusCode": 500, "body": {e}} def retrieve_secrets(client=None, secret_name=None): -- cgit v1.2.3 From 0ea88c0216d9e5eca9e4aca4f2fa427d38184648 Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 16:40:21 +0100 Subject: add passing tests for lambda handler --- tests/test_load_lambda.py | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 9286e48..0b13b54 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -32,7 +32,7 @@ def mock_sm_client(aws_credentials): class TestLambdaHandler: - def test_lambda_handler_returns_success(self, mocker): + def test_lambda_handler_returns_200_and_table_name_if_uploaded(self, mocker): mocker.patch( "src.load_lambda.upload_dfs_to_database", return_value={"uploaded": ["table_one", "table_two"], "not_uploaded": []}, @@ -42,23 +42,25 @@ class TestLambdaHandler: assert "table_one" in result["body"] assert "table_two" in result["body"] - def test_lambda_handler_does_not_upload_anything(self, mocker): + def test_lambda_handler_returns_200_and_table_name_if_not_uploaded(self, mocker): mocker.patch( "src.load_lambda.upload_dfs_to_database", - return_value={"uploaded": [], "not_uploaded": []}, + return_value={"uploaded": [], "not_uploaded": ["table_one"]}, ) result = lambda_handler(None, None) assert result["statusCode"] == 200 assert "No dataframes were uploaded" in result["body"] - def test_lambda_handler_returns_exception(self, mocker): + def test_lambda_handler_returns_error_if_both_lists_empty(self, mocker): mocker.patch( "src.load_lambda.upload_dfs_to_database", - return_value={"test": []}, + return_value={"uploaded": [], "not_uploaded": []}, ) - with pytest.raises(Exception): - lambda_handler(None, None) + result = lambda_handler(None, None) + + assert result == {"error"} + class TestRetrieveSecrets: -- cgit v1.2.3 From 1a145a36d524a785c821aafbdb3512c24be6c57e Mon Sep 17 00:00:00 2001 From: Ang Bel Date: Tue, 27 Aug 2024 17:00:04 +0100 Subject: test: transform refactoring - it now loads parquet files into s3 bucket --- src/dataframes.py | 32 ++++++++++++++++---------------- src/transform_lambda.py | 6 +++--- tests/test_dataframes.py | 10 +++------- 3 files changed, 22 insertions(+), 26 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 1f445a4..9d0f2ac 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -20,13 +20,13 @@ import requests def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - df_sales["created_date"] = pd.to_datetime(df_sales["created_at"].dt.date,format='%Y-%m-%d') - df_sales["created_time"] = df_sales["created_at"].dt.floor('s').dt.time - df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"].dt.date,format='%Y-%m-%d') - df_sales["last_updated_time"] = df_sales["last_updated"].dt.floor('s').dt.time + df_sales["created_date"] = df_sales["created_at"].astype('datetime64[ns]').dt.date + df_sales["created_time"] = df_sales["created_at"].astype('datetime64[ns]').dt.floor('s').dt.time + df_sales["last_updated_date"] = df_sales["last_updated"].astype('datetime64[ns]').dt.date + df_sales["last_updated_time"] = df_sales["last_updated"].astype('datetime64[ns]').dt.floor('s').dt.time df_sales['agreed_delivery_date'] = pd.to_datetime(df_sales['agreed_delivery_date'],format="%Y-%m-%d") df_sales['agreed_payment_date'] = pd.to_datetime(df_sales['agreed_payment_date'],format="%Y-%m-%d") - df_sales.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_sales = df_sales.drop(labels=['created_at','last_updated'],axis=1) df_sales.reset_index(inplace=True) return df_sales @@ -34,13 +34,13 @@ def create_fact_sales_order(dict_of_df): def create_fact_purchase_orders(dict_of_df): df_po = dict_of_df['purchase_order'] df_po.index.name = 'purchase_record_id' - df_po['created_date'] = pd.to_datetime(df_po['created_at'].dt.date,format='%Y-%m-%d') - df_po['created_time'] = df_po['created_at'].dt.floor('s').dt.time - df_po['last_updated_date'] = pd.to_datetime(df_po['last_updated'].dt.date,format='%Y-%m-%d') - df_po['last_updated_time'] = df_po['last_updated'].dt.floor('s').dt.time + df_po['created_date'] = df_po['created_at'].astype('datetime64[ns]').dt.date + df_po['created_time'] = df_po['created_at'].astype('datetime64[ns]').dt.floor('s').dt.time + df_po['last_updated_date'] = df_po['last_updated'].astype('datetime64[ns]').dt.date + df_po['last_updated_time'] = df_po['last_updated'].astype('datetime64[ns]').dt.floor('s').dt.time df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") - df_po.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_po = df_po.drop(labels=['created_at','last_updated'],axis=1) df_po.reset_index(inplace=True) return df_po @@ -48,12 +48,12 @@ def create_fact_purchase_orders(dict_of_df): def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = pd.to_datetime(df_payment["created_at"].dt.date,format='%Y-%m-%d') - df_payment["created_time"] = df_payment["created_at"].dt.floor('s').dt.time - df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"].dt.date,format='%Y-%m-%d') - df_payment["last_updated_time"] = df_payment["last_updated"].dt.floor('s').dt.time + df_payment["created_date"] = df_payment["created_at"].astype('datetime64[ns]').dt.date + df_payment["created_time"] = df_payment["created_at"].astype('datetime64[ns]').dt.floor('s').dt.time + df_payment["last_updated_date"] = df_payment["last_updated"].astype('datetime64[ns]').dt.date + df_payment["last_updated_time"] = df_payment["last_updated"].astype('datetime64[ns]').dt.floor('s').dt.time df_payment['payment_date'] = pd.to_datetime(df_payment['payment_date'],format="%Y-%m-%d") - df_payment.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_payment = df_payment.drop(labels=['created_at','last_updated'],axis=1) df_payment.reset_index(inplace=True) return df_payment @@ -83,7 +83,7 @@ def create_dim_date(dict_of_df): fact_dfs = [create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df)] list_of_date_columns = [] for df in fact_dfs: - date_col_names = [col_name for col_name in list(df.columns) if 'date' in col_name] + date_col_names = [col_name for col_name in list(df.columns) if '_date' in col_name] for col in date_col_names: list_of_date_columns.append(df[col]) sr_date = pd.array(pd.concat(list_of_date_columns),dtype='datetime64[ns]') diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 2cd9272..ccf90e5 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -117,7 +117,7 @@ def process_to_parquet_and_upload_to_s3( parquet_file = df.to_parquet( f"{table_name}.parquet", engine="pyarrow" ) # or fastparquet - client.upload_file(parquet_file, bucket, f"{table_name}.parquet") + client.upload_file(f"{table_name}.parquet", bucket, f"{table_name}.parquet") #changed parquet_file variable to the file name status["uploaded"].append(table_name) for table_name, df in mutable_df_dict.items(): @@ -127,7 +127,7 @@ def process_to_parquet_and_upload_to_s3( parquet_file = df.to_parquet( f"{table_name}.parquet", engine="pyarrow" ) # or fastparquet - client.upload_file(parquet_file, bucket, s3_key) + client.upload_file(f"{table_name}.parquet", bucket, s3_key) status["uploaded"].append(table_name) return status @@ -203,7 +203,7 @@ def list_existing_s3_files(bucket_name, client=boto3.client("s3")): existing_files = [obj["Key"] for obj in response["Contents"]] else: logger.error("The bucket is empty") - return None + return [] #changed from None to [] so it is an iterable except ClientError as e: logger.error(f"Error listing S3 objects: {e}") diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index 70aefe8..adbb5ed 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -139,11 +139,7 @@ class TestCreateFactPayment: for col in list(result.columns): assert col in expected_cols for col in expected_cols: - if '_date' in col: - print(col) - assert result[col].dtype == 'datetime64[ns]' - if '_time' in col: - print(col) - assert result[col].dtype == 'O' #<< O for object - + if '_date' or '_time' in col: + assert result[col].dtype == 'O' + \ No newline at end of file -- cgit v1.2.3 From 57617571df0a667aca55fc54184696a19c689524 Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 17:00:08 +0100 Subject: add lambda handler updated tests --- tests/test_load_lambda.py | 1 + 1 file changed, 1 insertion(+) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 0b13b54..829b908 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -63,6 +63,7 @@ class TestLambdaHandler: + class TestRetrieveSecrets: def test_retrieve_secrets_returns_dictionary(self, mock_sm_client): secret = { -- cgit v1.2.3 From dc095acd4d5b9f73a716a076ce601c3810f9635b Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Tue, 27 Aug 2024 16:01:11 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 1a145a3 according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/101 --- src/dataframes.py | 236 ++++++++++++++++++++++++++------------- src/transform_lambda.py | 5 +- tests/test_dataframes.py | 282 +++++++++++++++++++++++++++++++++++------------ 3 files changed, 375 insertions(+), 148 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 9d0f2ac..f122368 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -2,7 +2,7 @@ import pandas as pd from bs4 import BeautifulSoup import requests -#Table names: +# Table names: # fact_sales_order # fact_purchase_orders # fact_payment @@ -16,133 +16,213 @@ import requests # dim_counterparty -#no test, same as fact_payment +# no test, same as fact_payment def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - df_sales["created_date"] = df_sales["created_at"].astype('datetime64[ns]').dt.date - df_sales["created_time"] = df_sales["created_at"].astype('datetime64[ns]').dt.floor('s').dt.time - df_sales["last_updated_date"] = df_sales["last_updated"].astype('datetime64[ns]').dt.date - df_sales["last_updated_time"] = df_sales["last_updated"].astype('datetime64[ns]').dt.floor('s').dt.time - df_sales['agreed_delivery_date'] = pd.to_datetime(df_sales['agreed_delivery_date'],format="%Y-%m-%d") - df_sales['agreed_payment_date'] = pd.to_datetime(df_sales['agreed_payment_date'],format="%Y-%m-%d") - df_sales = df_sales.drop(labels=['created_at','last_updated'],axis=1) + df_sales["created_date"] = df_sales["created_at"].astype("datetime64[ns]").dt.date + df_sales["created_time"] = ( + df_sales["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_sales["last_updated_date"] = ( + df_sales["last_updated"].astype("datetime64[ns]").dt.date + ) + df_sales["last_updated_time"] = ( + df_sales["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_sales["agreed_delivery_date"] = pd.to_datetime( + df_sales["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_sales["agreed_payment_date"] = pd.to_datetime( + df_sales["agreed_payment_date"], format="%Y-%m-%d" + ) + df_sales = df_sales.drop(labels=["created_at", "last_updated"], axis=1) df_sales.reset_index(inplace=True) return df_sales -#no test, same as fact_payment + +# no test, same as fact_payment + + def create_fact_purchase_orders(dict_of_df): - df_po = dict_of_df['purchase_order'] - df_po.index.name = 'purchase_record_id' - df_po['created_date'] = df_po['created_at'].astype('datetime64[ns]').dt.date - df_po['created_time'] = df_po['created_at'].astype('datetime64[ns]').dt.floor('s').dt.time - df_po['last_updated_date'] = df_po['last_updated'].astype('datetime64[ns]').dt.date - df_po['last_updated_time'] = df_po['last_updated'].astype('datetime64[ns]').dt.floor('s').dt.time - df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") - df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") - df_po = df_po.drop(labels=['created_at','last_updated'],axis=1) + df_po = dict_of_df["purchase_order"] + df_po.index.name = "purchase_record_id" + df_po["created_date"] = df_po["created_at"].astype("datetime64[ns]").dt.date + df_po["created_time"] = ( + df_po["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_po["last_updated_date"] = df_po["last_updated"].astype("datetime64[ns]").dt.date + df_po["last_updated_time"] = ( + df_po["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_po["agreed_delivery_date"] = pd.to_datetime( + df_po["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_po["agreed_payment_date"] = pd.to_datetime( + df_po["agreed_payment_date"], format="%Y-%m-%d" + ) + df_po = df_po.drop(labels=["created_at", "last_updated"], axis=1) df_po.reset_index(inplace=True) return df_po -#test passed + +# test passed + + def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = df_payment["created_at"].astype('datetime64[ns]').dt.date - df_payment["created_time"] = df_payment["created_at"].astype('datetime64[ns]').dt.floor('s').dt.time - df_payment["last_updated_date"] = df_payment["last_updated"].astype('datetime64[ns]').dt.date - df_payment["last_updated_time"] = df_payment["last_updated"].astype('datetime64[ns]').dt.floor('s').dt.time - df_payment['payment_date'] = pd.to_datetime(df_payment['payment_date'],format="%Y-%m-%d") - df_payment = df_payment.drop(labels=['created_at','last_updated'],axis=1) + df_payment["created_date"] = ( + df_payment["created_at"].astype("datetime64[ns]").dt.date + ) + df_payment["created_time"] = ( + df_payment["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_payment["last_updated_date"] = ( + df_payment["last_updated"].astype("datetime64[ns]").dt.date + ) + df_payment["last_updated_time"] = ( + df_payment["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_payment["payment_date"] = pd.to_datetime( + df_payment["payment_date"], format="%Y-%m-%d" + ) + df_payment = df_payment.drop(labels=["created_at", "last_updated"], axis=1) df_payment.reset_index(inplace=True) return df_payment -#test passed + +# test passed + + def create_dim_transaction(dict_of_df): - df_transaction = dict_of_df["transaction"].drop(labels=['created_at', 'last_updated'], axis=1) + df_transaction = dict_of_df["transaction"].drop( + labels=["created_at", "last_updated"], axis=1 + ) return df_transaction -#test passed + +# test passed + + def create_dim_location(dict_of_df): - df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}) + df_loc = ( + dict_of_df["address"] + .drop(labels=["created_at", "last_updated"], axis=1) + .rename(columns={"address_id": "location_id"}) + ) return df_loc def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) - df_cp = pd.merge(dict_of_df['counterparty'], - df_prefixed_address, - left_on="legal_address_id", - right_on="counterparty_legal_address_id", - how="outer") - df_cp.drop(columns=["legal_address_id","counterparty_legal_address_id"],inplace=True) + df_prefixed_address = dict_of_df["address"].add_prefix( + "counterparty_legal_", axis=1 + ) + df_cp = pd.merge( + dict_of_df["counterparty"], + df_prefixed_address, + left_on="legal_address_id", + right_on="counterparty_legal_address_id", + how="outer", + ) + df_cp.drop( + columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True + ) return df_cp -#test passed + +# test passed + + def create_dim_date(dict_of_df): - fact_dfs = [create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df)] + fact_dfs = [ + create_fact_payment(dict_of_df), + create_fact_purchase_orders(dict_of_df), + create_fact_sales_order(dict_of_df), + ] list_of_date_columns = [] for df in fact_dfs: - date_col_names = [col_name for col_name in list(df.columns) if '_date' in col_name] + date_col_names = [ + col_name for col_name in list(df.columns) if "_date" in col_name + ] for col in date_col_names: list_of_date_columns.append(df[col]) - sr_date = pd.array(pd.concat(list_of_date_columns),dtype='datetime64[ns]') - df_date = pd.DataFrame(data=sr_date,columns=['date_id']) + sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") + df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) df_date.drop_duplicates(inplace=True) - df_date['year'] = df_date['date_id'].dt.year - df_date['month'] = df_date['date_id'].dt.month - df_date['day'] = df_date['date_id'].dt.day - df_date['day_of_week'] = df_date['date_id'].dt.dayofweek - df_date['day_name'] = df_date['date_id'].dt.day_name() - df_date['month_name'] = df_date['date_id'].dt.month_name() - df_date['quarter'] = df_date['date_id'].dt.quarter + df_date["year"] = df_date["date_id"].dt.year + df_date["month"] = df_date["date_id"].dt.month + df_date["day"] = df_date["date_id"].dt.day + df_date["day_of_week"] = df_date["date_id"].dt.dayofweek + df_date["day_name"] = df_date["date_id"].dt.day_name() + df_date["month_name"] = df_date["date_id"].dt.month_name() + df_date["quarter"] = df_date["date_id"].dt.quarter return df_date -#tests passed -def scrape_currency_names(): - response = requests.get('https://www.xe.com/currency/').content - soup = BeautifulSoup(response,'html.parser') - currency = [item.text for item in soup.findAll('a', attrs={'class' : "sc-299dec64-6 fZPTSw"})] - sr = pd.Series(currency) - df_cur = sr.str.split(pat=" - ",expand=True).rename({0:'currency_code',1:'currency_name'},axis=1) - return df_cur - -#tests passed -def create_dim_currency(dict_of_df,names=scrape_currency_names()): - df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1) - dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner') - return dim_cur -#tests passed -def create_dim_payment_type(dict_of_df): - df_payment_type = dict_of_df["payment_type"] - dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] - return dim_payment_type +# tests passed -#tests passed -def create_dim_design(dict_of_df): - df_design = dict_of_df["design"] - dim_design = df_design.loc[:, ["design_id", "design_name", "file_name", "file_location"]] - return dim_design -#tests passed -def create_dim_staff(dict_of_df): - staff_department = pd.merge(dict_of_df["staff"], dict_of_df["department"], on='department_id', how="left") - dim_staff = staff_department.loc[:, ['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address']] - return dim_staff +def scrape_currency_names(): + response = requests.get("https://www.xe.com/currency/").content + soup = BeautifulSoup(response, "html.parser") + currency = [ + item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) + ] + sr = pd.Series(currency) + df_cur = sr.str.split(pat=" - ", expand=True).rename( + {0: "currency_code", 1: "currency_name"}, axis=1 + ) + return df_cur +# tests passed +def create_dim_currency(dict_of_df, names=scrape_currency_names()): + df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) + dim_cur = pd.merge( + df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" + ) + return dim_cur +# tests passed +def create_dim_payment_type(dict_of_df): + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + return dim_payment_type +# tests passed +def create_dim_design(dict_of_df): + df_design = dict_of_df["design"] + dim_design = df_design.loc[ + :, ["design_id", "design_name", "file_name", "file_location"] + ] + return dim_design +# tests passed +def create_dim_staff(dict_of_df): + staff_department = pd.merge( + dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" + ) + dim_staff = staff_department.loc[ + :, + [ + "staff_id", + "first_name", + "last_name", + "department_name", + "location", + "email_address", + ], + ] + return dim_staff diff --git a/src/transform_lambda.py b/src/transform_lambda.py index ccf90e5..93b2284 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -117,7 +117,8 @@ def process_to_parquet_and_upload_to_s3( parquet_file = df.to_parquet( f"{table_name}.parquet", engine="pyarrow" ) # or fastparquet - client.upload_file(f"{table_name}.parquet", bucket, f"{table_name}.parquet") #changed parquet_file variable to the file name + # changed parquet_file variable to the file name + client.upload_file(f"{table_name}.parquet", bucket, f"{table_name}.parquet") status["uploaded"].append(table_name) for table_name, df in mutable_df_dict.items(): @@ -203,7 +204,7 @@ def list_existing_s3_files(bucket_name, client=boto3.client("s3")): existing_files = [obj["Key"] for obj in response["Contents"]] else: logger.error("The bucket is empty") - return [] #changed from None to [] so it is an iterable + return [] # changed from None to [] so it is an iterable except ClientError as e: logger.error(f"Error listing S3 objects: {e}") diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index adbb5ed..c9ff43f 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -3,42 +3,88 @@ import pandas as pd from unittest.mock import patch from datetime import datetime as dt + class TestCreateDimDesign: def test_dim_design_returns_dataframe(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) assert isinstance(result, pd.DataFrame) def test_dim_design_returns_correct_columns_and_values(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) - d2 = {"design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"]} + d2 = { + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=d2) expected_result = expected_df.copy() assert result.equals(expected_result) + class TestCreateDimStaff: def test_dim_staff_returns_dataframe(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - assert isinstance(result, pd.DataFrame) + assert isinstance(result, pd.DataFrame) def test_dim_staff_returns_correct_columns_and_values(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - expected_d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"]} + expected_d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) expected_result = expected_df.copy() - assert result.equals(expected_result) + assert result.equals(expected_result) + class TestCreatePaymentType: def test_create_dim_payment_type_returns_correct_columns_and_values(self): @@ -46,100 +92,200 @@ class TestCreatePaymentType: test_df = {"payment_type": pd.DataFrame(data=d)} result = create_dim_payment_type(test_df) expected_columns = ["payment_type_id", "payment_type_name"] - expected_d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} + expected_d = { + "payment_type_id": ["Hello", "Bye"], + "payment_type_name": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns assert result.equals(expected_df) + class TestCreateDimCounterparty: - def test_create_dim_counterparty_type_returns_correct_columns_and_object(self): - data_l = pd.DataFrame(data={"counterparty_id": ["Hello", "Bye"], - "counterparty_legal_name": ["Hello", "Bye"], - "commercial_contact": ["Hello", "Bye"], - "legal_address_id": ["bond street", "regent street"]}) - data_a = pd.DataFrame(data={"address_id":["bond street", "regent street"], - "postcode":[98365,93753]}) - test_df = {"address": data_a,"counterparty":data_l} + data_l = pd.DataFrame( + data={ + "counterparty_id": ["Hello", "Bye"], + "counterparty_legal_name": ["Hello", "Bye"], + "commercial_contact": ["Hello", "Bye"], + "legal_address_id": ["bond street", "regent street"], + } + ) + data_a = pd.DataFrame( + data={ + "address_id": ["bond street", "regent street"], + "postcode": [98365, 93753], + } + ) + test_df = {"address": data_a, "counterparty": data_l} result = create_dim_counterparty(test_df) - expected_columns = ["counterparty_id", "counterparty_legal_name", - "commercial_contact", "counterparty_legal_postcode"] + expected_columns = [ + "counterparty_id", + "counterparty_legal_name", + "commercial_contact", + "counterparty_legal_postcode", + ] print(data_l) print(data_a) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns + class TestCreateDimCurrency: - def test_dim_currency_returns_columns_and_values(self): - nones = [None,None,None] - d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"],"created_at":nones,"last_updated":nones} + nones = [None, None, None] + d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "created_at": nones, + "last_updated": nones, + } test_df = {"currency": pd.DataFrame(data=d)} - scraper_output = pd.DataFrame({"currency_code":["RUS","USD","PHP","GBP","EUR"],"currency_name":["Rubble","US Dollar","Peso","Pound","Euro"]}) - result = create_dim_currency(test_df,names=scraper_output).sort_values(by="currency_code",axis=0) - expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} - expected_df = pd.DataFrame(data=expected_d).sort_values(by="currency_code",axis=0) - assert isinstance(result, pd.DataFrame) - assert result.equals(expected_df) + scraper_output = pd.DataFrame( + { + "currency_code": ["RUS", "USD", "PHP", "GBP", "EUR"], + "currency_name": ["Rubble", "US Dollar", "Peso", "Pound", "Euro"], + } + ) + result = create_dim_currency(test_df, names=scraper_output).sort_values( + by="currency_code", axis=0 + ) + expected_d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "currency_name": ["US Dollar", "Euro", "Pound"], + } + expected_df = pd.DataFrame(data=expected_d).sort_values( + by="currency_code", axis=0 + ) + assert isinstance(result, pd.DataFrame) + assert result.equals(expected_df) def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self): result = scrape_currency_names() - assert isinstance(result,pd.DataFrame) - assert list(result.columns) == ['currency_code', 'currency_name'] + assert isinstance(result, pd.DataFrame) + assert list(result.columns) == ["currency_code", "currency_name"] -class TestCreateDimDate: +class TestCreateDimDate: def test_returns_required_columns(self): - df_one = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 5, 13),'not_dat':None},index=[0]) - df_two = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 9, 13)},index=[0]) - df_three = pd.DataFrame(data={'updated_date':dt(2022, 5, 17),'created_date':dt(2023, 5, 13)},index=[0]) - expected_df = pd.DataFrame(data= - [[dt(2020,5,17),2020,5,17,6,'Sunday','May',2], - [dt(2021,5,13),2021,5,13,3,'Thursday','May',2], - [dt(2021,9,13),2021,9,13,0,'Monday','September',3], - [dt(2022,5,17),2022,5,17,1,'Tuesday','May',2], - [dt(2023,5,13),2023,5,13,5,'Saturday','May',2]], - columns=['date_id','year','month','day','day_of_week','day_name','month_name','quarter']) + df_one = pd.DataFrame( + data={ + "updated_date": dt(2020, 5, 17), + "created_date": dt(2021, 5, 13), + "not_dat": None, + }, + index=[0], + ) + df_two = pd.DataFrame( + data={"updated_date": dt(2020, 5, 17), "created_date": dt(2021, 9, 13)}, + index=[0], + ) + df_three = pd.DataFrame( + data={"updated_date": dt(2022, 5, 17), "created_date": dt(2023, 5, 13)}, + index=[0], + ) + expected_df = pd.DataFrame( + data=[ + [dt(2020, 5, 17), 2020, 5, 17, 6, "Sunday", "May", 2], + [dt(2021, 5, 13), 2021, 5, 13, 3, "Thursday", "May", 2], + [dt(2021, 9, 13), 2021, 9, 13, 0, "Monday", "September", 3], + [dt(2022, 5, 17), 2022, 5, 17, 1, "Tuesday", "May", 2], + [dt(2023, 5, 13), 2023, 5, 13, 5, "Saturday", "May", 2], + ], + columns=[ + "date_id", + "year", + "month", + "day", + "day_of_week", + "day_name", + "month_name", + "quarter", + ], + ) with patch("src.dataframes.create_fact_payment") as mock_fp: with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo: with patch("src.dataframes.create_fact_sales_order") as mock_fso: mock_fp.return_value = df_one mock_fpo.return_value = df_two mock_fso.return_value = df_three - result = create_dim_date({'dum':0}) - result.reset_index(inplace=True,drop=True) + result = create_dim_date({"dum": 0}) + result.reset_index(inplace=True, drop=True) assert result.eq(expected_df, axis="columns").all(axis=None) - -class TestCreateDimLocation: + +class TestCreateDimLocation: def test_returns_correct_columns_lo(self): - dict_df = {'address':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], - columns=['created_at','last_updated','address_id','postal_code'])} + dict_df = { + "address": pd.DataFrame( + data=[["some_time", "some_other_time", 1, "SE18 9QO"]], + columns=["created_at", "last_updated", "address_id", "postal_code"], + ) + } result = create_dim_location(dict_df) - assert list(result.columns) == ['location_id','postal_code'] - + assert list(result.columns) == ["location_id", "postal_code"] + + class TestCreateDimTransaction: - def test_returns_correct_columns_tr(self): - dict_df = {'transaction':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], - columns=['created_at','last_updated','transaction_id','some_other_id'])} + def test_returns_correct_columns_tr(self): + dict_df = { + "transaction": pd.DataFrame( + data=[["some_time", "some_other_time", 1, "SE18 9QO"]], + columns=[ + "created_at", + "last_updated", + "transaction_id", + "some_other_id", + ], + ) + } result = create_dim_transaction(dict_df) - assert list(result.columns) == ['transaction_id','some_other_id'] + assert list(result.columns) == ["transaction_id", "some_other_id"] + class TestCreateFactPayment: def test_returns_correct_columns_payment(self): - dict_df = {'payment':pd.DataFrame(data=[[dt.strptime('2022-11-03 14:20:49.962846','%Y-%m-%d %H:%M:%S.%f'), - dt.strptime('2022-12-14 16:20:49.962194','%Y-%m-%d %H:%M:%S.%f'),1,'SE18 9QO','2020-07-16']], - columns=['created_at','last_updated','payment_id','some_other_id','payment_date'])} - expected_cols = ['payment_record_id','created_date','created_time','last_updated_date', - 'last_updated_time','payment_date','payment_id','some_other_id'] + dict_df = { + "payment": pd.DataFrame( + data=[ + [ + dt.strptime( + "2022-11-03 14:20:49.962846", "%Y-%m-%d %H:%M:%S.%f" + ), + dt.strptime( + "2022-12-14 16:20:49.962194", "%Y-%m-%d %H:%M:%S.%f" + ), + 1, + "SE18 9QO", + "2020-07-16", + ] + ], + columns=[ + "created_at", + "last_updated", + "payment_id", + "some_other_id", + "payment_date", + ], + ) + } + expected_cols = [ + "payment_record_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "payment_date", + "payment_id", + "some_other_id", + ] result = create_fact_payment(dict_df) - assert isinstance(result,pd.DataFrame) + assert isinstance(result, pd.DataFrame) for col in list(result.columns): assert col in expected_cols for col in expected_cols: - if '_date' or '_time' in col: - assert result[col].dtype == 'O' - - \ No newline at end of file + if "_date" or "_time" in col: + assert result[col].dtype == "O" -- cgit v1.2.3 From ad357ff34202827720dc216562dfbb0fbd65c297 Mon Sep 17 00:00:00 2001 From: HastarTara Date: Tue, 27 Aug 2024 17:02:25 +0100 Subject: test updates to transform lambda handler --- car_data.parquet | Bin 0 -> 2827 bytes src/transform_lambda.py | 59 ++++++++++++++++++++++++----------------- tests/test_transform_lambda.py | 39 +++++++++++++++++++++++++-- 3 files changed, 71 insertions(+), 27 deletions(-) create mode 100644 car_data.parquet diff --git a/car_data.parquet b/car_data.parquet new file mode 100644 index 0000000..1853af6 Binary files /dev/null and b/car_data.parquet differ diff --git a/src/transform_lambda.py b/src/transform_lambda.py index cd9541d..9830e0f 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -9,7 +9,7 @@ import pyarrow.parquet as pq from botocore.exceptions import ClientError from pg8000.native import Connection, InterfaceError from datetime import datetime - +import io class DBConnectionException(Exception): """Wraps pg8000.native Error or DatabaseError.""" @@ -59,6 +59,8 @@ def lambda_handler(event, context): TABLES, bucket_name("extract"), client=boto3.client("s3") ) + print(dict_of_df) + immutable_df_dict = { "dim_counterparty": create_dim_counterparty(dict_of_df), "dim_date": create_dim_date(dict_of_df), @@ -106,7 +108,7 @@ def process_to_parquet_and_upload_to_s3( immutable_df_dict, mutable_df_dict, bucket, - client=boto3.client("s3"), + client=boto3.client("s3") ): status = {"uploaded": [], "not_uploaded": []} @@ -114,21 +116,25 @@ def process_to_parquet_and_upload_to_s3( if table_name in existing_s3_files: status["not_uploaded"].append(table_name) else: - parquet_file = df.to_parquet( - f"{table_name}.parquet", engine="pyarrow" - ) # or fastparquet - client.upload_file(parquet_file, bucket, f"{table_name}.parquet") + parquet_buffer = io.BytesIO() + + df.to_parquet(parquet_buffer, engine="pyarrow") # or engine="fastparquet" + + parquet_buffer.seek(0) + + client.upload_fileobj(parquet_buffer, bucket, f"{table_name}.parquet") + status["uploaded"].append(table_name) - for table_name, df in mutable_df_dict.items(): - s3_key = datetime.strftime( - datetime.today(), f"{table_name}/%Y/%m/%d/{table_name}_%H:%M:%S.parquet" - ) - parquet_file = df.to_parquet( - f"{table_name}.parquet", engine="pyarrow" - ) # or fastparquet - client.upload_file(parquet_file, bucket, s3_key) - status["uploaded"].append(table_name) + # for table_name, df in mutable_df_dict.items(): + # s3_key = datetime.strftime( + # datetime.today(), f"{table_name}/%Y/%m/%d/{table_name}_%H:%M:%S.parquet" + # ) + # parquet_file = df.to_parquet( + # f"{table_name}.parquet", engine="pyarrow" + # ) # or fastparquet + # client.upload_file(parquet_file, bucket, s3_key) + # status["uploaded"].append(table_name) return status @@ -182,20 +188,23 @@ def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client("s3")): return table_dfs + + def bucket_name(bucket_prefix, client=boto3.client("s3")): - # response = client.list_buckets() - # for bucket in response["Buckets"]: - # if bucket_prefix in bucket["Name"]: - # return bucket["Name"] - - - response = client.list_buckets() - bucket_filter = [ + + response = client.list_buckets() + bucket_filter = [ bucket["Name"] for bucket in response["Buckets"] if bucket_prefix in bucket["Name"] - ] - return bucket_filter[0] + ] + if not bucket_filter: + raise ValueError(f"No bucket found with prefix: {bucket_prefix}") + + return bucket_filter[0] + + + def list_existing_s3_files(bucket_name, client=boto3.client("s3")): diff --git a/tests/test_transform_lambda.py b/tests/test_transform_lambda.py index cc4e07a..b4836c2 100644 --- a/tests/test_transform_lambda.py +++ b/tests/test_transform_lambda.py @@ -1,7 +1,7 @@ from src.transform_lambda import ( read_from_s3_subfolder_to_df, list_existing_s3_files, - bucket_name, + bucket_name, process_to_parquet_and_upload_to_s3 ) from moto import mock_aws import pytest @@ -152,4 +152,39 @@ class TestBucketName: def test_transform_bucket_name(self, mock_extract_bucket, mock_transform_bucket, s3_client): bucket2 = bucket_name('dummy_transform_buc', s3_client) assert bucket2 == 'dummy_transform_buc' - \ No newline at end of file + + + def test_recieves_error_when_bucket_doesnt_exist(self, mock_extract_bucket, s3_client): + s3_client.delete_bucket(Bucket='dummy_extract_buc') + with pytest.raises(ValueError): + bucket_name('dummy_extract_buc', s3_client) + + + + + + +class TestProcessToParquetUploadS3: + def test_func_uploads_to_s3(self, mock_transform_bucket, s3_client): + + expected_cars_df = pd.DataFrame( + np.array( + [ + ["Truck", "Chevrolet", "Grey"], + ["Convertible", "Mercedes", "Red"], + ["Van", "Volkswagen", "Blue"], + ] + ), + columns=["Car_type", "Brand", "Colour"], + ) + mock_dim_dict = {'car_data': expected_cars_df} + + response = process_to_parquet_and_upload_to_s3([], mock_dim_dict, {}, mock_transform_bucket, s3_client) + + + assert response == {"uploaded": ["car_data"], "not_uploaded": []} + + + + + -- cgit v1.2.3 From aed1c19a39062e8fe86cf0a531b8d1486b06d1ac Mon Sep 17 00:00:00 2001 From: Ang Bel Date: Tue, 27 Aug 2024 12:42:25 +0100 Subject: test: fact transformation function for payment test passes, other fact functions are equivalent, no tests written --- src/dataframes.py | 251 ++++++++++++++--------------------------- tests/test_dataframes.py | 144 +++++++++++++++++++++++ tests/test_fact_sales_order.py | 246 ---------------------------------------- 3 files changed, 229 insertions(+), 412 deletions(-) create mode 100644 tests/test_dataframes.py delete mode 100644 tests/test_fact_sales_order.py diff --git a/src/dataframes.py b/src/dataframes.py index ab53063..41f39b8 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -2,7 +2,7 @@ import pandas as pd from bs4 import BeautifulSoup import requests -# Table names: +#Table names: # fact_sales_order # fact_purchase_orders # fact_payment @@ -16,214 +16,133 @@ import requests # dim_counterparty +#no test, same as fact_payment def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - df_sales["created_date"] = pd.to_datetime(df_sales["created_at"]).dt.date - df_sales["created_time"] = pd.to_datetime(df_sales["created_at"]).dt.time - df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"]).dt.date - df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time - fact_sales_order = df_sales.loc[ - :, - [ - "sales_record_id", - "sales_order_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "sales_staff_id", - "counterparty_id", - "units_sold", - "unit_price", - "currency_id", - "design_id", - "agreed_payment_date", - "agreed_delivery_date", - "agreed_delivery_location_id", - ], - ] - return fact_sales_order - - -# fact_purchase_order from purchase_order - - + df_sales["created_date"] = pd.to_datetime(df_sales["created_at"],format='%Y-%m-%d') + df_sales["created_time"] = pd.to_datetime(df_sales["created_at"],format='%H-%M-%S') + df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"],format='%Y-%m-%d') + df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"],format='%H-%M-%S') + df_sales['agreed_delivery_date'] = pd.to_datetime(df_sales['agreed_delivery_date'],format="%Y-%m-%d") + df_sales['agreed_payment_date'] = pd.to_datetime(df_sales['agreed_payment_date'],format="%Y-%m-%d") + df_sales.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_sales.reset_index(inplace=True) + return df_sales + +#no test, same as fact_payment def create_fact_purchase_orders(dict_of_df): - df_po = dict_of_df["purchase_order"] - df_po.index.name = "purchase_record_id" - df_po["created_date"] = df_po["created_at"].date() - df_po["created_time"] = df_po["created_at"].dt.time - df_po["last_updated_date"] = df_po["last_updated_at"].date() - df_po["last_updated_time"] = df_po["last_updated_at"].dt.time - df_po["agreed_delivery_date"] = pd.to_datetime( - df_po["agreed_delivery_date"], format="%Y-%m-%d" - ) - df_po["agreed_payment_date"] = pd.to_datetime( - df_po["agreed_payment_date"], format="%Y-%m-%d" - ) - df_po.drop(labels=["created_at", "last_updated_at"], axis=1, inplace=True) + df_po = dict_of_df['purchase_order'] + df_po.index.name = 'purchase_record_id' + df_po['created_date'] = pd.to_datetime(df_po['created_at'],format='%Y-%m-%d') + df_po['created_time'] = pd.to_datetime(df_po['created_at'],format='%H-%M-%S') + df_po['last_updated_date'] = pd.to_datetime(df_po['last_updated'],format='%Y-%m-%d') + df_po['last_updated_time'] = pd.to_datetime(df_po['last_updated'],format='%H-%M-%S') + df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") + df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") + df_po.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_po.reset_index(inplace=True) return df_po - +#test passed def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = df_payment["created_at"].date() - df_payment["created_time"] = df_payment["created_at"].time - df_payment["last_updated_date"] = df_payment["last_updated"].date() - df_payment["last_updated_time"] = df_payment["last_updated"].time - df_payment["payment_date"] = pd.to_datetime( - df_payment["payment_date"], format="%Y-%m-%d" - ) - fact_payment = df_payment.loc[ - :, - [ - "payment_record_id", - "payment_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "transaction_id", - "counterparty_id", - "payment_amount", - "currency_id", - "payment_type_id", - "paid", - "payment_date", - ], - ] - return fact_payment - - -# test passed - - + df_payment["created_date"] = pd.to_datetime(df_payment["created_at"],format='%Y-%m-%d') + df_payment["created_time"] = pd.to_datetime(df_payment["created_at"],format='%H-%M-%S') + df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"],format='%Y-%m-%d') + df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"],format='%H-%M-%S') + df_payment['payment_date'] = pd.to_datetime(df_payment['payment_date'],format="%Y-%m-%d") + df_payment.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_payment.reset_index(inplace=True) + return df_payment + +#test passed def create_dim_transaction(dict_of_df): - df_transaction = dict_of_df["transaction"].drop( - labels=["created_at", "last_updated"], axis=1 - ) + df_transaction = dict_of_df["transaction"].drop(labels=['created_at', 'last_updated'], axis=1) return df_transaction - -# test passed +#test passed def create_dim_location(dict_of_df): - df_loc = ( - dict_of_df["address"] - .drop(labels=["created_at", "last_updated"], axis=1) - .rename(columns={"address_id": "location_id"}) - ) + df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}) return df_loc def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df["address"].add_prefix( - "counterparty_legal_", axis=1 - ) - df_cp = pd.merge( - dict_of_df["counterparty"], - df_prefixed_address, - left_on="legal_address_id", - right_on="counterparty_legal_address_id", - how="outer", - ) - df_cp.drop( - columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True - ) + df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) + df_cp = pd.merge(dict_of_df['counterparty'], + df_prefixed_address, + left_on="legal_address_id", + right_on="counterparty_legal_address_id", + how="outer") + df_cp.drop(columns=["legal_address_id","counterparty_legal_address_id"],inplace=True) return df_cp - -# test passed - - +#test passed def create_dim_date(dict_of_df): - fact_dfs = [ - create_fact_payment(dict_of_df), - create_fact_purchase_orders(dict_of_df), - create_fact_sales_order(dict_of_df), - ] - date_col_names = [ - col_name for col_name in list(fact_dfs[0].columns) if "date" in col_name - ] + fact_dfs = [create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df)] list_of_date_columns = [] for df in fact_dfs: + date_col_names = [col_name for col_name in list(df.columns) if 'date' in col_name] for col in date_col_names: list_of_date_columns.append(df[col]) - sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") - df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) + sr_date = pd.array(pd.concat(list_of_date_columns),dtype='datetime64[ns]') + df_date = pd.DataFrame(data=sr_date,columns=['date_id']) df_date.drop_duplicates(inplace=True) - df_date["year"] = df_date["date_id"].dt.year - df_date["month"] = df_date["date_id"].dt.month - df_date["day"] = df_date["date_id"].dt.day - df_date["day_of_week"] = df_date["date_id"].dt.dayofweek - df_date["day_name"] = df_date["date_id"].dt.day_name() - df_date["month_name"] = df_date["date_id"].dt.month_name() - df_date["quarter"] = df_date["date_id"].dt.quarter + df_date['year'] = df_date['date_id'].dt.year + df_date['month'] = df_date['date_id'].dt.month + df_date['day'] = df_date['date_id'].dt.day + df_date['day_of_week'] = df_date['date_id'].dt.dayofweek + df_date['day_name'] = df_date['date_id'].dt.day_name() + df_date['month_name'] = df_date['date_id'].dt.month_name() + df_date['quarter'] = df_date['date_id'].dt.quarter return df_date - -# tests passed +#tests passed def scrape_currency_names(): - response = requests.get("https://www.xe.com/currency/").content - soup = BeautifulSoup(response, "html.parser") - currency = [ - item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) - ] + response = requests.get('https://www.xe.com/currency/').content + soup = BeautifulSoup(response,'html.parser') + currency = [item.text for item in soup.findAll('a', attrs={'class' : "sc-299dec64-6 fZPTSw"})] sr = pd.Series(currency) - df_cur = sr.str.split(pat=" - ", expand=True).rename( - {0: "currency_code", 1: "currency_name"}, axis=1 - ) + df_cur = sr.str.split(pat=" - ",expand=True).rename({0:'currency_code',1:'currency_name'},axis=1) return df_cur +#tests passed +def create_dim_currency(dict_of_df,names=scrape_currency_names()): + df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1) + dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner') + return dim_cur + +#tests passed +def create_dim_payment_type(dict_of_df): + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + return dim_payment_type + +#tests passed +def create_dim_design(dict_of_df): + df_design = dict_of_df["design"] + dim_design = df_design.loc[:, ["design_id", "design_name", "file_name", "file_location"]] + return dim_design +#tests passed +def create_dim_staff(dict_of_df): + staff_department = pd.merge(dict_of_df["staff"], dict_of_df["department"], on='department_id', how="left") + dim_staff = staff_department.loc[:, ['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address']] + return dim_staff + + -# tests passed -def create_dim_currency(dict_of_df, names=scrape_currency_names()): - df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) - dim_cur = pd.merge( - df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" - ) - return dim_cur -# tests passed -def create_dim_payment_type(dict_of_df): - df_payment_type = dict_of_df["payment_type"] - dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] - return dim_payment_type -# tests passed -def create_dim_design(dict_of_df): - df_design = dict_of_df["design"] - dim_design = df_design.loc[ - :, ["design_id", "design_name", "file_name", "file_location"] - ] - return dim_design -# tests passed -def create_dim_staff(dict_of_df): - staff_department = pd.merge( - dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" - ) - dim_staff = staff_department.loc[ - :, - [ - "staff_id", - "first_name", - "last_name", - "department_name", - "location", - "email_address", - ], - ] - return dim_staff diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py new file mode 100644 index 0000000..8f32b1d --- /dev/null +++ b/tests/test_dataframes.py @@ -0,0 +1,144 @@ +from src.dataframes import * +import pandas as pd +from unittest.mock import patch +from datetime import datetime as dt + +class TestCreateDimDesign: + def test_dim_design_returns_dataframe(self): + d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + test_df = {"design": pd.DataFrame(data=d)} + result = create_dim_design(test_df) + assert isinstance(result, pd.DataFrame) + + def test_dim_design_returns_correct_columns_and_values(self): + d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + test_df = {"design": pd.DataFrame(data=d)} + result = create_dim_design(test_df) + d2 = {"design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"]} + expected_df = pd.DataFrame(data=d2) + expected_result = expected_df.copy() + assert result.equals(expected_result) + +class TestCreateDimStaff: + def test_dim_staff_returns_dataframe(self): + d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} + result = create_dim_staff(test_df) + assert isinstance(result, pd.DataFrame) + + def test_dim_staff_returns_correct_columns_and_values(self): + d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} + result = create_dim_staff(test_df) + expected_d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"]} + expected_df = pd.DataFrame(data=expected_d) + expected_result = expected_df.copy() + assert result.equals(expected_result) + +class TestCreatePaymentType: + def test_create_dim_payment_type_returns_correct_columns_and_values(self): + d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} + test_df = {"payment_type": pd.DataFrame(data=d)} + result = create_dim_payment_type(test_df) + expected_columns = ["payment_type_id", "payment_type_name"] + expected_d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} + expected_df = pd.DataFrame(data=expected_d) + assert isinstance(result, pd.DataFrame) + assert list(result.columns) == expected_columns + assert result.equals(expected_df) + +class TestCreateDimCounterparty: + + def test_create_dim_counterparty_type_returns_correct_columns_and_object(self): + data_l = pd.DataFrame(data={"counterparty_id": ["Hello", "Bye"], + "counterparty_legal_name": ["Hello", "Bye"], + "commercial_contact": ["Hello", "Bye"], + "legal_address_id": ["bond street", "regent street"]}) + data_a = pd.DataFrame(data={"address_id":["bond street", "regent street"], + "postcode":[98365,93753]}) + test_df = {"address": data_a,"counterparty":data_l} + result = create_dim_counterparty(test_df) + + expected_columns = ["counterparty_id", "counterparty_legal_name", + "commercial_contact", "counterparty_legal_postcode"] + print(data_l) + print(data_a) + assert isinstance(result, pd.DataFrame) + assert list(result.columns) == expected_columns + +class TestCreateDimCurrency: + + def test_dim_currency_returns_columns_and_values(self): + nones = [None,None,None] + d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"],"created_at":nones,"last_updated":nones} + test_df = {"currency": pd.DataFrame(data=d)} + scraper_output = pd.DataFrame({"currency_code":["RUS","USD","PHP","GBP","EUR"],"currency_name":["Rubble","US Dollar","Peso","Pound","Euro"]}) + result = create_dim_currency(test_df,names=scraper_output).sort_values(by="currency_code",axis=0) + expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} + expected_df = pd.DataFrame(data=expected_d).sort_values(by="currency_code",axis=0) + assert isinstance(result, pd.DataFrame) + assert result.equals(expected_df) + + def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self): + result = scrape_currency_names() + assert isinstance(result,pd.DataFrame) + assert list(result.columns) == ['currency_code', 'currency_name'] + +class TestCreateDimDate: + + def test_returns_required_columns(self): + df_one = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 5, 13),'not_dat':None},index=[0]) + df_two = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 9, 13)},index=[0]) + df_three = pd.DataFrame(data={'updated_date':dt(2022, 5, 17),'created_date':dt(2023, 5, 13)},index=[0]) + expected_df = pd.DataFrame(data= + [[dt(2020,5,17),2020,5,17,6,'Sunday','May',2], + [dt(2021,5,13),2021,5,13,3,'Thursday','May',2], + [dt(2021,9,13),2021,9,13,0,'Monday','September',3], + [dt(2022,5,17),2022,5,17,1,'Tuesday','May',2], + [dt(2023,5,13),2023,5,13,5,'Saturday','May',2]], + columns=['date_id','year','month','day','day_of_week','day_name','month_name','quarter']) + with patch("src.dataframes.create_fact_payment") as mock_fp: + with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo: + with patch("src.dataframes.create_fact_sales_order") as mock_fso: + mock_fp.return_value = df_one + mock_fpo.return_value = df_two + mock_fso.return_value = df_three + result = create_dim_date({'dum':0}) + result.reset_index(inplace=True,drop=True) + assert result.eq(expected_df, axis="columns").all(axis=None) + +class TestCreateDimLocation: + + def test_returns_correct_columns_lo(self): + dict_df = {'address':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], + columns=['created_at','last_updated','address_id','postal_code'])} + result = create_dim_location(dict_df) + assert list(result.columns) == ['location_id','postal_code'] + +class TestCreateDimTransaction: + def test_returns_correct_columns_tr(self): + dict_df = {'transaction':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], + columns=['created_at','last_updated','transaction_id','some_other_id'])} + result = create_dim_transaction(dict_df) + assert list(result.columns) == ['transaction_id','some_other_id'] + +class TestCreateFactPayment: + def test_returns_correct_columns_payment(self): + dict_df = {'payment':pd.DataFrame(data=[[dt(2020,5,17,6,15,20),dt(2020,5,20,8,19,30),1,'SE18 9QO','2020-7-16']], + columns=['created_at','last_updated','payment_id','some_other_id','payment_date'])} + expected_cols = ['payment_record_id','created_date','created_time','last_updated_date', + 'last_updated_time','payment_date','payment_id','some_other_id'] + result = create_fact_payment(dict_df) + assert isinstance(result,pd.DataFrame) + for col in list(result.columns): + assert col in expected_cols + for col in expected_cols: + if 'date' in col: + assert result[col].dtype == 'datetime64[ns]' + + \ No newline at end of file diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py deleted file mode 100644 index a245379..0000000 --- a/tests/test_fact_sales_order.py +++ /dev/null @@ -1,246 +0,0 @@ -from src.dataframes import * -import pandas as pd -from unittest.mock import patch -from datetime import datetime as dt - - -class TestCreateDimDesign: - def test_dim_design_returns_dataframe(self): - d = { - "test": ["Hello", "Bye"], - "design_id": ["Hello", "Bye"], - "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"], - "Hello": ["Hello", "Bye"], - } - test_df = {"design": pd.DataFrame(data=d)} - result = create_dim_design(test_df) - assert isinstance(result, pd.DataFrame) - - def test_dim_design_returns_correct_columns_and_values(self): - d = { - "test": ["Hello", "Bye"], - "design_id": ["Hello", "Bye"], - "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"], - "Hello": ["Hello", "Bye"], - } - test_df = {"design": pd.DataFrame(data=d)} - result = create_dim_design(test_df) - d2 = { - "design_id": ["Hello", "Bye"], - "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"], - } - expected_df = pd.DataFrame(data=d2) - expected_result = expected_df.copy() - assert result.equals(expected_result) - - -class TestCreateDimStaff: - def test_dim_staff_returns_dataframe(self): - d = { - "staff_id": ["Hello", "Bye"], - "first_name": ["Hello", "Bye"], - "last_name": ["Hello", "Bye"], - "department_id": ["Hello", "Bye"], - } - d2 = { - "department_name": ["Hello", "Bye"], - "location": ["Hello", "Bye"], - "email_address": ["Hello", "Bye"], - "department_id": ["Hello", "Bye"], - } - test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} - result = create_dim_staff(test_df) - assert isinstance(result, pd.DataFrame) - - def test_dim_staff_returns_correct_columns_and_values(self): - d = { - "staff_id": ["Hello", "Bye"], - "first_name": ["Hello", "Bye"], - "last_name": ["Hello", "Bye"], - "department_id": ["Hello", "Bye"], - } - d2 = { - "department_name": ["Hello", "Bye"], - "location": ["Hello", "Bye"], - "email_address": ["Hello", "Bye"], - "department_id": ["Hello", "Bye"], - } - test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} - result = create_dim_staff(test_df) - expected_d = { - "staff_id": ["Hello", "Bye"], - "first_name": ["Hello", "Bye"], - "last_name": ["Hello", "Bye"], - "department_name": ["Hello", "Bye"], - "location": ["Hello", "Bye"], - "email_address": ["Hello", "Bye"], - } - expected_df = pd.DataFrame(data=expected_d) - expected_result = expected_df.copy() - assert result.equals(expected_result) - - -class TestCreatePaymentType: - def test_create_dim_payment_type_returns_correct_columns_and_values(self): - d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} - test_df = {"payment_type": pd.DataFrame(data=d)} - result = create_dim_payment_type(test_df) - expected_columns = ["payment_type_id", "payment_type_name"] - expected_d = { - "payment_type_id": ["Hello", "Bye"], - "payment_type_name": ["Hello", "Bye"], - } - expected_df = pd.DataFrame(data=expected_d) - assert isinstance(result, pd.DataFrame) - assert list(result.columns) == expected_columns - assert result.equals(expected_df) - - -class TestCreateDimCounterparty: - def test_create_dim_counterparty_type_returns_correct_columns_and_object(self): - data_l = pd.DataFrame( - data={ - "counterparty_id": ["Hello", "Bye"], - "counterparty_legal_name": ["Hello", "Bye"], - "commercial_contact": ["Hello", "Bye"], - "legal_address_id": ["bond street", "regent street"], - } - ) - data_a = pd.DataFrame( - data={ - "address_id": ["bond street", "regent street"], - "postcode": [98365, 93753], - } - ) - test_df = {"address": data_a, "counterparty": data_l} - result = create_dim_counterparty(test_df) - - expected_columns = [ - "counterparty_id", - "counterparty_legal_name", - "commercial_contact", - "counterparty_legal_postcode", - ] - print(data_l) - print(data_a) - assert isinstance(result, pd.DataFrame) - assert list(result.columns) == expected_columns - - -class TestCreateDimCurrency: - def test_dim_currency_returns_columns_and_values(self): - nones = [None, None, None] - d = { - "currency_id": [1, 2, 3], - "currency_code": ["USD", "EUR", "GBP"], - "created_at": nones, - "last_updated": nones, - } - test_df = {"currency": pd.DataFrame(data=d)} - scraper_output = pd.DataFrame( - { - "currency_code": ["RUS", "USD", "PHP", "GBP", "EUR"], - "currency_name": ["Rubble", "US Dollar", "Peso", "Pound", "Euro"], - } - ) - result = create_dim_currency(test_df, names=scraper_output).sort_values( - by="currency_code", axis=0 - ) - expected_d = { - "currency_id": [1, 2, 3], - "currency_code": ["USD", "EUR", "GBP"], - "currency_name": ["US Dollar", "Euro", "Pound"], - } - expected_df = pd.DataFrame(data=expected_d).sort_values( - by="currency_code", axis=0 - ) - assert isinstance(result, pd.DataFrame) - assert result.equals(expected_df) - - def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self): - result = scrape_currency_names() - assert isinstance(result, pd.DataFrame) - assert list(result.columns) == ["currency_code", "currency_name"] - - -class TestCreateDimDate: - def test_returns_required_columns(self): - df_one = pd.DataFrame( - data={ - "updated_date": dt(2020, 5, 17), - "created_date": dt(2021, 5, 13), - "not_dat": None, - }, - index=[0], - ) - df_two = pd.DataFrame( - data={"updated_date": dt(2020, 5, 17), "created_date": dt(2021, 9, 13)}, - index=[0], - ) - df_three = pd.DataFrame( - data={"updated_date": dt(2022, 5, 17), "created_date": dt(2023, 5, 13)}, - index=[0], - ) - expected_df = pd.DataFrame( - data=[ - [dt(2020, 5, 17), 2020, 5, 17, 6, "Sunday", "May", 2], - [dt(2021, 5, 13), 2021, 5, 13, 3, "Thursday", "May", 2], - [dt(2021, 9, 13), 2021, 9, 13, 0, "Monday", "September", 3], - [dt(2022, 5, 17), 2022, 5, 17, 1, "Tuesday", "May", 2], - [dt(2023, 5, 13), 2023, 5, 13, 5, "Saturday", "May", 2], - ], - columns=[ - "date_id", - "year", - "month", - "day", - "day_of_week", - "day_name", - "month_name", - "quarter", - ], - ) - with patch("src.dataframes.create_fact_payment") as mock_fp: - with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo: - with patch("src.dataframes.create_fact_sales_order") as mock_fso: - mock_fp.return_value = df_one - mock_fpo.return_value = df_two - mock_fso.return_value = df_three - result = create_dim_date({"dum": 0}) - result.reset_index(inplace=True, drop=True) - assert result.eq(expected_df, axis="columns").all(axis=None) - - -class TestCreateDimLocation: - def test_returns_correct_columns_lo(self): - dict_df = { - "address": pd.DataFrame( - data=[["some_time", "some_other_time", 1, "SE18 9QO"]], - columns=["created_at", "last_updated", "address_id", "postal_code"], - ) - } - result = create_dim_location(dict_df) - assert list(result.columns) == ["location_id", "postal_code"] - - -class TestCreateDimTransaction: - def test_returns_correct_columns_tr(self): - dict_df = { - "transaction": pd.DataFrame( - data=[["some_time", "some_other_time", 1, "SE18 9QO"]], - columns=[ - "created_at", - "last_updated", - "transaction_id", - "some_other_id", - ], - ) - } - result = create_dim_transaction(dict_df) - assert list(result.columns) == ["transaction_id", "some_other_id"] -- cgit v1.2.3 From 8588d4b318d7732d33a59bc6c8b93870310668c5 Mon Sep 17 00:00:00 2001 From: Ang Bel Date: Tue, 27 Aug 2024 15:18:54 +0100 Subject: test: refactored fact functions with test passing --- src/dataframes.py | 24 ++++++++++++------------ tests/test_dataframes.py | 9 +++++++-- 2 files changed, 19 insertions(+), 14 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 41f39b8..1f445a4 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -20,10 +20,10 @@ import requests def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - df_sales["created_date"] = pd.to_datetime(df_sales["created_at"],format='%Y-%m-%d') - df_sales["created_time"] = pd.to_datetime(df_sales["created_at"],format='%H-%M-%S') - df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"],format='%Y-%m-%d') - df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"],format='%H-%M-%S') + df_sales["created_date"] = pd.to_datetime(df_sales["created_at"].dt.date,format='%Y-%m-%d') + df_sales["created_time"] = df_sales["created_at"].dt.floor('s').dt.time + df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"].dt.date,format='%Y-%m-%d') + df_sales["last_updated_time"] = df_sales["last_updated"].dt.floor('s').dt.time df_sales['agreed_delivery_date'] = pd.to_datetime(df_sales['agreed_delivery_date'],format="%Y-%m-%d") df_sales['agreed_payment_date'] = pd.to_datetime(df_sales['agreed_payment_date'],format="%Y-%m-%d") df_sales.drop(labels=['created_at','last_updated'],axis=1,inplace=True) @@ -34,10 +34,10 @@ def create_fact_sales_order(dict_of_df): def create_fact_purchase_orders(dict_of_df): df_po = dict_of_df['purchase_order'] df_po.index.name = 'purchase_record_id' - df_po['created_date'] = pd.to_datetime(df_po['created_at'],format='%Y-%m-%d') - df_po['created_time'] = pd.to_datetime(df_po['created_at'],format='%H-%M-%S') - df_po['last_updated_date'] = pd.to_datetime(df_po['last_updated'],format='%Y-%m-%d') - df_po['last_updated_time'] = pd.to_datetime(df_po['last_updated'],format='%H-%M-%S') + df_po['created_date'] = pd.to_datetime(df_po['created_at'].dt.date,format='%Y-%m-%d') + df_po['created_time'] = df_po['created_at'].dt.floor('s').dt.time + df_po['last_updated_date'] = pd.to_datetime(df_po['last_updated'].dt.date,format='%Y-%m-%d') + df_po['last_updated_time'] = df_po['last_updated'].dt.floor('s').dt.time df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") df_po.drop(labels=['created_at','last_updated'],axis=1,inplace=True) @@ -48,10 +48,10 @@ def create_fact_purchase_orders(dict_of_df): def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = pd.to_datetime(df_payment["created_at"],format='%Y-%m-%d') - df_payment["created_time"] = pd.to_datetime(df_payment["created_at"],format='%H-%M-%S') - df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"],format='%Y-%m-%d') - df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"],format='%H-%M-%S') + df_payment["created_date"] = pd.to_datetime(df_payment["created_at"].dt.date,format='%Y-%m-%d') + df_payment["created_time"] = df_payment["created_at"].dt.floor('s').dt.time + df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"].dt.date,format='%Y-%m-%d') + df_payment["last_updated_time"] = df_payment["last_updated"].dt.floor('s').dt.time df_payment['payment_date'] = pd.to_datetime(df_payment['payment_date'],format="%Y-%m-%d") df_payment.drop(labels=['created_at','last_updated'],axis=1,inplace=True) df_payment.reset_index(inplace=True) diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index 8f32b1d..70aefe8 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -129,7 +129,8 @@ class TestCreateDimTransaction: class TestCreateFactPayment: def test_returns_correct_columns_payment(self): - dict_df = {'payment':pd.DataFrame(data=[[dt(2020,5,17,6,15,20),dt(2020,5,20,8,19,30),1,'SE18 9QO','2020-7-16']], + dict_df = {'payment':pd.DataFrame(data=[[dt.strptime('2022-11-03 14:20:49.962846','%Y-%m-%d %H:%M:%S.%f'), + dt.strptime('2022-12-14 16:20:49.962194','%Y-%m-%d %H:%M:%S.%f'),1,'SE18 9QO','2020-07-16']], columns=['created_at','last_updated','payment_id','some_other_id','payment_date'])} expected_cols = ['payment_record_id','created_date','created_time','last_updated_date', 'last_updated_time','payment_date','payment_id','some_other_id'] @@ -138,7 +139,11 @@ class TestCreateFactPayment: for col in list(result.columns): assert col in expected_cols for col in expected_cols: - if 'date' in col: + if '_date' in col: + print(col) assert result[col].dtype == 'datetime64[ns]' + if '_time' in col: + print(col) + assert result[col].dtype == 'O' #<< O for object \ No newline at end of file -- cgit v1.2.3 From efab1eccd4e2f0a8069ff4f1c968807a9c1ce05f Mon Sep 17 00:00:00 2001 From: Ang Bel Date: Tue, 27 Aug 2024 17:00:04 +0100 Subject: test: transform refactoring - it now loads parquet files into s3 bucket --- src/dataframes.py | 32 ++++++++++++++++---------------- src/transform_lambda.py | 6 +++--- tests/test_dataframes.py | 10 +++------- 3 files changed, 22 insertions(+), 26 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 1f445a4..9d0f2ac 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -20,13 +20,13 @@ import requests def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - df_sales["created_date"] = pd.to_datetime(df_sales["created_at"].dt.date,format='%Y-%m-%d') - df_sales["created_time"] = df_sales["created_at"].dt.floor('s').dt.time - df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"].dt.date,format='%Y-%m-%d') - df_sales["last_updated_time"] = df_sales["last_updated"].dt.floor('s').dt.time + df_sales["created_date"] = df_sales["created_at"].astype('datetime64[ns]').dt.date + df_sales["created_time"] = df_sales["created_at"].astype('datetime64[ns]').dt.floor('s').dt.time + df_sales["last_updated_date"] = df_sales["last_updated"].astype('datetime64[ns]').dt.date + df_sales["last_updated_time"] = df_sales["last_updated"].astype('datetime64[ns]').dt.floor('s').dt.time df_sales['agreed_delivery_date'] = pd.to_datetime(df_sales['agreed_delivery_date'],format="%Y-%m-%d") df_sales['agreed_payment_date'] = pd.to_datetime(df_sales['agreed_payment_date'],format="%Y-%m-%d") - df_sales.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_sales = df_sales.drop(labels=['created_at','last_updated'],axis=1) df_sales.reset_index(inplace=True) return df_sales @@ -34,13 +34,13 @@ def create_fact_sales_order(dict_of_df): def create_fact_purchase_orders(dict_of_df): df_po = dict_of_df['purchase_order'] df_po.index.name = 'purchase_record_id' - df_po['created_date'] = pd.to_datetime(df_po['created_at'].dt.date,format='%Y-%m-%d') - df_po['created_time'] = df_po['created_at'].dt.floor('s').dt.time - df_po['last_updated_date'] = pd.to_datetime(df_po['last_updated'].dt.date,format='%Y-%m-%d') - df_po['last_updated_time'] = df_po['last_updated'].dt.floor('s').dt.time + df_po['created_date'] = df_po['created_at'].astype('datetime64[ns]').dt.date + df_po['created_time'] = df_po['created_at'].astype('datetime64[ns]').dt.floor('s').dt.time + df_po['last_updated_date'] = df_po['last_updated'].astype('datetime64[ns]').dt.date + df_po['last_updated_time'] = df_po['last_updated'].astype('datetime64[ns]').dt.floor('s').dt.time df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") - df_po.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_po = df_po.drop(labels=['created_at','last_updated'],axis=1) df_po.reset_index(inplace=True) return df_po @@ -48,12 +48,12 @@ def create_fact_purchase_orders(dict_of_df): def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = pd.to_datetime(df_payment["created_at"].dt.date,format='%Y-%m-%d') - df_payment["created_time"] = df_payment["created_at"].dt.floor('s').dt.time - df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"].dt.date,format='%Y-%m-%d') - df_payment["last_updated_time"] = df_payment["last_updated"].dt.floor('s').dt.time + df_payment["created_date"] = df_payment["created_at"].astype('datetime64[ns]').dt.date + df_payment["created_time"] = df_payment["created_at"].astype('datetime64[ns]').dt.floor('s').dt.time + df_payment["last_updated_date"] = df_payment["last_updated"].astype('datetime64[ns]').dt.date + df_payment["last_updated_time"] = df_payment["last_updated"].astype('datetime64[ns]').dt.floor('s').dt.time df_payment['payment_date'] = pd.to_datetime(df_payment['payment_date'],format="%Y-%m-%d") - df_payment.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_payment = df_payment.drop(labels=['created_at','last_updated'],axis=1) df_payment.reset_index(inplace=True) return df_payment @@ -83,7 +83,7 @@ def create_dim_date(dict_of_df): fact_dfs = [create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df)] list_of_date_columns = [] for df in fact_dfs: - date_col_names = [col_name for col_name in list(df.columns) if 'date' in col_name] + date_col_names = [col_name for col_name in list(df.columns) if '_date' in col_name] for col in date_col_names: list_of_date_columns.append(df[col]) sr_date = pd.array(pd.concat(list_of_date_columns),dtype='datetime64[ns]') diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 2cd9272..ccf90e5 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -117,7 +117,7 @@ def process_to_parquet_and_upload_to_s3( parquet_file = df.to_parquet( f"{table_name}.parquet", engine="pyarrow" ) # or fastparquet - client.upload_file(parquet_file, bucket, f"{table_name}.parquet") + client.upload_file(f"{table_name}.parquet", bucket, f"{table_name}.parquet") #changed parquet_file variable to the file name status["uploaded"].append(table_name) for table_name, df in mutable_df_dict.items(): @@ -127,7 +127,7 @@ def process_to_parquet_and_upload_to_s3( parquet_file = df.to_parquet( f"{table_name}.parquet", engine="pyarrow" ) # or fastparquet - client.upload_file(parquet_file, bucket, s3_key) + client.upload_file(f"{table_name}.parquet", bucket, s3_key) status["uploaded"].append(table_name) return status @@ -203,7 +203,7 @@ def list_existing_s3_files(bucket_name, client=boto3.client("s3")): existing_files = [obj["Key"] for obj in response["Contents"]] else: logger.error("The bucket is empty") - return None + return [] #changed from None to [] so it is an iterable except ClientError as e: logger.error(f"Error listing S3 objects: {e}") diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index 70aefe8..adbb5ed 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -139,11 +139,7 @@ class TestCreateFactPayment: for col in list(result.columns): assert col in expected_cols for col in expected_cols: - if '_date' in col: - print(col) - assert result[col].dtype == 'datetime64[ns]' - if '_time' in col: - print(col) - assert result[col].dtype == 'O' #<< O for object - + if '_date' or '_time' in col: + assert result[col].dtype == 'O' + \ No newline at end of file -- cgit v1.2.3 From 26902dc234c114382c2926923820c3537490c30e Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Tue, 27 Aug 2024 16:01:11 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 1a145a3 according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/101 --- src/dataframes.py | 236 ++++++++++++++++++++++++++------------- src/transform_lambda.py | 5 +- tests/test_dataframes.py | 282 +++++++++++++++++++++++++++++++++++------------ 3 files changed, 375 insertions(+), 148 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 9d0f2ac..f122368 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -2,7 +2,7 @@ import pandas as pd from bs4 import BeautifulSoup import requests -#Table names: +# Table names: # fact_sales_order # fact_purchase_orders # fact_payment @@ -16,133 +16,213 @@ import requests # dim_counterparty -#no test, same as fact_payment +# no test, same as fact_payment def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - df_sales["created_date"] = df_sales["created_at"].astype('datetime64[ns]').dt.date - df_sales["created_time"] = df_sales["created_at"].astype('datetime64[ns]').dt.floor('s').dt.time - df_sales["last_updated_date"] = df_sales["last_updated"].astype('datetime64[ns]').dt.date - df_sales["last_updated_time"] = df_sales["last_updated"].astype('datetime64[ns]').dt.floor('s').dt.time - df_sales['agreed_delivery_date'] = pd.to_datetime(df_sales['agreed_delivery_date'],format="%Y-%m-%d") - df_sales['agreed_payment_date'] = pd.to_datetime(df_sales['agreed_payment_date'],format="%Y-%m-%d") - df_sales = df_sales.drop(labels=['created_at','last_updated'],axis=1) + df_sales["created_date"] = df_sales["created_at"].astype("datetime64[ns]").dt.date + df_sales["created_time"] = ( + df_sales["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_sales["last_updated_date"] = ( + df_sales["last_updated"].astype("datetime64[ns]").dt.date + ) + df_sales["last_updated_time"] = ( + df_sales["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_sales["agreed_delivery_date"] = pd.to_datetime( + df_sales["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_sales["agreed_payment_date"] = pd.to_datetime( + df_sales["agreed_payment_date"], format="%Y-%m-%d" + ) + df_sales = df_sales.drop(labels=["created_at", "last_updated"], axis=1) df_sales.reset_index(inplace=True) return df_sales -#no test, same as fact_payment + +# no test, same as fact_payment + + def create_fact_purchase_orders(dict_of_df): - df_po = dict_of_df['purchase_order'] - df_po.index.name = 'purchase_record_id' - df_po['created_date'] = df_po['created_at'].astype('datetime64[ns]').dt.date - df_po['created_time'] = df_po['created_at'].astype('datetime64[ns]').dt.floor('s').dt.time - df_po['last_updated_date'] = df_po['last_updated'].astype('datetime64[ns]').dt.date - df_po['last_updated_time'] = df_po['last_updated'].astype('datetime64[ns]').dt.floor('s').dt.time - df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") - df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") - df_po = df_po.drop(labels=['created_at','last_updated'],axis=1) + df_po = dict_of_df["purchase_order"] + df_po.index.name = "purchase_record_id" + df_po["created_date"] = df_po["created_at"].astype("datetime64[ns]").dt.date + df_po["created_time"] = ( + df_po["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_po["last_updated_date"] = df_po["last_updated"].astype("datetime64[ns]").dt.date + df_po["last_updated_time"] = ( + df_po["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_po["agreed_delivery_date"] = pd.to_datetime( + df_po["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_po["agreed_payment_date"] = pd.to_datetime( + df_po["agreed_payment_date"], format="%Y-%m-%d" + ) + df_po = df_po.drop(labels=["created_at", "last_updated"], axis=1) df_po.reset_index(inplace=True) return df_po -#test passed + +# test passed + + def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = df_payment["created_at"].astype('datetime64[ns]').dt.date - df_payment["created_time"] = df_payment["created_at"].astype('datetime64[ns]').dt.floor('s').dt.time - df_payment["last_updated_date"] = df_payment["last_updated"].astype('datetime64[ns]').dt.date - df_payment["last_updated_time"] = df_payment["last_updated"].astype('datetime64[ns]').dt.floor('s').dt.time - df_payment['payment_date'] = pd.to_datetime(df_payment['payment_date'],format="%Y-%m-%d") - df_payment = df_payment.drop(labels=['created_at','last_updated'],axis=1) + df_payment["created_date"] = ( + df_payment["created_at"].astype("datetime64[ns]").dt.date + ) + df_payment["created_time"] = ( + df_payment["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_payment["last_updated_date"] = ( + df_payment["last_updated"].astype("datetime64[ns]").dt.date + ) + df_payment["last_updated_time"] = ( + df_payment["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_payment["payment_date"] = pd.to_datetime( + df_payment["payment_date"], format="%Y-%m-%d" + ) + df_payment = df_payment.drop(labels=["created_at", "last_updated"], axis=1) df_payment.reset_index(inplace=True) return df_payment -#test passed + +# test passed + + def create_dim_transaction(dict_of_df): - df_transaction = dict_of_df["transaction"].drop(labels=['created_at', 'last_updated'], axis=1) + df_transaction = dict_of_df["transaction"].drop( + labels=["created_at", "last_updated"], axis=1 + ) return df_transaction -#test passed + +# test passed + + def create_dim_location(dict_of_df): - df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}) + df_loc = ( + dict_of_df["address"] + .drop(labels=["created_at", "last_updated"], axis=1) + .rename(columns={"address_id": "location_id"}) + ) return df_loc def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) - df_cp = pd.merge(dict_of_df['counterparty'], - df_prefixed_address, - left_on="legal_address_id", - right_on="counterparty_legal_address_id", - how="outer") - df_cp.drop(columns=["legal_address_id","counterparty_legal_address_id"],inplace=True) + df_prefixed_address = dict_of_df["address"].add_prefix( + "counterparty_legal_", axis=1 + ) + df_cp = pd.merge( + dict_of_df["counterparty"], + df_prefixed_address, + left_on="legal_address_id", + right_on="counterparty_legal_address_id", + how="outer", + ) + df_cp.drop( + columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True + ) return df_cp -#test passed + +# test passed + + def create_dim_date(dict_of_df): - fact_dfs = [create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df)] + fact_dfs = [ + create_fact_payment(dict_of_df), + create_fact_purchase_orders(dict_of_df), + create_fact_sales_order(dict_of_df), + ] list_of_date_columns = [] for df in fact_dfs: - date_col_names = [col_name for col_name in list(df.columns) if '_date' in col_name] + date_col_names = [ + col_name for col_name in list(df.columns) if "_date" in col_name + ] for col in date_col_names: list_of_date_columns.append(df[col]) - sr_date = pd.array(pd.concat(list_of_date_columns),dtype='datetime64[ns]') - df_date = pd.DataFrame(data=sr_date,columns=['date_id']) + sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") + df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) df_date.drop_duplicates(inplace=True) - df_date['year'] = df_date['date_id'].dt.year - df_date['month'] = df_date['date_id'].dt.month - df_date['day'] = df_date['date_id'].dt.day - df_date['day_of_week'] = df_date['date_id'].dt.dayofweek - df_date['day_name'] = df_date['date_id'].dt.day_name() - df_date['month_name'] = df_date['date_id'].dt.month_name() - df_date['quarter'] = df_date['date_id'].dt.quarter + df_date["year"] = df_date["date_id"].dt.year + df_date["month"] = df_date["date_id"].dt.month + df_date["day"] = df_date["date_id"].dt.day + df_date["day_of_week"] = df_date["date_id"].dt.dayofweek + df_date["day_name"] = df_date["date_id"].dt.day_name() + df_date["month_name"] = df_date["date_id"].dt.month_name() + df_date["quarter"] = df_date["date_id"].dt.quarter return df_date -#tests passed -def scrape_currency_names(): - response = requests.get('https://www.xe.com/currency/').content - soup = BeautifulSoup(response,'html.parser') - currency = [item.text for item in soup.findAll('a', attrs={'class' : "sc-299dec64-6 fZPTSw"})] - sr = pd.Series(currency) - df_cur = sr.str.split(pat=" - ",expand=True).rename({0:'currency_code',1:'currency_name'},axis=1) - return df_cur - -#tests passed -def create_dim_currency(dict_of_df,names=scrape_currency_names()): - df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1) - dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner') - return dim_cur -#tests passed -def create_dim_payment_type(dict_of_df): - df_payment_type = dict_of_df["payment_type"] - dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] - return dim_payment_type +# tests passed -#tests passed -def create_dim_design(dict_of_df): - df_design = dict_of_df["design"] - dim_design = df_design.loc[:, ["design_id", "design_name", "file_name", "file_location"]] - return dim_design -#tests passed -def create_dim_staff(dict_of_df): - staff_department = pd.merge(dict_of_df["staff"], dict_of_df["department"], on='department_id', how="left") - dim_staff = staff_department.loc[:, ['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address']] - return dim_staff +def scrape_currency_names(): + response = requests.get("https://www.xe.com/currency/").content + soup = BeautifulSoup(response, "html.parser") + currency = [ + item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) + ] + sr = pd.Series(currency) + df_cur = sr.str.split(pat=" - ", expand=True).rename( + {0: "currency_code", 1: "currency_name"}, axis=1 + ) + return df_cur +# tests passed +def create_dim_currency(dict_of_df, names=scrape_currency_names()): + df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) + dim_cur = pd.merge( + df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" + ) + return dim_cur +# tests passed +def create_dim_payment_type(dict_of_df): + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + return dim_payment_type +# tests passed +def create_dim_design(dict_of_df): + df_design = dict_of_df["design"] + dim_design = df_design.loc[ + :, ["design_id", "design_name", "file_name", "file_location"] + ] + return dim_design +# tests passed +def create_dim_staff(dict_of_df): + staff_department = pd.merge( + dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" + ) + dim_staff = staff_department.loc[ + :, + [ + "staff_id", + "first_name", + "last_name", + "department_name", + "location", + "email_address", + ], + ] + return dim_staff diff --git a/src/transform_lambda.py b/src/transform_lambda.py index ccf90e5..93b2284 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -117,7 +117,8 @@ def process_to_parquet_and_upload_to_s3( parquet_file = df.to_parquet( f"{table_name}.parquet", engine="pyarrow" ) # or fastparquet - client.upload_file(f"{table_name}.parquet", bucket, f"{table_name}.parquet") #changed parquet_file variable to the file name + # changed parquet_file variable to the file name + client.upload_file(f"{table_name}.parquet", bucket, f"{table_name}.parquet") status["uploaded"].append(table_name) for table_name, df in mutable_df_dict.items(): @@ -203,7 +204,7 @@ def list_existing_s3_files(bucket_name, client=boto3.client("s3")): existing_files = [obj["Key"] for obj in response["Contents"]] else: logger.error("The bucket is empty") - return [] #changed from None to [] so it is an iterable + return [] # changed from None to [] so it is an iterable except ClientError as e: logger.error(f"Error listing S3 objects: {e}") diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index adbb5ed..c9ff43f 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -3,42 +3,88 @@ import pandas as pd from unittest.mock import patch from datetime import datetime as dt + class TestCreateDimDesign: def test_dim_design_returns_dataframe(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) assert isinstance(result, pd.DataFrame) def test_dim_design_returns_correct_columns_and_values(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) - d2 = {"design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"]} + d2 = { + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=d2) expected_result = expected_df.copy() assert result.equals(expected_result) + class TestCreateDimStaff: def test_dim_staff_returns_dataframe(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - assert isinstance(result, pd.DataFrame) + assert isinstance(result, pd.DataFrame) def test_dim_staff_returns_correct_columns_and_values(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - expected_d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"]} + expected_d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) expected_result = expected_df.copy() - assert result.equals(expected_result) + assert result.equals(expected_result) + class TestCreatePaymentType: def test_create_dim_payment_type_returns_correct_columns_and_values(self): @@ -46,100 +92,200 @@ class TestCreatePaymentType: test_df = {"payment_type": pd.DataFrame(data=d)} result = create_dim_payment_type(test_df) expected_columns = ["payment_type_id", "payment_type_name"] - expected_d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} + expected_d = { + "payment_type_id": ["Hello", "Bye"], + "payment_type_name": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns assert result.equals(expected_df) + class TestCreateDimCounterparty: - def test_create_dim_counterparty_type_returns_correct_columns_and_object(self): - data_l = pd.DataFrame(data={"counterparty_id": ["Hello", "Bye"], - "counterparty_legal_name": ["Hello", "Bye"], - "commercial_contact": ["Hello", "Bye"], - "legal_address_id": ["bond street", "regent street"]}) - data_a = pd.DataFrame(data={"address_id":["bond street", "regent street"], - "postcode":[98365,93753]}) - test_df = {"address": data_a,"counterparty":data_l} + data_l = pd.DataFrame( + data={ + "counterparty_id": ["Hello", "Bye"], + "counterparty_legal_name": ["Hello", "Bye"], + "commercial_contact": ["Hello", "Bye"], + "legal_address_id": ["bond street", "regent street"], + } + ) + data_a = pd.DataFrame( + data={ + "address_id": ["bond street", "regent street"], + "postcode": [98365, 93753], + } + ) + test_df = {"address": data_a, "counterparty": data_l} result = create_dim_counterparty(test_df) - expected_columns = ["counterparty_id", "counterparty_legal_name", - "commercial_contact", "counterparty_legal_postcode"] + expected_columns = [ + "counterparty_id", + "counterparty_legal_name", + "commercial_contact", + "counterparty_legal_postcode", + ] print(data_l) print(data_a) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns + class TestCreateDimCurrency: - def test_dim_currency_returns_columns_and_values(self): - nones = [None,None,None] - d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"],"created_at":nones,"last_updated":nones} + nones = [None, None, None] + d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "created_at": nones, + "last_updated": nones, + } test_df = {"currency": pd.DataFrame(data=d)} - scraper_output = pd.DataFrame({"currency_code":["RUS","USD","PHP","GBP","EUR"],"currency_name":["Rubble","US Dollar","Peso","Pound","Euro"]}) - result = create_dim_currency(test_df,names=scraper_output).sort_values(by="currency_code",axis=0) - expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} - expected_df = pd.DataFrame(data=expected_d).sort_values(by="currency_code",axis=0) - assert isinstance(result, pd.DataFrame) - assert result.equals(expected_df) + scraper_output = pd.DataFrame( + { + "currency_code": ["RUS", "USD", "PHP", "GBP", "EUR"], + "currency_name": ["Rubble", "US Dollar", "Peso", "Pound", "Euro"], + } + ) + result = create_dim_currency(test_df, names=scraper_output).sort_values( + by="currency_code", axis=0 + ) + expected_d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "currency_name": ["US Dollar", "Euro", "Pound"], + } + expected_df = pd.DataFrame(data=expected_d).sort_values( + by="currency_code", axis=0 + ) + assert isinstance(result, pd.DataFrame) + assert result.equals(expected_df) def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self): result = scrape_currency_names() - assert isinstance(result,pd.DataFrame) - assert list(result.columns) == ['currency_code', 'currency_name'] + assert isinstance(result, pd.DataFrame) + assert list(result.columns) == ["currency_code", "currency_name"] -class TestCreateDimDate: +class TestCreateDimDate: def test_returns_required_columns(self): - df_one = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 5, 13),'not_dat':None},index=[0]) - df_two = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 9, 13)},index=[0]) - df_three = pd.DataFrame(data={'updated_date':dt(2022, 5, 17),'created_date':dt(2023, 5, 13)},index=[0]) - expected_df = pd.DataFrame(data= - [[dt(2020,5,17),2020,5,17,6,'Sunday','May',2], - [dt(2021,5,13),2021,5,13,3,'Thursday','May',2], - [dt(2021,9,13),2021,9,13,0,'Monday','September',3], - [dt(2022,5,17),2022,5,17,1,'Tuesday','May',2], - [dt(2023,5,13),2023,5,13,5,'Saturday','May',2]], - columns=['date_id','year','month','day','day_of_week','day_name','month_name','quarter']) + df_one = pd.DataFrame( + data={ + "updated_date": dt(2020, 5, 17), + "created_date": dt(2021, 5, 13), + "not_dat": None, + }, + index=[0], + ) + df_two = pd.DataFrame( + data={"updated_date": dt(2020, 5, 17), "created_date": dt(2021, 9, 13)}, + index=[0], + ) + df_three = pd.DataFrame( + data={"updated_date": dt(2022, 5, 17), "created_date": dt(2023, 5, 13)}, + index=[0], + ) + expected_df = pd.DataFrame( + data=[ + [dt(2020, 5, 17), 2020, 5, 17, 6, "Sunday", "May", 2], + [dt(2021, 5, 13), 2021, 5, 13, 3, "Thursday", "May", 2], + [dt(2021, 9, 13), 2021, 9, 13, 0, "Monday", "September", 3], + [dt(2022, 5, 17), 2022, 5, 17, 1, "Tuesday", "May", 2], + [dt(2023, 5, 13), 2023, 5, 13, 5, "Saturday", "May", 2], + ], + columns=[ + "date_id", + "year", + "month", + "day", + "day_of_week", + "day_name", + "month_name", + "quarter", + ], + ) with patch("src.dataframes.create_fact_payment") as mock_fp: with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo: with patch("src.dataframes.create_fact_sales_order") as mock_fso: mock_fp.return_value = df_one mock_fpo.return_value = df_two mock_fso.return_value = df_three - result = create_dim_date({'dum':0}) - result.reset_index(inplace=True,drop=True) + result = create_dim_date({"dum": 0}) + result.reset_index(inplace=True, drop=True) assert result.eq(expected_df, axis="columns").all(axis=None) - -class TestCreateDimLocation: + +class TestCreateDimLocation: def test_returns_correct_columns_lo(self): - dict_df = {'address':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], - columns=['created_at','last_updated','address_id','postal_code'])} + dict_df = { + "address": pd.DataFrame( + data=[["some_time", "some_other_time", 1, "SE18 9QO"]], + columns=["created_at", "last_updated", "address_id", "postal_code"], + ) + } result = create_dim_location(dict_df) - assert list(result.columns) == ['location_id','postal_code'] - + assert list(result.columns) == ["location_id", "postal_code"] + + class TestCreateDimTransaction: - def test_returns_correct_columns_tr(self): - dict_df = {'transaction':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], - columns=['created_at','last_updated','transaction_id','some_other_id'])} + def test_returns_correct_columns_tr(self): + dict_df = { + "transaction": pd.DataFrame( + data=[["some_time", "some_other_time", 1, "SE18 9QO"]], + columns=[ + "created_at", + "last_updated", + "transaction_id", + "some_other_id", + ], + ) + } result = create_dim_transaction(dict_df) - assert list(result.columns) == ['transaction_id','some_other_id'] + assert list(result.columns) == ["transaction_id", "some_other_id"] + class TestCreateFactPayment: def test_returns_correct_columns_payment(self): - dict_df = {'payment':pd.DataFrame(data=[[dt.strptime('2022-11-03 14:20:49.962846','%Y-%m-%d %H:%M:%S.%f'), - dt.strptime('2022-12-14 16:20:49.962194','%Y-%m-%d %H:%M:%S.%f'),1,'SE18 9QO','2020-07-16']], - columns=['created_at','last_updated','payment_id','some_other_id','payment_date'])} - expected_cols = ['payment_record_id','created_date','created_time','last_updated_date', - 'last_updated_time','payment_date','payment_id','some_other_id'] + dict_df = { + "payment": pd.DataFrame( + data=[ + [ + dt.strptime( + "2022-11-03 14:20:49.962846", "%Y-%m-%d %H:%M:%S.%f" + ), + dt.strptime( + "2022-12-14 16:20:49.962194", "%Y-%m-%d %H:%M:%S.%f" + ), + 1, + "SE18 9QO", + "2020-07-16", + ] + ], + columns=[ + "created_at", + "last_updated", + "payment_id", + "some_other_id", + "payment_date", + ], + ) + } + expected_cols = [ + "payment_record_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "payment_date", + "payment_id", + "some_other_id", + ] result = create_fact_payment(dict_df) - assert isinstance(result,pd.DataFrame) + assert isinstance(result, pd.DataFrame) for col in list(result.columns): assert col in expected_cols for col in expected_cols: - if '_date' or '_time' in col: - assert result[col].dtype == 'O' - - \ No newline at end of file + if "_date" or "_time" in col: + assert result[col].dtype == "O" -- cgit v1.2.3 From f8988db9372802053db60e311960f5da4defba02 Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Tue, 27 Aug 2024 11:44:00 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in a05a371 according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/98 --- src/dataframes.py | 50 ++++++++++++++++++++++++++++++++++++++++++++++++ tests/test_dataframes.py | 13 +++++++++++++ 2 files changed, 63 insertions(+) diff --git a/src/dataframes.py b/src/dataframes.py index f122368..36361d2 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -20,6 +20,7 @@ import requests def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" +<<<<<<< HEAD df_sales["created_date"] = df_sales["created_at"].astype("datetime64[ns]").dt.date df_sales["created_time"] = ( df_sales["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time @@ -29,6 +30,15 @@ def create_fact_sales_order(dict_of_df): ) df_sales["last_updated_time"] = ( df_sales["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time +======= + df_sales["created_date"] = pd.to_datetime(df_sales["created_at"], format="%Y-%m-%d") + df_sales["created_time"] = pd.to_datetime(df_sales["created_at"], format="%H-%M-%S") + df_sales["last_updated_date"] = pd.to_datetime( + df_sales["last_updated"], format="%Y-%m-%d" + ) + df_sales["last_updated_time"] = pd.to_datetime( + df_sales["last_updated"], format="%H-%M-%S" +>>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) ) df_sales["agreed_delivery_date"] = pd.to_datetime( df_sales["agreed_delivery_date"], format="%Y-%m-%d" @@ -36,7 +46,11 @@ def create_fact_sales_order(dict_of_df): df_sales["agreed_payment_date"] = pd.to_datetime( df_sales["agreed_payment_date"], format="%Y-%m-%d" ) +<<<<<<< HEAD df_sales = df_sales.drop(labels=["created_at", "last_updated"], axis=1) +======= + df_sales.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) +>>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) df_sales.reset_index(inplace=True) return df_sales @@ -47,6 +61,7 @@ def create_fact_sales_order(dict_of_df): def create_fact_purchase_orders(dict_of_df): df_po = dict_of_df["purchase_order"] df_po.index.name = "purchase_record_id" +<<<<<<< HEAD df_po["created_date"] = df_po["created_at"].astype("datetime64[ns]").dt.date df_po["created_time"] = ( df_po["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time @@ -54,6 +69,15 @@ def create_fact_purchase_orders(dict_of_df): df_po["last_updated_date"] = df_po["last_updated"].astype("datetime64[ns]").dt.date df_po["last_updated_time"] = ( df_po["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time +======= + df_po["created_date"] = pd.to_datetime(df_po["created_at"], format="%Y-%m-%d") + df_po["created_time"] = pd.to_datetime(df_po["created_at"], format="%H-%M-%S") + df_po["last_updated_date"] = pd.to_datetime( + df_po["last_updated"], format="%Y-%m-%d" + ) + df_po["last_updated_time"] = pd.to_datetime( + df_po["last_updated"], format="%H-%M-%S" +>>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) ) df_po["agreed_delivery_date"] = pd.to_datetime( df_po["agreed_delivery_date"], format="%Y-%m-%d" @@ -61,7 +85,11 @@ def create_fact_purchase_orders(dict_of_df): df_po["agreed_payment_date"] = pd.to_datetime( df_po["agreed_payment_date"], format="%Y-%m-%d" ) +<<<<<<< HEAD df_po = df_po.drop(labels=["created_at", "last_updated"], axis=1) +======= + df_po.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) +>>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) df_po.reset_index(inplace=True) return df_po @@ -72,6 +100,7 @@ def create_fact_purchase_orders(dict_of_df): def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" +<<<<<<< HEAD df_payment["created_date"] = ( df_payment["created_at"].astype("datetime64[ns]").dt.date ) @@ -83,11 +112,28 @@ def create_fact_payment(dict_of_df): ) df_payment["last_updated_time"] = ( df_payment["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time +======= + df_payment["created_date"] = pd.to_datetime( + df_payment["created_at"], format="%Y-%m-%d" + ) + df_payment["created_time"] = pd.to_datetime( + df_payment["created_at"], format="%H-%M-%S" + ) + df_payment["last_updated_date"] = pd.to_datetime( + df_payment["last_updated"], format="%Y-%m-%d" + ) + df_payment["last_updated_time"] = pd.to_datetime( + df_payment["last_updated"], format="%H-%M-%S" +>>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) ) df_payment["payment_date"] = pd.to_datetime( df_payment["payment_date"], format="%Y-%m-%d" ) +<<<<<<< HEAD df_payment = df_payment.drop(labels=["created_at", "last_updated"], axis=1) +======= + df_payment.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) +>>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) df_payment.reset_index(inplace=True) return df_payment @@ -143,7 +189,11 @@ def create_dim_date(dict_of_df): list_of_date_columns = [] for df in fact_dfs: date_col_names = [ +<<<<<<< HEAD col_name for col_name in list(df.columns) if "_date" in col_name +======= + col_name for col_name in list(df.columns) if "date" in col_name +>>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) ] for col in date_col_names: list_of_date_columns.append(df[col]) diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index c9ff43f..cc133fe 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -252,6 +252,7 @@ class TestCreateFactPayment: "payment": pd.DataFrame( data=[ [ +<<<<<<< HEAD dt.strptime( "2022-11-03 14:20:49.962846", "%Y-%m-%d %H:%M:%S.%f" ), @@ -261,6 +262,13 @@ class TestCreateFactPayment: 1, "SE18 9QO", "2020-07-16", +======= + dt(2020, 5, 17, 6, 15, 20), + dt(2020, 5, 20, 8, 19, 30), + 1, + "SE18 9QO", + "2020-7-16", +>>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) ] ], columns=[ @@ -287,5 +295,10 @@ class TestCreateFactPayment: for col in list(result.columns): assert col in expected_cols for col in expected_cols: +<<<<<<< HEAD if "_date" or "_time" in col: assert result[col].dtype == "O" +======= + if "date" in col: + assert result[col].dtype == "datetime64[ns]" +>>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) -- cgit v1.2.3 From 102575af5e1ac3f12b3f7e1c459a3a06bc5ec80a Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 17:24:47 +0100 Subject: amend to inner join --- src/dataframes.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 36361d2..4b32b36 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -161,7 +161,7 @@ def create_dim_location(dict_of_df): def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df["address"].add_prefix( + df_prefixed_address = dict_of_df["address"].drop(labels=["created_at", "last_updated"], axis=1).add_prefix( "counterparty_legal_", axis=1 ) df_cp = pd.merge( @@ -169,10 +169,10 @@ def create_dim_counterparty(dict_of_df): df_prefixed_address, left_on="legal_address_id", right_on="counterparty_legal_address_id", - how="outer", + how="inner", ) df_cp.drop( - columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True + columns=["legal_address_id", "counterparty_legal_address_id", ], inplace=True ) return df_cp -- cgit v1.2.3 From 0915d4fe4e151d6b593467129b51a1322398fc04 Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 17:27:21 +0100 Subject: add json.loads --- src/load_lambda.py | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 9e15af3..7339ab9 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -64,7 +64,7 @@ def retrieve_secrets(client=None, secret_name=None): logger.error(f"Secret {secret_name} does not contain a SecretString") raise ValueError(f"Secret {secret_name} does not contain a SecretString") - return json.loads(get_secret_value_response["SecretString"]) + return get_secret_value_response["SecretString"] # connect to database, slightly different way of doing it, to allow manipulation through pandas @@ -72,10 +72,10 @@ def retrieve_secrets(client=None, secret_name=None): def connect_to_db_and_return_engine(sm_secret=None): if sm_secret is None: - sm_secret = retrieve_secrets() + sm_secret = json.loads(retrieve_secrets()) try: - secrets = json.loads(sm_secret) + secrets = sm_secret host = secrets["host"] port = secrets["port"] user = secrets["user"] @@ -171,13 +171,14 @@ def upload_dfs_to_database(): ] for file_name, df in dict_of_dfs.items(): + print(df) if file_name in immutable_df_dict: table_name = file_name.split(".")[0] + print(table_name, "<<<<<") try: df.to_sql( table_name, con=db_engine, - schema="project_team_2", if_exists="append", index=False, ) -- cgit v1.2.3 From 08c971f0e56d0896aa09200c26b5cfa53ff29ca1 Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 17:27:40 +0100 Subject: add json.loads to retrieve secrets --- tests/test_load_lambda.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 829b908..02cf2c0 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -79,14 +79,14 @@ class TestRetrieveSecrets: mock_sm_client.create_secret(Name=secret_name, SecretString=json.dumps(secret)) - result = retrieve_secrets(mock_sm_client, secret_name) + result = json.loads(retrieve_secrets(mock_sm_client, secret_name)) assert isinstance(result, dict) def test_retrieve_secrets_returns_correct_keys_and_values(self, mock_sm_client): secret_name = "test_secret" - result = retrieve_secrets(mock_sm_client, secret_name) + result = json.loads(retrieve_secrets(mock_sm_client, secret_name)) assert result["user"] == "test_user_id" assert result["password"] == "test_password" -- cgit v1.2.3 From 95935534931b5ff6e617ba74c86cb7a6718128e4 Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Wed, 28 Aug 2024 08:24:21 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 08c971f according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/102 --- src/dataframes.py | 182 ++++++++++++++++++++++++---------------------- tests/test_dataframes.py | 43 ++++++----- tests/test_load_lambda.py | 2 - 3 files changed, 123 insertions(+), 104 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 4b32b36..43facd6 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -20,8 +20,11 @@ import requests def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" -<<<<<<< HEAD - df_sales["created_date"] = df_sales["created_at"].astype("datetime64[ns]").dt.date + + +<< << << < HEAD + df_sales["created_date"] = df_sales["created_at"].astype( + "datetime64[ns]").dt.date df_sales["created_time"] = ( df_sales["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time ) @@ -30,27 +33,29 @@ def create_fact_sales_order(dict_of_df): ) df_sales["last_updated_time"] = ( df_sales["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time -======= - df_sales["created_date"] = pd.to_datetime(df_sales["created_at"], format="%Y-%m-%d") - df_sales["created_time"] = pd.to_datetime(df_sales["created_at"], format="%H-%M-%S") - df_sales["last_updated_date"] = pd.to_datetime( +== == == = + df_sales["created_date"]=pd.to_datetime( + df_sales["created_at"], format="%Y-%m-%d") + df_sales["created_time"]=pd.to_datetime( + df_sales["created_at"], format="%H-%M-%S") + df_sales["last_updated_date"]=pd.to_datetime( df_sales["last_updated"], format="%Y-%m-%d" ) - df_sales["last_updated_time"] = pd.to_datetime( + df_sales["last_updated_time"]=pd.to_datetime( df_sales["last_updated"], format="%H-%M-%S" ->>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) +>> >>>> > 5db3f61(style: format code with Autopep8, Black and Ruff Formatter) ) - df_sales["agreed_delivery_date"] = pd.to_datetime( + df_sales["agreed_delivery_date"]=pd.to_datetime( df_sales["agreed_delivery_date"], format="%Y-%m-%d" ) - df_sales["agreed_payment_date"] = pd.to_datetime( + df_sales["agreed_payment_date"]=pd.to_datetime( df_sales["agreed_payment_date"], format="%Y-%m-%d" ) -<<<<<<< HEAD - df_sales = df_sales.drop(labels=["created_at", "last_updated"], axis=1) -======= +<< << << < HEAD + df_sales=df_sales.drop(labels=["created_at", "last_updated"], axis=1) +== == == = df_sales.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) ->>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) +>> >>>> > 5db3f61(style: format code with Autopep8, Black and Ruff Formatter) df_sales.reset_index(inplace=True) return df_sales @@ -59,37 +64,40 @@ def create_fact_sales_order(dict_of_df): def create_fact_purchase_orders(dict_of_df): - df_po = dict_of_df["purchase_order"] - df_po.index.name = "purchase_record_id" -<<<<<<< HEAD - df_po["created_date"] = df_po["created_at"].astype("datetime64[ns]").dt.date - df_po["created_time"] = ( + df_po=dict_of_df["purchase_order"] + df_po.index.name="purchase_record_id" +<< << << < HEAD + df_po["created_date"]=df_po["created_at"].astype("datetime64[ns]").dt.date + df_po["created_time"]=( df_po["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time ) - df_po["last_updated_date"] = df_po["last_updated"].astype("datetime64[ns]").dt.date - df_po["last_updated_time"] = ( + df_po["last_updated_date"]=df_po["last_updated"].astype( + "datetime64[ns]").dt.date + df_po["last_updated_time"]=( df_po["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time -======= - df_po["created_date"] = pd.to_datetime(df_po["created_at"], format="%Y-%m-%d") - df_po["created_time"] = pd.to_datetime(df_po["created_at"], format="%H-%M-%S") - df_po["last_updated_date"] = pd.to_datetime( +== == == = + df_po["created_date"]=pd.to_datetime( + df_po["created_at"], format="%Y-%m-%d") + df_po["created_time"]=pd.to_datetime( + df_po["created_at"], format="%H-%M-%S") + df_po["last_updated_date"]=pd.to_datetime( df_po["last_updated"], format="%Y-%m-%d" ) - df_po["last_updated_time"] = pd.to_datetime( + df_po["last_updated_time"]=pd.to_datetime( df_po["last_updated"], format="%H-%M-%S" ->>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) +>> >>>> > 5db3f61(style: format code with Autopep8, Black and Ruff Formatter) ) - df_po["agreed_delivery_date"] = pd.to_datetime( + df_po["agreed_delivery_date"]=pd.to_datetime( df_po["agreed_delivery_date"], format="%Y-%m-%d" ) - df_po["agreed_payment_date"] = pd.to_datetime( + df_po["agreed_payment_date"]=pd.to_datetime( df_po["agreed_payment_date"], format="%Y-%m-%d" ) -<<<<<<< HEAD - df_po = df_po.drop(labels=["created_at", "last_updated"], axis=1) -======= +<< << << < HEAD + df_po=df_po.drop(labels=["created_at", "last_updated"], axis=1) +== == == = df_po.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) ->>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) +>> >>>> > 5db3f61(style: format code with Autopep8, Black and Ruff Formatter) df_po.reset_index(inplace=True) return df_po @@ -98,42 +106,44 @@ def create_fact_purchase_orders(dict_of_df): def create_fact_payment(dict_of_df): - df_payment = dict_of_df["payment"] - df_payment.index.name = "payment_record_id" -<<<<<<< HEAD - df_payment["created_date"] = ( + df_payment=dict_of_df["payment"] + df_payment.index.name="payment_record_id" +<< << << < HEAD + df_payment["created_date"]=( df_payment["created_at"].astype("datetime64[ns]").dt.date ) - df_payment["created_time"] = ( + df_payment["created_time"]=( df_payment["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time ) - df_payment["last_updated_date"] = ( + df_payment["last_updated_date"]=( df_payment["last_updated"].astype("datetime64[ns]").dt.date ) - df_payment["last_updated_time"] = ( - df_payment["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time -======= - df_payment["created_date"] = pd.to_datetime( + df_payment["last_updated_time"]=( + df_payment["last_updated"].astype( + "datetime64[ns]").dt.floor("s").dt.time +== == == = + df_payment["created_date"]=pd.to_datetime( df_payment["created_at"], format="%Y-%m-%d" ) - df_payment["created_time"] = pd.to_datetime( + df_payment["created_time"]=pd.to_datetime( df_payment["created_at"], format="%H-%M-%S" ) - df_payment["last_updated_date"] = pd.to_datetime( + df_payment["last_updated_date"]=pd.to_datetime( df_payment["last_updated"], format="%Y-%m-%d" ) - df_payment["last_updated_time"] = pd.to_datetime( + df_payment["last_updated_time"]=pd.to_datetime( df_payment["last_updated"], format="%H-%M-%S" ->>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) +>> >>>> > 5db3f61(style: format code with Autopep8, Black and Ruff Formatter) ) - df_payment["payment_date"] = pd.to_datetime( + df_payment["payment_date"]=pd.to_datetime( df_payment["payment_date"], format="%Y-%m-%d" ) -<<<<<<< HEAD - df_payment = df_payment.drop(labels=["created_at", "last_updated"], axis=1) -======= - df_payment.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) ->>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) +<< << << < HEAD + df_payment=df_payment.drop(labels=["created_at", "last_updated"], axis=1) +== == == = + df_payment.drop( + labels=["created_at", "last_updated"], axis=1, inplace=True) +>> >>>> > 5db3f61(style: format code with Autopep8, Black and Ruff Formatter) df_payment.reset_index(inplace=True) return df_payment @@ -142,7 +152,7 @@ def create_fact_payment(dict_of_df): def create_dim_transaction(dict_of_df): - df_transaction = dict_of_df["transaction"].drop( + df_transaction=dict_of_df["transaction"].drop( labels=["created_at", "last_updated"], axis=1 ) return df_transaction @@ -152,7 +162,7 @@ def create_dim_transaction(dict_of_df): def create_dim_location(dict_of_df): - df_loc = ( + df_loc=( dict_of_df["address"] .drop(labels=["created_at", "last_updated"], axis=1) .rename(columns={"address_id": "location_id"}) @@ -161,10 +171,10 @@ def create_dim_location(dict_of_df): def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df["address"].drop(labels=["created_at", "last_updated"], axis=1).add_prefix( + df_prefixed_address=dict_of_df["address"].drop(labels=["created_at", "last_updated"], axis=1).add_prefix( "counterparty_legal_", axis=1 ) - df_cp = pd.merge( + df_cp=pd.merge( dict_of_df["counterparty"], df_prefixed_address, left_on="legal_address_id", @@ -181,32 +191,32 @@ def create_dim_counterparty(dict_of_df): def create_dim_date(dict_of_df): - fact_dfs = [ + fact_dfs=[ create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df), ] - list_of_date_columns = [] + list_of_date_columns=[] for df in fact_dfs: - date_col_names = [ -<<<<<<< HEAD + date_col_names=[ +<< << << < HEAD col_name for col_name in list(df.columns) if "_date" in col_name -======= +== == == = col_name for col_name in list(df.columns) if "date" in col_name ->>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) +>> >>>> > 5db3f61(style: format code with Autopep8, Black and Ruff Formatter) ] for col in date_col_names: list_of_date_columns.append(df[col]) - sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") - df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) + sr_date=pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") + df_date=pd.DataFrame(data=sr_date, columns=["date_id"]) df_date.drop_duplicates(inplace=True) - df_date["year"] = df_date["date_id"].dt.year - df_date["month"] = df_date["date_id"].dt.month - df_date["day"] = df_date["date_id"].dt.day - df_date["day_of_week"] = df_date["date_id"].dt.dayofweek - df_date["day_name"] = df_date["date_id"].dt.day_name() - df_date["month_name"] = df_date["date_id"].dt.month_name() - df_date["quarter"] = df_date["date_id"].dt.quarter + df_date["year"]=df_date["date_id"].dt.year + df_date["month"]=df_date["date_id"].dt.month + df_date["day"]=df_date["date_id"].dt.day + df_date["day_of_week"]=df_date["date_id"].dt.dayofweek + df_date["day_name"]=df_date["date_id"].dt.day_name() + df_date["month_name"]=df_date["date_id"].dt.month_name() + df_date["quarter"]=df_date["date_id"].dt.quarter return df_date @@ -214,13 +224,13 @@ def create_dim_date(dict_of_df): def scrape_currency_names(): - response = requests.get("https://www.xe.com/currency/").content - soup = BeautifulSoup(response, "html.parser") - currency = [ + response=requests.get("https://www.xe.com/currency/").content + soup=BeautifulSoup(response, "html.parser") + currency=[ item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) ] - sr = pd.Series(currency) - df_cur = sr.str.split(pat=" - ", expand=True).rename( + sr=pd.Series(currency) + df_cur=sr.str.split(pat=" - ", expand=True).rename( {0: "currency_code", 1: "currency_name"}, axis=1 ) return df_cur @@ -230,8 +240,9 @@ def scrape_currency_names(): def create_dim_currency(dict_of_df, names=scrape_currency_names()): - df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) - dim_cur = pd.merge( + df_cur=dict_of_df["currency"].drop( + labels=["created_at", "last_updated"], axis=1) + dim_cur=pd.merge( df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" ) return dim_cur @@ -241,8 +252,9 @@ def create_dim_currency(dict_of_df, names=scrape_currency_names()): def create_dim_payment_type(dict_of_df): - df_payment_type = dict_of_df["payment_type"] - dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + df_payment_type=dict_of_df["payment_type"] + dim_payment_type=df_payment_type.loc[:, [ + "payment_type_id", "payment_type_name"]] return dim_payment_type @@ -250,8 +262,8 @@ def create_dim_payment_type(dict_of_df): def create_dim_design(dict_of_df): - df_design = dict_of_df["design"] - dim_design = df_design.loc[ + df_design=dict_of_df["design"] + dim_design=df_design.loc[ :, ["design_id", "design_name", "file_name", "file_location"] ] return dim_design @@ -261,10 +273,10 @@ def create_dim_design(dict_of_df): def create_dim_staff(dict_of_df): - staff_department = pd.merge( + staff_department=pd.merge( dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" ) - dim_staff = staff_department.loc[ + dim_staff=staff_department.loc[ :, [ "staff_id", diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index cc133fe..785a3fd 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -54,7 +54,8 @@ class TestCreateDimStaff: "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"], } - test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} + test_df = {"staff": pd.DataFrame( + data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) assert isinstance(result, pd.DataFrame) @@ -71,7 +72,8 @@ class TestCreateDimStaff: "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"], } - test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} + test_df = {"staff": pd.DataFrame( + data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) expected_d = { "staff_id": ["Hello", "Bye"], @@ -88,7 +90,8 @@ class TestCreateDimStaff: class TestCreatePaymentType: def test_create_dim_payment_type_returns_correct_columns_and_values(self): - d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} + d = {"payment_type_id": ["Hello", "Bye"], + "payment_type_name": ["Hello", "Bye"]} test_df = {"payment_type": pd.DataFrame(data=d)} result = create_dim_payment_type(test_df) expected_columns = ["payment_type_id", "payment_type_name"] @@ -180,11 +183,13 @@ class TestCreateDimDate: index=[0], ) df_two = pd.DataFrame( - data={"updated_date": dt(2020, 5, 17), "created_date": dt(2021, 9, 13)}, + data={"updated_date": dt(2020, 5, 17), + "created_date": dt(2021, 9, 13)}, index=[0], ) df_three = pd.DataFrame( - data={"updated_date": dt(2022, 5, 17), "created_date": dt(2023, 5, 13)}, + data={"updated_date": dt(2022, 5, 17), + "created_date": dt(2023, 5, 13)}, index=[0], ) expected_df = pd.DataFrame( @@ -214,7 +219,8 @@ class TestCreateDimDate: mock_fso.return_value = df_three result = create_dim_date({"dum": 0}) result.reset_index(inplace=True, drop=True) - assert result.eq(expected_df, axis="columns").all(axis=None) + assert result.eq( + expected_df, axis="columns").all(axis=None) class TestCreateDimLocation: @@ -222,7 +228,8 @@ class TestCreateDimLocation: dict_df = { "address": pd.DataFrame( data=[["some_time", "some_other_time", 1, "SE18 9QO"]], - columns=["created_at", "last_updated", "address_id", "postal_code"], + columns=["created_at", "last_updated", + "address_id", "postal_code"], ) } result = create_dim_location(dict_df) @@ -252,7 +259,7 @@ class TestCreateFactPayment: "payment": pd.DataFrame( data=[ [ -<<<<<<< HEAD + << << << < HEAD dt.strptime( "2022-11-03 14:20:49.962846", "%Y-%m-%d %H:%M:%S.%f" ), @@ -262,13 +269,13 @@ class TestCreateFactPayment: 1, "SE18 9QO", "2020-07-16", -======= + == == === dt(2020, 5, 17, 6, 15, 20), dt(2020, 5, 20, 8, 19, 30), 1, "SE18 9QO", "2020-7-16", ->>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) + >>>>>> > 5db3f61(style: format code with Autopep8, Black and Ruff Formatter) ] ], columns=[ @@ -295,10 +302,12 @@ class TestCreateFactPayment: for col in list(result.columns): assert col in expected_cols for col in expected_cols: -<<<<<<< HEAD - if "_date" or "_time" in col: - assert result[col].dtype == "O" -======= - if "date" in col: - assert result[col].dtype == "datetime64[ns]" ->>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) + + +<< << << < HEAD +if "_date" or "_time" in col: + assert result[col].dtype == "O" +== == == = +if "date" in col: + assert result[col].dtype == "datetime64[ns]" +>>>>>> > 5db3f61(style: format code with Autopep8, Black and Ruff Formatter) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 02cf2c0..65106f7 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -62,8 +62,6 @@ class TestLambdaHandler: assert result == {"error"} - - class TestRetrieveSecrets: def test_retrieve_secrets_returns_dictionary(self, mock_sm_client): secret = { -- cgit v1.2.3 From 4bd3f408a185d16f9580294755621156ad850ab4 Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Wed, 28 Aug 2024 08:36:33 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in d0b0fa9 according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/102 --- src/dataframes.py | 118 +++++++++++++++++++++++------------------------ tests/test_dataframes.py | 2 - 2 files changed, 59 insertions(+), 61 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index ab32fff..2a46bd6 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -20,9 +20,8 @@ import requests def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - - df_sales["created_date"] = df_sales["created_at"].astype( - "datetime64[ns]").dt.date + + df_sales["created_date"] = df_sales["created_at"].astype("datetime64[ns]").dt.date df_sales["created_time"] = ( df_sales["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time ) @@ -32,13 +31,13 @@ def create_fact_sales_order(dict_of_df): df_sales["last_updated_time"] = ( df_sales["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time ) - df_sales["agreed_delivery_date"]=pd.to_datetime( + df_sales["agreed_delivery_date"] = pd.to_datetime( df_sales["agreed_delivery_date"], format="%Y-%m-%d" ) - df_sales["agreed_payment_date"]=pd.to_datetime( + df_sales["agreed_payment_date"] = pd.to_datetime( df_sales["agreed_payment_date"], format="%Y-%m-%d" ) - df_sales=df_sales.drop(labels=["created_at", "last_updated"], axis=1) + df_sales = df_sales.drop(labels=["created_at", "last_updated"], axis=1) df_sales.reset_index(inplace=True) return df_sales @@ -68,25 +67,23 @@ def create_fact_sales_order(dict_of_df): def create_fact_purchase_orders(dict_of_df): - df_po=dict_of_df["purchase_order"] - df_po.index.name="purchase_record_id" - df_po["created_date"]=df_po["created_at"].astype("datetime64[ns]").dt.date - df_po["created_time"]=( + df_po = dict_of_df["purchase_order"] + df_po.index.name = "purchase_record_id" + df_po["created_date"] = df_po["created_at"].astype("datetime64[ns]").dt.date + df_po["created_time"] = ( df_po["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time ) - df_po["last_updated_date"]=df_po["last_updated"].astype( - "datetime64[ns]").dt.date - df_po["last_updated_time"]=( + df_po["last_updated_date"] = df_po["last_updated"].astype("datetime64[ns]").dt.date + df_po["last_updated_time"] = ( df_po["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time - ) - df_po["agreed_delivery_date"]=pd.to_datetime( + df_po["agreed_delivery_date"] = pd.to_datetime( df_po["agreed_delivery_date"], format="%Y-%m-%d" ) - df_po["agreed_payment_date"]=pd.to_datetime( + df_po["agreed_payment_date"] = pd.to_datetime( df_po["agreed_payment_date"], format="%Y-%m-%d" ) - df_po=df_po.drop(labels=["created_at", "last_updated"], axis=1) + df_po = df_po.drop(labels=["created_at", "last_updated"], axis=1) df_po.reset_index(inplace=True) return df_po @@ -95,26 +92,25 @@ def create_fact_purchase_orders(dict_of_df): def create_fact_payment(dict_of_df): - df_payment=dict_of_df["payment"] - df_payment.index.name="payment_record_id" - df_payment["created_date"]=( + df_payment = dict_of_df["payment"] + df_payment.index.name = "payment_record_id" + df_payment["created_date"] = ( df_payment["created_at"].astype("datetime64[ns]").dt.date ) - df_payment["created_time"]=( + df_payment["created_time"] = ( df_payment["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time ) - df_payment["last_updated_date"]=( + df_payment["last_updated_date"] = ( df_payment["last_updated"].astype("datetime64[ns]").dt.date ) - df_payment["last_updated_time"]=( - df_payment["last_updated"].astype( - "datetime64[ns]").dt.floor("s").dt.time + df_payment["last_updated_time"] = ( + df_payment["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time ) - df_payment["payment_date"]=pd.to_datetime( + df_payment["payment_date"] = pd.to_datetime( df_payment["payment_date"], format="%Y-%m-%d" ) - df_payment=df_payment.drop(labels=["created_at", "last_updated"], axis=1) - + df_payment = df_payment.drop(labels=["created_at", "last_updated"], axis=1) + df_payment.reset_index(inplace=True) return df_payment @@ -123,7 +119,7 @@ def create_fact_payment(dict_of_df): def create_dim_transaction(dict_of_df): - df_transaction=dict_of_df["transaction"].drop( + df_transaction = dict_of_df["transaction"].drop( labels=["created_at", "last_updated"], axis=1 ) return df_transaction @@ -133,7 +129,7 @@ def create_dim_transaction(dict_of_df): def create_dim_location(dict_of_df): - df_loc=( + df_loc = ( dict_of_df["address"] .drop(labels=["created_at", "last_updated"], axis=1) .rename(columns={"address_id": "location_id"}) @@ -142,10 +138,12 @@ def create_dim_location(dict_of_df): def create_dim_counterparty(dict_of_df): - df_prefixed_address=dict_of_df["address"].drop(labels=["created_at", "last_updated"], axis=1).add_prefix( - "counterparty_legal_", axis=1 + df_prefixed_address = ( + dict_of_df["address"] + .drop(labels=["created_at", "last_updated"], axis=1) + .add_prefix("counterparty_legal_", axis=1) ) - df_cp=pd.merge( + df_cp = pd.merge( dict_of_df["counterparty"], df_prefixed_address, left_on="legal_address_id", @@ -153,7 +151,11 @@ def create_dim_counterparty(dict_of_df): how="inner", ) df_cp.drop( - columns=["legal_address_id", "counterparty_legal_address_id", ], inplace=True + columns=[ + "legal_address_id", + "counterparty_legal_address_id", + ], + inplace=True, ) return df_cp @@ -162,7 +164,7 @@ def create_dim_counterparty(dict_of_df): def create_dim_date(dict_of_df): - fact_dfs=[ + fact_dfs = [ create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df), @@ -174,16 +176,16 @@ def create_dim_date(dict_of_df): ] for col in date_col_names: list_of_date_columns.append(df[col]) - sr_date=pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") - df_date=pd.DataFrame(data=sr_date, columns=["date_id"]) + sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") + df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) df_date.drop_duplicates(inplace=True) - df_date["year"]=df_date["date_id"].dt.year - df_date["month"]=df_date["date_id"].dt.month - df_date["day"]=df_date["date_id"].dt.day - df_date["day_of_week"]=df_date["date_id"].dt.dayofweek - df_date["day_name"]=df_date["date_id"].dt.day_name() - df_date["month_name"]=df_date["date_id"].dt.month_name() - df_date["quarter"]=df_date["date_id"].dt.quarter + df_date["year"] = df_date["date_id"].dt.year + df_date["month"] = df_date["date_id"].dt.month + df_date["day"] = df_date["date_id"].dt.day + df_date["day_of_week"] = df_date["date_id"].dt.dayofweek + df_date["day_name"] = df_date["date_id"].dt.day_name() + df_date["month_name"] = df_date["date_id"].dt.month_name() + df_date["quarter"] = df_date["date_id"].dt.quarter return df_date @@ -191,13 +193,13 @@ def create_dim_date(dict_of_df): def scrape_currency_names(): - response=requests.get("https://www.xe.com/currency/").content - soup=BeautifulSoup(response, "html.parser") - currency=[ + response = requests.get("https://www.xe.com/currency/").content + soup = BeautifulSoup(response, "html.parser") + currency = [ item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) ] - sr=pd.Series(currency) - df_cur=sr.str.split(pat=" - ", expand=True).rename( + sr = pd.Series(currency) + df_cur = sr.str.split(pat=" - ", expand=True).rename( {0: "currency_code", 1: "currency_name"}, axis=1 ) return df_cur @@ -207,9 +209,8 @@ def scrape_currency_names(): def create_dim_currency(dict_of_df, names=scrape_currency_names()): - df_cur=dict_of_df["currency"].drop( - labels=["created_at", "last_updated"], axis=1) - dim_cur=pd.merge( + df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) + dim_cur = pd.merge( df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" ) return dim_cur @@ -219,9 +220,8 @@ def create_dim_currency(dict_of_df, names=scrape_currency_names()): def create_dim_payment_type(dict_of_df): - df_payment_type=dict_of_df["payment_type"] - dim_payment_type=df_payment_type.loc[:, [ - "payment_type_id", "payment_type_name"]] + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] return dim_payment_type @@ -229,8 +229,8 @@ def create_dim_payment_type(dict_of_df): def create_dim_design(dict_of_df): - df_design=dict_of_df["design"] - dim_design=df_design.loc[ + df_design = dict_of_df["design"] + dim_design = df_design.loc[ :, ["design_id", "design_name", "file_name", "file_location"] ] return dim_design @@ -240,10 +240,10 @@ def create_dim_design(dict_of_df): def create_dim_staff(dict_of_df): - staff_department=pd.merge( + staff_department = pd.merge( dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" ) - dim_staff=staff_department.loc[ + dim_staff = staff_department.loc[ :, [ "staff_id", diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index ff282eb..ea7bad1 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -227,7 +227,6 @@ class TestCreateDimDate: expected_df, axis="columns").all(axis=None) - class TestCreateDimLocation: def test_returns_correct_columns_lo(self): dict_df = { @@ -302,6 +301,5 @@ class TestCreateFactPayment: for col in expected_cols: - if "_date" or "_time" in col: assert result[col].dtype == "O" -- cgit v1.2.3 From 03787e3aabc5bc516bb7bfcc3831a74681932c36 Mon Sep 17 00:00:00 2001 From: HastarTara Date: Wed, 28 Aug 2024 09:48:07 +0100 Subject: moved extract_l & dataframes into own directory in src --- src/dataframes.py | 228 ------------------------------- src/transform_lambda.py | 217 ----------------------------- src/transform_lambda/dataframes.py | 228 +++++++++++++++++++++++++++++++ src/transform_lambda/transform_lambda.py | 217 +++++++++++++++++++++++++++++ 4 files changed, 445 insertions(+), 445 deletions(-) delete mode 100644 src/dataframes.py delete mode 100644 src/transform_lambda.py create mode 100644 src/transform_lambda/dataframes.py create mode 100644 src/transform_lambda/transform_lambda.py diff --git a/src/dataframes.py b/src/dataframes.py deleted file mode 100644 index f122368..0000000 --- a/src/dataframes.py +++ /dev/null @@ -1,228 +0,0 @@ -import pandas as pd -from bs4 import BeautifulSoup -import requests - -# Table names: -# fact_sales_order -# fact_purchase_orders -# fact_payment -# dim_transaction -# dim_staff -# dim_payment_type -# dim_location -# dim_design -# dim_date -# dim_currency -# dim_counterparty - - -# no test, same as fact_payment -def create_fact_sales_order(dict_of_df): - df_sales = dict_of_df["sales_order"] - df_sales.index.name = "sales_record_id" - df_sales["created_date"] = df_sales["created_at"].astype("datetime64[ns]").dt.date - df_sales["created_time"] = ( - df_sales["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time - ) - df_sales["last_updated_date"] = ( - df_sales["last_updated"].astype("datetime64[ns]").dt.date - ) - df_sales["last_updated_time"] = ( - df_sales["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time - ) - df_sales["agreed_delivery_date"] = pd.to_datetime( - df_sales["agreed_delivery_date"], format="%Y-%m-%d" - ) - df_sales["agreed_payment_date"] = pd.to_datetime( - df_sales["agreed_payment_date"], format="%Y-%m-%d" - ) - df_sales = df_sales.drop(labels=["created_at", "last_updated"], axis=1) - df_sales.reset_index(inplace=True) - return df_sales - - -# no test, same as fact_payment - - -def create_fact_purchase_orders(dict_of_df): - df_po = dict_of_df["purchase_order"] - df_po.index.name = "purchase_record_id" - df_po["created_date"] = df_po["created_at"].astype("datetime64[ns]").dt.date - df_po["created_time"] = ( - df_po["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time - ) - df_po["last_updated_date"] = df_po["last_updated"].astype("datetime64[ns]").dt.date - df_po["last_updated_time"] = ( - df_po["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time - ) - df_po["agreed_delivery_date"] = pd.to_datetime( - df_po["agreed_delivery_date"], format="%Y-%m-%d" - ) - df_po["agreed_payment_date"] = pd.to_datetime( - df_po["agreed_payment_date"], format="%Y-%m-%d" - ) - df_po = df_po.drop(labels=["created_at", "last_updated"], axis=1) - df_po.reset_index(inplace=True) - return df_po - - -# test passed - - -def create_fact_payment(dict_of_df): - df_payment = dict_of_df["payment"] - df_payment.index.name = "payment_record_id" - df_payment["created_date"] = ( - df_payment["created_at"].astype("datetime64[ns]").dt.date - ) - df_payment["created_time"] = ( - df_payment["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time - ) - df_payment["last_updated_date"] = ( - df_payment["last_updated"].astype("datetime64[ns]").dt.date - ) - df_payment["last_updated_time"] = ( - df_payment["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time - ) - df_payment["payment_date"] = pd.to_datetime( - df_payment["payment_date"], format="%Y-%m-%d" - ) - df_payment = df_payment.drop(labels=["created_at", "last_updated"], axis=1) - df_payment.reset_index(inplace=True) - return df_payment - - -# test passed - - -def create_dim_transaction(dict_of_df): - df_transaction = dict_of_df["transaction"].drop( - labels=["created_at", "last_updated"], axis=1 - ) - return df_transaction - - -# test passed - - -def create_dim_location(dict_of_df): - df_loc = ( - dict_of_df["address"] - .drop(labels=["created_at", "last_updated"], axis=1) - .rename(columns={"address_id": "location_id"}) - ) - return df_loc - - -def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df["address"].add_prefix( - "counterparty_legal_", axis=1 - ) - df_cp = pd.merge( - dict_of_df["counterparty"], - df_prefixed_address, - left_on="legal_address_id", - right_on="counterparty_legal_address_id", - how="outer", - ) - df_cp.drop( - columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True - ) - return df_cp - - -# test passed - - -def create_dim_date(dict_of_df): - fact_dfs = [ - create_fact_payment(dict_of_df), - create_fact_purchase_orders(dict_of_df), - create_fact_sales_order(dict_of_df), - ] - list_of_date_columns = [] - for df in fact_dfs: - date_col_names = [ - col_name for col_name in list(df.columns) if "_date" in col_name - ] - for col in date_col_names: - list_of_date_columns.append(df[col]) - sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") - df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) - df_date.drop_duplicates(inplace=True) - df_date["year"] = df_date["date_id"].dt.year - df_date["month"] = df_date["date_id"].dt.month - df_date["day"] = df_date["date_id"].dt.day - df_date["day_of_week"] = df_date["date_id"].dt.dayofweek - df_date["day_name"] = df_date["date_id"].dt.day_name() - df_date["month_name"] = df_date["date_id"].dt.month_name() - df_date["quarter"] = df_date["date_id"].dt.quarter - return df_date - - -# tests passed - - -def scrape_currency_names(): - response = requests.get("https://www.xe.com/currency/").content - soup = BeautifulSoup(response, "html.parser") - currency = [ - item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) - ] - sr = pd.Series(currency) - df_cur = sr.str.split(pat=" - ", expand=True).rename( - {0: "currency_code", 1: "currency_name"}, axis=1 - ) - return df_cur - - -# tests passed - - -def create_dim_currency(dict_of_df, names=scrape_currency_names()): - df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) - dim_cur = pd.merge( - df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" - ) - return dim_cur - - -# tests passed - - -def create_dim_payment_type(dict_of_df): - df_payment_type = dict_of_df["payment_type"] - dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] - return dim_payment_type - - -# tests passed - - -def create_dim_design(dict_of_df): - df_design = dict_of_df["design"] - dim_design = df_design.loc[ - :, ["design_id", "design_name", "file_name", "file_location"] - ] - return dim_design - - -# tests passed - - -def create_dim_staff(dict_of_df): - staff_department = pd.merge( - dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" - ) - dim_staff = staff_department.loc[ - :, - [ - "staff_id", - "first_name", - "last_name", - "department_name", - "location", - "email_address", - ], - ] - return dim_staff diff --git a/src/transform_lambda.py b/src/transform_lambda.py deleted file mode 100644 index 93b2284..0000000 --- a/src/transform_lambda.py +++ /dev/null @@ -1,217 +0,0 @@ -import json -import boto3 -import re -import logging -import pandas as pd -import pyarrow as pa -import pyarrow.parquet as pq -from dataframes import * -from botocore.exceptions import ClientError -from pg8000.native import Connection, InterfaceError -from datetime import datetime - - -class DBConnectionException(Exception): - """Wraps pg8000.native Error or DatabaseError.""" - - def __init__(self, e): - """Initialise with provided error message.""" - self.message = str(e) - super().__init__(self.message) - - -logger = logging.getLogger(__name__) - -logging.basicConfig( - format="{asctime} - {levelname} - {message}", - style="{", - datefmt="%Y-%m-%d %H:%M", - level=logging.DEBUG, -) - -logging.getLogger("botocore").setLevel(logging.WARNING) - -TABLES = [ - "sales_order", - "transaction", - "payment", - "counterparty", - "address", - "staff", - "purchase_order", - "department", - "currency", - "design", - "payment_type", -] - - -def lambda_handler(event, context): - db = None - - try: - db = connect_to_database() - bucket = bucket_name("transform") - - existing_s3_files = list_existing_s3_files(bucket) - - dict_of_df = read_from_s3_subfolder_to_df( - TABLES, bucket_name("extract"), client=boto3.client("s3") - ) - - immutable_df_dict = { - "dim_counterparty": create_dim_counterparty(dict_of_df), - "dim_date": create_dim_date(dict_of_df), - "dim_location": create_dim_location(dict_of_df), - "dim_staff": create_dim_staff(dict_of_df), - "dim_design": create_dim_design(dict_of_df), - } - - mutable_df_dict = { - "fact_sales_order": create_fact_sales_order(dict_of_df), - "fact_purchase_order": create_fact_purchase_orders(dict_of_df), - "fact_payment": create_fact_payment(dict_of_df), - "dim_currency": create_dim_currency(dict_of_df), - } - - status = process_to_parquet_and_upload_to_s3( - existing_s3_files, immutable_df_dict, mutable_df_dict, bucket - ) - - if not status["uploaded"]: - logger.info("No dataframes written to the bucket.") - return { - "statusCode": 204, - "body": json.dumps("No files where uploaded."), - } - - return { - "statusCode": 200, - "body": json.dumps( - f"""Parquet files processed for {', '.join(status['uploaded'])} and uploaded successfully.{ - 'The following tables were not uploaded: '+', '.join([status['not_uploaded']]) if status['not_uploaded'] else ''}""" - ), - } - - except Exception as e: - logger.error(f"Error: {e}", exc_info=True) - return {"statusCode": 500, "body": json.dumps("Internal server error.")} - finally: - if db: - db.close() - - -def process_to_parquet_and_upload_to_s3( - existing_s3_files, - immutable_df_dict, - mutable_df_dict, - bucket, - client=boto3.client("s3"), -): - status = {"uploaded": [], "not_uploaded": []} - - for table_name, df in immutable_df_dict.items(): - if table_name in existing_s3_files: - status["not_uploaded"].append(table_name) - else: - parquet_file = df.to_parquet( - f"{table_name}.parquet", engine="pyarrow" - ) # or fastparquet - # changed parquet_file variable to the file name - client.upload_file(f"{table_name}.parquet", bucket, f"{table_name}.parquet") - status["uploaded"].append(table_name) - - for table_name, df in mutable_df_dict.items(): - s3_key = datetime.strftime( - datetime.today(), f"{table_name}/%Y/%m/%d/{table_name}_%H:%M:%S.parquet" - ) - parquet_file = df.to_parquet( - f"{table_name}.parquet", engine="pyarrow" - ) # or fastparquet - client.upload_file(f"{table_name}.parquet", bucket, s3_key) - status["uploaded"].append(table_name) - - return status - - -def retrieve_secrets(): - secret_name = "bentley-secrets" - region_name = "eu-west-2" - - # Create a Secrets Manager client - session = boto3.session.Session() - client = session.client(service_name="secretsmanager", region_name=region_name) - - try: - get_secret_value_response = client.get_secret_value(SecretId=secret_name) - except ClientError as e: - logger.error(f"Failed to retrieve secret {secret_name}: {str(e)}") - raise e - except KeyError: - logger.error(f"Secret {secret_name} does not contain a SecretString") - raise ValueError(f"Secret {secret_name} does not contain a SecretString") - - return get_secret_value_response["SecretString"] - - -def connect_to_database() -> Connection: - try: - secrets = json.loads(retrieve_secrets()) - host = secrets["host"] - port = secrets["port"] - user = secrets["user"] - password = secrets["password"] - database = secrets["database"] - - return Connection( - database=database, user=user, password=password, host=host, port=port - ) - except InterfaceError as i: - logger.error(f"Interface error: {i}") - raise DBConnectionException("Failed to connect to database") - - -def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client("s3")): - table_dfs = {} - for table in tables: - response = client.list_objects_v2(Bucket=bucket, Prefix=table) - list_of_keys = [ - "s3://" + bucket + "/" + object["Key"] for object in response["Contents"] - ] - list_of_df = [pd.read_csv(key) for key in list_of_keys] - table_dfs[table] = pd.concat(list_of_df) - return table_dfs - - -def bucket_name(bucket_prefix, client=boto3.client("s3")): - response = client.list_buckets() - bucket_filter = [ - bucket["Name"] - for bucket in response["Buckets"] - if bucket_prefix in bucket["Name"] - ] - - return bucket_filter[0] - - -def list_existing_s3_files(bucket_name, client=boto3.client("s3")): - logging.info("Listing existing S3 files") - - try: - response = client.list_objects_v2(Bucket=bucket_name) - - if "Contents" in response: - existing_files = [obj["Key"] for obj in response["Contents"]] - else: - logger.error("The bucket is empty") - return [] # changed from None to [] so it is an iterable - - except ClientError as e: - logger.error(f"Error listing S3 objects: {e}") - raise e - - return existing_files - - -if __name__ == "__main__": - lambda_handler({}, "") diff --git a/src/transform_lambda/dataframes.py b/src/transform_lambda/dataframes.py new file mode 100644 index 0000000..f122368 --- /dev/null +++ b/src/transform_lambda/dataframes.py @@ -0,0 +1,228 @@ +import pandas as pd +from bs4 import BeautifulSoup +import requests + +# Table names: +# fact_sales_order +# fact_purchase_orders +# fact_payment +# dim_transaction +# dim_staff +# dim_payment_type +# dim_location +# dim_design +# dim_date +# dim_currency +# dim_counterparty + + +# no test, same as fact_payment +def create_fact_sales_order(dict_of_df): + df_sales = dict_of_df["sales_order"] + df_sales.index.name = "sales_record_id" + df_sales["created_date"] = df_sales["created_at"].astype("datetime64[ns]").dt.date + df_sales["created_time"] = ( + df_sales["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_sales["last_updated_date"] = ( + df_sales["last_updated"].astype("datetime64[ns]").dt.date + ) + df_sales["last_updated_time"] = ( + df_sales["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_sales["agreed_delivery_date"] = pd.to_datetime( + df_sales["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_sales["agreed_payment_date"] = pd.to_datetime( + df_sales["agreed_payment_date"], format="%Y-%m-%d" + ) + df_sales = df_sales.drop(labels=["created_at", "last_updated"], axis=1) + df_sales.reset_index(inplace=True) + return df_sales + + +# no test, same as fact_payment + + +def create_fact_purchase_orders(dict_of_df): + df_po = dict_of_df["purchase_order"] + df_po.index.name = "purchase_record_id" + df_po["created_date"] = df_po["created_at"].astype("datetime64[ns]").dt.date + df_po["created_time"] = ( + df_po["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_po["last_updated_date"] = df_po["last_updated"].astype("datetime64[ns]").dt.date + df_po["last_updated_time"] = ( + df_po["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_po["agreed_delivery_date"] = pd.to_datetime( + df_po["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_po["agreed_payment_date"] = pd.to_datetime( + df_po["agreed_payment_date"], format="%Y-%m-%d" + ) + df_po = df_po.drop(labels=["created_at", "last_updated"], axis=1) + df_po.reset_index(inplace=True) + return df_po + + +# test passed + + +def create_fact_payment(dict_of_df): + df_payment = dict_of_df["payment"] + df_payment.index.name = "payment_record_id" + df_payment["created_date"] = ( + df_payment["created_at"].astype("datetime64[ns]").dt.date + ) + df_payment["created_time"] = ( + df_payment["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_payment["last_updated_date"] = ( + df_payment["last_updated"].astype("datetime64[ns]").dt.date + ) + df_payment["last_updated_time"] = ( + df_payment["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_payment["payment_date"] = pd.to_datetime( + df_payment["payment_date"], format="%Y-%m-%d" + ) + df_payment = df_payment.drop(labels=["created_at", "last_updated"], axis=1) + df_payment.reset_index(inplace=True) + return df_payment + + +# test passed + + +def create_dim_transaction(dict_of_df): + df_transaction = dict_of_df["transaction"].drop( + labels=["created_at", "last_updated"], axis=1 + ) + return df_transaction + + +# test passed + + +def create_dim_location(dict_of_df): + df_loc = ( + dict_of_df["address"] + .drop(labels=["created_at", "last_updated"], axis=1) + .rename(columns={"address_id": "location_id"}) + ) + return df_loc + + +def create_dim_counterparty(dict_of_df): + df_prefixed_address = dict_of_df["address"].add_prefix( + "counterparty_legal_", axis=1 + ) + df_cp = pd.merge( + dict_of_df["counterparty"], + df_prefixed_address, + left_on="legal_address_id", + right_on="counterparty_legal_address_id", + how="outer", + ) + df_cp.drop( + columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True + ) + return df_cp + + +# test passed + + +def create_dim_date(dict_of_df): + fact_dfs = [ + create_fact_payment(dict_of_df), + create_fact_purchase_orders(dict_of_df), + create_fact_sales_order(dict_of_df), + ] + list_of_date_columns = [] + for df in fact_dfs: + date_col_names = [ + col_name for col_name in list(df.columns) if "_date" in col_name + ] + for col in date_col_names: + list_of_date_columns.append(df[col]) + sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") + df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) + df_date.drop_duplicates(inplace=True) + df_date["year"] = df_date["date_id"].dt.year + df_date["month"] = df_date["date_id"].dt.month + df_date["day"] = df_date["date_id"].dt.day + df_date["day_of_week"] = df_date["date_id"].dt.dayofweek + df_date["day_name"] = df_date["date_id"].dt.day_name() + df_date["month_name"] = df_date["date_id"].dt.month_name() + df_date["quarter"] = df_date["date_id"].dt.quarter + return df_date + + +# tests passed + + +def scrape_currency_names(): + response = requests.get("https://www.xe.com/currency/").content + soup = BeautifulSoup(response, "html.parser") + currency = [ + item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) + ] + sr = pd.Series(currency) + df_cur = sr.str.split(pat=" - ", expand=True).rename( + {0: "currency_code", 1: "currency_name"}, axis=1 + ) + return df_cur + + +# tests passed + + +def create_dim_currency(dict_of_df, names=scrape_currency_names()): + df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) + dim_cur = pd.merge( + df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" + ) + return dim_cur + + +# tests passed + + +def create_dim_payment_type(dict_of_df): + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + return dim_payment_type + + +# tests passed + + +def create_dim_design(dict_of_df): + df_design = dict_of_df["design"] + dim_design = df_design.loc[ + :, ["design_id", "design_name", "file_name", "file_location"] + ] + return dim_design + + +# tests passed + + +def create_dim_staff(dict_of_df): + staff_department = pd.merge( + dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" + ) + dim_staff = staff_department.loc[ + :, + [ + "staff_id", + "first_name", + "last_name", + "department_name", + "location", + "email_address", + ], + ] + return dim_staff diff --git a/src/transform_lambda/transform_lambda.py b/src/transform_lambda/transform_lambda.py new file mode 100644 index 0000000..93b2284 --- /dev/null +++ b/src/transform_lambda/transform_lambda.py @@ -0,0 +1,217 @@ +import json +import boto3 +import re +import logging +import pandas as pd +import pyarrow as pa +import pyarrow.parquet as pq +from dataframes import * +from botocore.exceptions import ClientError +from pg8000.native import Connection, InterfaceError +from datetime import datetime + + +class DBConnectionException(Exception): + """Wraps pg8000.native Error or DatabaseError.""" + + def __init__(self, e): + """Initialise with provided error message.""" + self.message = str(e) + super().__init__(self.message) + + +logger = logging.getLogger(__name__) + +logging.basicConfig( + format="{asctime} - {levelname} - {message}", + style="{", + datefmt="%Y-%m-%d %H:%M", + level=logging.DEBUG, +) + +logging.getLogger("botocore").setLevel(logging.WARNING) + +TABLES = [ + "sales_order", + "transaction", + "payment", + "counterparty", + "address", + "staff", + "purchase_order", + "department", + "currency", + "design", + "payment_type", +] + + +def lambda_handler(event, context): + db = None + + try: + db = connect_to_database() + bucket = bucket_name("transform") + + existing_s3_files = list_existing_s3_files(bucket) + + dict_of_df = read_from_s3_subfolder_to_df( + TABLES, bucket_name("extract"), client=boto3.client("s3") + ) + + immutable_df_dict = { + "dim_counterparty": create_dim_counterparty(dict_of_df), + "dim_date": create_dim_date(dict_of_df), + "dim_location": create_dim_location(dict_of_df), + "dim_staff": create_dim_staff(dict_of_df), + "dim_design": create_dim_design(dict_of_df), + } + + mutable_df_dict = { + "fact_sales_order": create_fact_sales_order(dict_of_df), + "fact_purchase_order": create_fact_purchase_orders(dict_of_df), + "fact_payment": create_fact_payment(dict_of_df), + "dim_currency": create_dim_currency(dict_of_df), + } + + status = process_to_parquet_and_upload_to_s3( + existing_s3_files, immutable_df_dict, mutable_df_dict, bucket + ) + + if not status["uploaded"]: + logger.info("No dataframes written to the bucket.") + return { + "statusCode": 204, + "body": json.dumps("No files where uploaded."), + } + + return { + "statusCode": 200, + "body": json.dumps( + f"""Parquet files processed for {', '.join(status['uploaded'])} and uploaded successfully.{ + 'The following tables were not uploaded: '+', '.join([status['not_uploaded']]) if status['not_uploaded'] else ''}""" + ), + } + + except Exception as e: + logger.error(f"Error: {e}", exc_info=True) + return {"statusCode": 500, "body": json.dumps("Internal server error.")} + finally: + if db: + db.close() + + +def process_to_parquet_and_upload_to_s3( + existing_s3_files, + immutable_df_dict, + mutable_df_dict, + bucket, + client=boto3.client("s3"), +): + status = {"uploaded": [], "not_uploaded": []} + + for table_name, df in immutable_df_dict.items(): + if table_name in existing_s3_files: + status["not_uploaded"].append(table_name) + else: + parquet_file = df.to_parquet( + f"{table_name}.parquet", engine="pyarrow" + ) # or fastparquet + # changed parquet_file variable to the file name + client.upload_file(f"{table_name}.parquet", bucket, f"{table_name}.parquet") + status["uploaded"].append(table_name) + + for table_name, df in mutable_df_dict.items(): + s3_key = datetime.strftime( + datetime.today(), f"{table_name}/%Y/%m/%d/{table_name}_%H:%M:%S.parquet" + ) + parquet_file = df.to_parquet( + f"{table_name}.parquet", engine="pyarrow" + ) # or fastparquet + client.upload_file(f"{table_name}.parquet", bucket, s3_key) + status["uploaded"].append(table_name) + + return status + + +def retrieve_secrets(): + secret_name = "bentley-secrets" + region_name = "eu-west-2" + + # Create a Secrets Manager client + session = boto3.session.Session() + client = session.client(service_name="secretsmanager", region_name=region_name) + + try: + get_secret_value_response = client.get_secret_value(SecretId=secret_name) + except ClientError as e: + logger.error(f"Failed to retrieve secret {secret_name}: {str(e)}") + raise e + except KeyError: + logger.error(f"Secret {secret_name} does not contain a SecretString") + raise ValueError(f"Secret {secret_name} does not contain a SecretString") + + return get_secret_value_response["SecretString"] + + +def connect_to_database() -> Connection: + try: + secrets = json.loads(retrieve_secrets()) + host = secrets["host"] + port = secrets["port"] + user = secrets["user"] + password = secrets["password"] + database = secrets["database"] + + return Connection( + database=database, user=user, password=password, host=host, port=port + ) + except InterfaceError as i: + logger.error(f"Interface error: {i}") + raise DBConnectionException("Failed to connect to database") + + +def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client("s3")): + table_dfs = {} + for table in tables: + response = client.list_objects_v2(Bucket=bucket, Prefix=table) + list_of_keys = [ + "s3://" + bucket + "/" + object["Key"] for object in response["Contents"] + ] + list_of_df = [pd.read_csv(key) for key in list_of_keys] + table_dfs[table] = pd.concat(list_of_df) + return table_dfs + + +def bucket_name(bucket_prefix, client=boto3.client("s3")): + response = client.list_buckets() + bucket_filter = [ + bucket["Name"] + for bucket in response["Buckets"] + if bucket_prefix in bucket["Name"] + ] + + return bucket_filter[0] + + +def list_existing_s3_files(bucket_name, client=boto3.client("s3")): + logging.info("Listing existing S3 files") + + try: + response = client.list_objects_v2(Bucket=bucket_name) + + if "Contents" in response: + existing_files = [obj["Key"] for obj in response["Contents"]] + else: + logger.error("The bucket is empty") + return [] # changed from None to [] so it is an iterable + + except ClientError as e: + logger.error(f"Error listing S3 objects: {e}") + raise e + + return existing_files + + +if __name__ == "__main__": + lambda_handler({}, "") -- cgit v1.2.3 From 553c24060a9a4224efceec5d27c0e6083bca4b98 Mon Sep 17 00:00:00 2001 From: HastarTara Date: Wed, 28 Aug 2024 10:46:17 +0100 Subject: work on lambda handler dirctory config --- terraform/lambda.tf | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/terraform/lambda.tf b/terraform/lambda.tf index d33a6c9..6e5000a 100644 --- a/terraform/lambda.tf +++ b/terraform/lambda.tf @@ -87,6 +87,13 @@ data "archive_file" "transform_lambda_zip" { type = "zip" source_file = "${path.module}/../src/transform_lambda.py" output_path = "${path.module}/../transform_function.zip" + + +data "archive_file" "transform_lambda_zip" { + type = "zip" + source_dir = "../src/transform_lambda" + output_path = "../transform_lambda.zip" +} } resource "aws_s3_object" "transform_lambda_code" { bucket = aws_s3_bucket.lambda_code_bucket.bucket -- cgit v1.2.3 From 05e39b418ea6991e87adedc979c887ae4e72edc3 Mon Sep 17 00:00:00 2001 From: HastarTara Date: Wed, 28 Aug 2024 10:47:43 +0100 Subject: work on lambda handler dirctory config 2 --- terraform/lambda.tf | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/terraform/lambda.tf b/terraform/lambda.tf index 6e5000a..5f4a58e 100644 --- a/terraform/lambda.tf +++ b/terraform/lambda.tf @@ -83,18 +83,13 @@ resource "aws_lambda_function" "extract_lambda" { # Transform Lambda Function # ############################# -data "archive_file" "transform_lambda_zip" { - type = "zip" - source_file = "${path.module}/../src/transform_lambda.py" - output_path = "${path.module}/../transform_function.zip" - data "archive_file" "transform_lambda_zip" { type = "zip" - source_dir = "../src/transform_lambda" - output_path = "../transform_lambda.zip" -} + source_dir = "${path.module}../src/transform_lambda" + output_path = "${path.module}../transform_lambda.zip" } + resource "aws_s3_object" "transform_lambda_code" { bucket = aws_s3_bucket.lambda_code_bucket.bucket key = "${var.transform_lambda_name}/transform_function.zip" -- cgit v1.2.3 From 3f24ec753902feecec4c17e2877e19853bde1bb2 Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Wed, 28 Aug 2024 09:59:43 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in ad357ff according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/105 --- src/transform_lambda.py | 40 +++++++++++------------ tests/test_transform_lambda.py | 73 +++++++++++++++++++++--------------------- 2 files changed, 55 insertions(+), 58 deletions(-) diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 9830e0f..3b1e9e6 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -11,6 +11,7 @@ from pg8000.native import Connection, InterfaceError from datetime import datetime import io + class DBConnectionException(Exception): """Wraps pg8000.native Error or DatabaseError.""" @@ -108,7 +109,7 @@ def process_to_parquet_and_upload_to_s3( immutable_df_dict, mutable_df_dict, bucket, - client=boto3.client("s3") + client=boto3.client("s3"), ): status = {"uploaded": [], "not_uploaded": []} @@ -117,13 +118,14 @@ def process_to_parquet_and_upload_to_s3( status["not_uploaded"].append(table_name) else: parquet_buffer = io.BytesIO() - - df.to_parquet(parquet_buffer, engine="pyarrow") # or engine="fastparquet" - + + # or engine="fastparquet" + df.to_parquet(parquet_buffer, engine="pyarrow") + parquet_buffer.seek(0) - + client.upload_fileobj(parquet_buffer, bucket, f"{table_name}.parquet") - + status["uploaded"].append(table_name) # for table_name, df in mutable_df_dict.items(): @@ -188,23 +190,17 @@ def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client("s3")): return table_dfs - - def bucket_name(bucket_prefix, client=boto3.client("s3")): - - response = client.list_buckets() - bucket_filter = [ - bucket["Name"] - for bucket in response["Buckets"] - if bucket_prefix in bucket["Name"] - ] - if not bucket_filter: - raise ValueError(f"No bucket found with prefix: {bucket_prefix}") - - return bucket_filter[0] - - - + response = client.list_buckets() + bucket_filter = [ + bucket["Name"] + for bucket in response["Buckets"] + if bucket_prefix in bucket["Name"] + ] + if not bucket_filter: + raise ValueError(f"No bucket found with prefix: {bucket_prefix}") + + return bucket_filter[0] def list_existing_s3_files(bucket_name, client=boto3.client("s3")): diff --git a/tests/test_transform_lambda.py b/tests/test_transform_lambda.py index b4836c2..6cf3a09 100644 --- a/tests/test_transform_lambda.py +++ b/tests/test_transform_lambda.py @@ -1,7 +1,8 @@ from src.transform_lambda import ( read_from_s3_subfolder_to_df, list_existing_s3_files, - bucket_name, process_to_parquet_and_upload_to_s3 + bucket_name, + process_to_parquet_and_upload_to_s3, ) from moto import mock_aws import pytest @@ -33,28 +34,30 @@ def s3_client(aws_credentials): with mock_aws(): yield boto3.client("s3") + @pytest.fixture(scope="class") def mock_extract_bucket(s3_client): mock_extract_bucket = s3_client.create_bucket( - Bucket="dummy_extract_buc", - CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, - ) + Bucket="dummy_extract_buc", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) return mock_extract_bucket - + + @pytest.fixture(scope="class") def mock_transform_bucket(s3_client): mock_transform_bucket = s3_client.create_bucket( - Bucket="dummy_transform_buc", - CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, - ) + Bucket="dummy_transform_buc", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) return mock_transform_bucket - class TestReadFromS3: # @pytest.mark.skip(reason="The test is broken!") - def test_returns_dictionary_with_correct_value_pair(self, s3_client, mock_extract_bucket): - + def test_returns_dictionary_with_correct_value_pair( + self, s3_client, mock_extract_bucket + ): s3_client.upload_file( "tests/dummy_identical.csv", "dummy_extract_buc", @@ -80,9 +83,13 @@ class TestReadFromS3: assert result["Foods"].eq(expected_df, axis="columns").all(axis=None) # @pytest.mark.skip(reason="The test is broken!") - def test_returns_dictionary_of_dataframes_for_multiple_tables(self, s3_client, mock_extract_bucket): + def test_returns_dictionary_of_dataframes_for_multiple_tables( + self, s3_client, mock_extract_bucket + ): s3_client.upload_file( - "tests/dummy_2.csv", "dummy_extract_buc", "Cars/2024/08/21/Cars_14:03:56.csv" + "tests/dummy_2.csv", + "dummy_extract_buc", + "Cars/2024/08/21/Cars_14:03:56.csv", ) tables = ["Foods", "Cars"] result = read_from_s3_subfolder_to_df( @@ -143,30 +150,28 @@ class TestListExistingFiles: class TestBucketName: - def test_functions_retrieves__extractbucket(self, mock_extract_bucket, mock_transform_bucket,s3_client): - + def test_functions_retrieves__extractbucket( + self, mock_extract_bucket, mock_transform_bucket, s3_client + ): bucket = bucket_name("dummy_extract_buc", s3_client) assert bucket == "dummy_extract_buc" + def test_transform_bucket_name( + self, mock_extract_bucket, mock_transform_bucket, s3_client + ): + bucket2 = bucket_name("dummy_transform_buc", s3_client) + assert bucket2 == "dummy_transform_buc" - def test_transform_bucket_name(self, mock_extract_bucket, mock_transform_bucket, s3_client): - bucket2 = bucket_name('dummy_transform_buc', s3_client) - assert bucket2 == 'dummy_transform_buc' - - - def test_recieves_error_when_bucket_doesnt_exist(self, mock_extract_bucket, s3_client): - s3_client.delete_bucket(Bucket='dummy_extract_buc') + def test_recieves_error_when_bucket_doesnt_exist( + self, mock_extract_bucket, s3_client + ): + s3_client.delete_bucket(Bucket="dummy_extract_buc") with pytest.raises(ValueError): - bucket_name('dummy_extract_buc', s3_client) - - - - + bucket_name("dummy_extract_buc", s3_client) class TestProcessToParquetUploadS3: def test_func_uploads_to_s3(self, mock_transform_bucket, s3_client): - expected_cars_df = pd.DataFrame( np.array( [ @@ -177,14 +182,10 @@ class TestProcessToParquetUploadS3: ), columns=["Car_type", "Brand", "Colour"], ) - mock_dim_dict = {'car_data': expected_cars_df} - - response = process_to_parquet_and_upload_to_s3([], mock_dim_dict, {}, mock_transform_bucket, s3_client) + mock_dim_dict = {"car_data": expected_cars_df} + response = process_to_parquet_and_upload_to_s3( + [], mock_dim_dict, {}, mock_transform_bucket, s3_client + ) assert response == {"uploaded": ["car_data"], "not_uploaded": []} - - - - - -- cgit v1.2.3 From c6e711bd4196ba1c5b65218d347da1e7b98cac12 Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Wed, 28 Aug 2024 10:37:48 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 4651e2f according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/106 --- src/transform_lambda/transform_lambda.py | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/src/transform_lambda/transform_lambda.py b/src/transform_lambda/transform_lambda.py index c25ab39..8a2cae8 100644 --- a/src/transform_lambda/transform_lambda.py +++ b/src/transform_lambda/transform_lambda.py @@ -11,7 +11,6 @@ from pg8000.native import Connection, InterfaceError from datetime import datetime - class DBConnectionException(Exception): """Wraps pg8000.native Error or DatabaseError.""" @@ -115,13 +114,16 @@ def process_to_parquet_and_upload_to_s3( if table_name in existing_s3_files: status["not_uploaded"].append(table_name) else: -<<<<<<< HEAD:src/transform_lambda/transform_lambda.py + + +<< << << < HEAD: src/transform_lambda/transform_lambda.py parquet_file = df.to_parquet( f"{table_name}.parquet", engine="pyarrow" ) # or fastparquet # changed parquet_file variable to the file name - client.upload_file(f"{table_name}.parquet", bucket, f"{table_name}.parquet") -======= + client.upload_file(f"{table_name}.parquet", + bucket, f"{table_name}.parquet") +== == == = parquet_buffer = io.BytesIO() # or engine="fastparquet" @@ -129,9 +131,10 @@ def process_to_parquet_and_upload_to_s3( parquet_buffer.seek(0) - client.upload_fileobj(parquet_buffer, bucket, f"{table_name}.parquet") + client.upload_fileobj(parquet_buffer, bucket, + f"{table_name}.parquet") ->>>>>>> 3f24ec753902feecec4c17e2877e19853bde1bb2:src/transform_lambda.py +>>>>>> > 3f24ec753902feecec4c17e2877e19853bde1bb2: src/transform_lambda.py status["uploaded"].append(table_name) for table_name, df in mutable_df_dict.items(): -- cgit v1.2.3 From 6c8567770042ad547366f0f02b091379a88d60d6 Mon Sep 17 00:00:00 2001 From: Alex Date: Wed, 28 Aug 2024 10:50:47 +0000 Subject: chore: get out of merge hell --- src/transform_lambda/transform_lambda.py | 21 ++------------------- 1 file changed, 2 insertions(+), 19 deletions(-) diff --git a/src/transform_lambda/transform_lambda.py b/src/transform_lambda/transform_lambda.py index 8a2cae8..02e9887 100644 --- a/src/transform_lambda/transform_lambda.py +++ b/src/transform_lambda/transform_lambda.py @@ -114,27 +114,12 @@ def process_to_parquet_and_upload_to_s3( if table_name in existing_s3_files: status["not_uploaded"].append(table_name) else: - - -<< << << < HEAD: src/transform_lambda/transform_lambda.py parquet_file = df.to_parquet( f"{table_name}.parquet", engine="pyarrow" ) # or fastparquet # changed parquet_file variable to the file name client.upload_file(f"{table_name}.parquet", bucket, f"{table_name}.parquet") -== == == = - parquet_buffer = io.BytesIO() - - # or engine="fastparquet" - df.to_parquet(parquet_buffer, engine="pyarrow") - - parquet_buffer.seek(0) - - client.upload_fileobj(parquet_buffer, bucket, - f"{table_name}.parquet") - ->>>>>> > 3f24ec753902feecec4c17e2877e19853bde1bb2: src/transform_lambda.py status["uploaded"].append(table_name) for table_name, df in mutable_df_dict.items(): @@ -205,12 +190,10 @@ def bucket_name(bucket_prefix, client=boto3.client("s3")): bucket["Name"] for bucket in response["Buckets"] if bucket_prefix in bucket["Name"] - ] -<<<<<<< HEAD:src/transform_lambda/transform_lambda.py -======= + ] + if not bucket_filter: raise ValueError(f"No bucket found with prefix: {bucket_prefix}") ->>>>>>> 3f24ec753902feecec4c17e2877e19853bde1bb2:src/transform_lambda.py return bucket_filter[0] -- cgit v1.2.3 From bf55c50ed6228eb1ca3b10e7280ed35944f7f42f Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Wed, 28 Aug 2024 10:51:00 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 6c85677 according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/106 --- src/transform_lambda/transform_lambda.py | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/src/transform_lambda/transform_lambda.py b/src/transform_lambda/transform_lambda.py index 02e9887..3dbb57b 100644 --- a/src/transform_lambda/transform_lambda.py +++ b/src/transform_lambda/transform_lambda.py @@ -118,8 +118,7 @@ def process_to_parquet_and_upload_to_s3( f"{table_name}.parquet", engine="pyarrow" ) # or fastparquet # changed parquet_file variable to the file name - client.upload_file(f"{table_name}.parquet", - bucket, f"{table_name}.parquet") + client.upload_file(f"{table_name}.parquet", bucket, f"{table_name}.parquet") status["uploaded"].append(table_name) for table_name, df in mutable_df_dict.items(): @@ -190,8 +189,8 @@ def bucket_name(bucket_prefix, client=boto3.client("s3")): bucket["Name"] for bucket in response["Buckets"] if bucket_prefix in bucket["Name"] - ] - + ] + if not bucket_filter: raise ValueError(f"No bucket found with prefix: {bucket_prefix}") -- cgit v1.2.3 From 03a5959df25f74d52ed5393c2a5af6b1b9eb34c9 Mon Sep 17 00:00:00 2001 From: T-Aji Date: Wed, 28 Aug 2024 12:48:13 +0100 Subject: refactored functs to include columns instead of drop columns --- src/load_lambda.py | 5 +- src/transform_lambda/dataframes.py | 157 ++++++++++++++++++++----------- src/transform_lambda/transform_lambda.py | 5 +- tests/test_dataframes.py | 2 +- 4 files changed, 111 insertions(+), 58 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 7339ab9..926b4db 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -134,6 +134,9 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): file_obj = client.get_object(Bucket=bucket_name, Key=file_key) parquet_file = pq.ParquetFile(BytesIO(file_obj["Body"].read())) df = parquet_file.read().to_pandas() + print("df", df) + print("type", type(df)) + print(df.columns) dfs[file_key] = df except ClientError as e: logger.error(f"Unable to retrieve S3 object {file_key}: {e}") @@ -148,7 +151,7 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): except ClientError as client_error: logger.error(f"Unable to list objects: {client_error}") raise - + print() return dfs diff --git a/src/transform_lambda/dataframes.py b/src/transform_lambda/dataframes.py index 2a46bd6..bf0556b 100644 --- a/src/transform_lambda/dataframes.py +++ b/src/transform_lambda/dataframes.py @@ -37,30 +37,28 @@ def create_fact_sales_order(dict_of_df): df_sales["agreed_payment_date"] = pd.to_datetime( df_sales["agreed_payment_date"], format="%Y-%m-%d" ) - df_sales = df_sales.drop(labels=["created_at", "last_updated"], axis=1) - - df_sales.reset_index(inplace=True) - return df_sales + fact_sales = df_sales.loc[:, + [ + "sales_order_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "staff_id", + "counterparty_id", + "units_sold", + "unit_price", + "currency_id", + "design_id", + "agreed_payment_date", + "agreed_delivery_date", + "agreed_delivery_location_id" + ], + ] + fact_sales.rename(columns={"staff_id": "sales_staff_id"}).reset_index(inplace=True) + - df_sales["created_date"] = df_sales["created_at"].astype("datetime64[ns]").dt.date - df_sales["created_time"] = ( - df_sales["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time - ) - df_sales["last_updated_date"] = ( - df_sales["last_updated"].astype("datetime64[ns]").dt.date - ) - df_sales["last_updated_time"] = ( - df_sales["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time - ) - df_sales["agreed_delivery_date"] = pd.to_datetime( - df_sales["agreed_delivery_date"], format="%Y-%m-%d" - ) - df_sales["agreed_payment_date"] = pd.to_datetime( - df_sales["agreed_payment_date"], format="%Y-%m-%d" - ) - df_sales = df_sales.drop(labels=["created_at", "last_updated"], axis=1) - df_sales.reset_index(inplace=True) - return df_sales + return fact_sales # no test, same as fact_payment @@ -83,9 +81,27 @@ def create_fact_purchase_orders(dict_of_df): df_po["agreed_payment_date"] = pd.to_datetime( df_po["agreed_payment_date"], format="%Y-%m-%d" ) - df_po = df_po.drop(labels=["created_at", "last_updated"], axis=1) - df_po.reset_index(inplace=True) - return df_po + fact_purchase_order = df_po.loc[:, + [ + "purchase_order_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "staff_id", + "counterparty_id", + "item_code", + "item_quantity", + "item_unit_price", + "currency_id", + "agreed_delivery_date", + "agreed_payment_date", + "agreed_delivery_location_id" + ] + + ] + fact_purchase_order.reset_index(inplace=True) + return fact_purchase_order # test passed @@ -109,38 +125,57 @@ def create_fact_payment(dict_of_df): df_payment["payment_date"] = pd.to_datetime( df_payment["payment_date"], format="%Y-%m-%d" ) - df_payment = df_payment.drop(labels=["created_at", "last_updated"], axis=1) - - df_payment.reset_index(inplace=True) - return df_payment + fact_payment = df_payment.loc[:, + [ + "payment_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "transaction_id", + "counterparty_id", + "payment_amount", + "currency_id", + "payment_type_id", + "paid", + "payment_date" + ] + ] + fact_payment.reset_index(inplace=True) + return fact_payment # test passed def create_dim_transaction(dict_of_df): - df_transaction = dict_of_df["transaction"].drop( - labels=["created_at", "last_updated"], axis=1 - ) - return df_transaction + dim_transaction = dict_of_df["transaction"].loc[:, + [ + "transaction_id", + "transaction_type", + "sales_order_id", + "purchase_order_id" + ] + ] + return dim_transaction # test passed def create_dim_location(dict_of_df): - df_loc = ( - dict_of_df["address"] - .drop(labels=["created_at", "last_updated"], axis=1) + dim_location = ( + dict_of_df["address"].drop(labels=["created_at", "last_updated"], axis=1) .rename(columns={"address_id": "location_id"}) ) - return df_loc + return dim_location def create_dim_counterparty(dict_of_df): df_prefixed_address = ( dict_of_df["address"] .drop(labels=["created_at", "last_updated"], axis=1) + .rename(columns={"phone": "phone_number"}) .add_prefix("counterparty_legal_", axis=1) ) df_cp = pd.merge( @@ -149,15 +184,18 @@ def create_dim_counterparty(dict_of_df): left_on="legal_address_id", right_on="counterparty_legal_address_id", how="inner", - ) - df_cp.drop( - columns=[ + )#.dropna(inplace=True) + dim_counterparty = df_cp.drop( + labels=[ "legal_address_id", "counterparty_legal_address_id", - ], - inplace=True, + "created_at", + "last_updated", + "commercial_contact", + "delivery_contact" + ], axis=1 ) - return df_cp + return dim_counterparty # test passed @@ -179,6 +217,7 @@ def create_dim_date(dict_of_df): sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) df_date.drop_duplicates(inplace=True) + # df_date.dropna(inplace=True) df_date["year"] = df_date["date_id"].dt.year df_date["month"] = df_date["date_id"].dt.month df_date["day"] = df_date["date_id"].dt.day @@ -210,10 +249,11 @@ def scrape_currency_names(): def create_dim_currency(dict_of_df, names=scrape_currency_names()): df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) - dim_cur = pd.merge( - df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" + dim_currency = pd.merge( + df_cur, names, left_on="currency_code", right_on="currency_code", how="left" ) - return dim_cur + dim_currency.drop_duplicates(inplace=True) + return dim_currency # tests passed @@ -221,7 +261,12 @@ def create_dim_currency(dict_of_df, names=scrape_currency_names()): def create_dim_payment_type(dict_of_df): df_payment_type = dict_of_df["payment_type"] - dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + dim_payment_type = df_payment_type.loc[:, + [ + "payment_type_id", + "payment_type_name" + ] + ] return dim_payment_type @@ -230,8 +275,13 @@ def create_dim_payment_type(dict_of_df): def create_dim_design(dict_of_df): df_design = dict_of_df["design"] - dim_design = df_design.loc[ - :, ["design_id", "design_name", "file_name", "file_location"] + dim_design = df_design.loc[:, + [ + "design_id", + "design_name", + "file_name", + "file_location" + ] ] return dim_design @@ -243,15 +293,14 @@ def create_dim_staff(dict_of_df): staff_department = pd.merge( dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" ) - dim_staff = staff_department.loc[ - :, + dim_staff = staff_department.loc[:, [ "staff_id", "first_name", "last_name", "department_name", "location", - "email_address", - ], + "email_address" + ] ] return dim_staff diff --git a/src/transform_lambda/transform_lambda.py b/src/transform_lambda/transform_lambda.py index 93b2284..1453c6c 100644 --- a/src/transform_lambda/transform_lambda.py +++ b/src/transform_lambda/transform_lambda.py @@ -42,7 +42,7 @@ TABLES = [ "department", "currency", "design", - "payment_type", + "payment_type" ] @@ -73,7 +73,8 @@ def lambda_handler(event, context): "fact_payment": create_fact_payment(dict_of_df), "dim_currency": create_dim_currency(dict_of_df), } - + print(immutable_df_dict.values()) + print(mutable_df_dict.values()) status = process_to_parquet_and_upload_to_s3( existing_s3_files, immutable_df_dict, mutable_df_dict, bucket ) diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index ea7bad1..7dd592a 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -1,4 +1,4 @@ -from src.dataframes import * +from src.transform_lambda.dataframes import * import pandas as pd from unittest.mock import patch from datetime import datetime as dt -- cgit v1.2.3 From d064b2ec2c7393f8de50560a7edfe100851bfea3 Mon Sep 17 00:00:00 2001 From: T-Aji Date: Wed, 28 Aug 2024 14:39:13 +0100 Subject: debugging load_lambda --- src/load_lambda.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 926b4db..272cb8c 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -164,13 +164,13 @@ def upload_dfs_to_database(): "dim_date.parquet", # this needs to be mutable "dim_location.parquet", "dim_staff.parquet", - "dim_design.parquet", + "dim_design.parquet" ] mutable_df_dict = [ "fact_sales_order", "fact_purchase_order", "fact_payment", - "dim_currency", + "dim_currency" ] for file_name, df in dict_of_dfs.items(): @@ -182,6 +182,7 @@ def upload_dfs_to_database(): df.to_sql( table_name, con=db_engine, + schema="project_team_2", if_exists="append", index=False, ) -- cgit v1.2.3 From 6235a2bb04b60d57a41196b07bbf0296920c6980 Mon Sep 17 00:00:00 2001 From: T-Aji Date: Wed, 28 Aug 2024 17:52:45 +0100 Subject: wip commit --- src/load_lambda.py | 174 +++++++++++++++++++------------ src/transform_lambda/dataframes.py | 8 +- src/transform_lambda/transform_lambda.py | 2 +- tests/test_transform_lambda.py | 2 +- 4 files changed, 115 insertions(+), 71 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 272cb8c..cdcf105 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -7,7 +7,8 @@ import logging import json import traceback from sqlalchemy import create_engine - +from datetime import datetime as dt +import re logger = logging.getLogger(__name__) @@ -15,10 +16,10 @@ logging.basicConfig( format="{asctime} - {levelname} - {message}", style="{", datefmt="%Y-%m-%d %H:%M", - level=logging.DEBUG, + level=logging.INFO, ) - -logging.getLogger("botocore").setLevel(logging.INFO) +# logging.getLogger("botocore").setLevel(logging.INFO) +# logging.getLogger('sqlalchemy.engine').setLevel(logging.DEBUG) def lambda_handler(event, context): @@ -38,10 +39,10 @@ def lambda_handler(event, context): ), } else: - logger.error(f"error") + logger.error(f"error", exc_info=True) return {"error"} except Exception as e: - logger.error({e}) + logger.error({e}, exc_info=True) return {"statusCode": 500, "body": {e}} @@ -58,10 +59,10 @@ def retrieve_secrets(client=None, secret_name=None): get_secret_value_response = client.get_secret_value(SecretId=secret_name) print(get_secret_value_response) except ClientError as e: - logger.error(f"Failed to retrieve secret {secret_name}: {str(e)}") + logger.error(f"Failed to retrieve secret {secret_name}: {str(e)}", exc_info=True) raise e except KeyError: - logger.error(f"Secret {secret_name} does not contain a SecretString") + logger.error(f"Secret {secret_name} does not contain a SecretString", exc_info=True) raise ValueError(f"Secret {secret_name} does not contain a SecretString") return get_secret_value_response["SecretString"] @@ -86,7 +87,7 @@ def connect_to_db_and_return_engine(sm_secret=None): engine = create_engine(conn_str) return engine except Exception as e: - logger.error(f"Interface error: {e}") + logger.error(f"Interface error: {e}", exc_info=True) raise RuntimeError("Failed to create database engine") @@ -97,7 +98,7 @@ def get_transform_bucket(client=None): try: response = client.list_buckets() except ClientError as e: - logger.error(f"Error listing S3 buckets: {e}") + logger.error(f"Error listing S3 buckets: {e}", exc_info=True) raise RuntimeError("Error listing S3 buckets") transform_bucket_filter = [ @@ -107,7 +108,7 @@ def get_transform_bucket(client=None): ] if not transform_bucket_filter: - logger.error("No transform bucket found") + logger.error("No transform bucket found", exc_info=True) raise ValueError("No transform bucket found") return transform_bucket_filter[0] @@ -117,41 +118,78 @@ def get_transform_bucket(client=None): # convert parquet files into dataframes # return a dictionary of dataframes with name as key, and dataframe object as value +def get_latest_timestamp(existing_files): + if existing_files: + all_datetimes = [] + for file_name in existing_files: + match = re.search(r"\/(.+/).+_(.+)\.parquet", file_name) + if match: + datetime_str = "".join(match.group(1, 2)) + all_datetimes.append( + dt.strptime(datetime_str, "%Y/%m/%d/%H:%M:%S") + ) + return max(all_datetimes) if all_datetimes else dt.min + return existing_files def convert_parquet_files_to_dfs(bucket_name=None, client=None): + mutable_df_dict = [ + "dim_currency", + "fact_sales_order", + "fact_purchase_order", + "fact_payment" + + ] + try: if client is None: client = boto3.client("s3") if bucket_name is None: bucket_name = get_transform_bucket() files = client.list_objects_v2(Bucket=bucket_name) - + dfs = {} if "Contents" in files: - for file in files["Contents"]: - file_key = file["Key"] + s3_key_list = [file["Key"]for file in files["Contents"]] + immutables_l = [] + mutables_d = {prefix:[] for prefix in mutable_df_dict} + for tab, s3_key in mutables_d.items(): + for file in s3_key_list: + if tab in file: + s3_key.append(file) + elif "2024" not in file: + immutables_l.append(file) + else: + continue + immutables_l = list(set(immutables_l)) + print(mutables_d,'mutables_d') + latest_s3_keys = [] + for k,v in mutables_d.items(): + latest_s3_keys.append(dt.strftime(get_latest_timestamp(v), f"{k}/%Y/%m/%d/{k}_%H:%M:%S.parquet")) + print(latest_s3_keys,'latest') + print(immutables_l,'immutables_l') + for file_key in latest_s3_keys+immutables_l: try: file_obj = client.get_object(Bucket=bucket_name, Key=file_key) parquet_file = pq.ParquetFile(BytesIO(file_obj["Body"].read())) df = parquet_file.read().to_pandas() - print("df", df) - print("type", type(df)) - print(df.columns) - dfs[file_key] = df + df_without_nulls = df.dropna() + #print("df_without_nulls", df_without_nulls) + #print("type", type(df_without_nulls)) + #print(df_without_nulls.columns) + dfs[file_key] = df_without_nulls except ClientError as e: - logger.error(f"Unable to retrieve S3 object {file_key}: {e}") + logger.error(f"Unable to retrieve S3 object {file_key}: {e}", exc_info=True) except Exception as e: - logger.error(f"Unable to process file {file_key}: {e}") + logger.error(f"Unable to process file {file_key}: {e}", exc_info=True) else: - logger.error(f"No files found in {bucket_name}.") + logger.error(f"No files found in {bucket_name}.", exc_info=True) return {} except ValueError as value_error: - logger.error(f"Unable to list objects: {value_error}") + logger.error(f"Unable to list objects: {value_error}", exc_info=True) raise except ClientError as client_error: - logger.error(f"Unable to list objects: {client_error}") + logger.error(f"Unable to list objects: {client_error}", exc_info=True) raise - print() return dfs @@ -160,53 +198,57 @@ def upload_dfs_to_database(): dict_of_dfs = convert_parquet_files_to_dfs() db_engine = connect_to_db_and_return_engine() immutable_df_dict = [ - "dim_counterparty.parquet", - "dim_date.parquet", # this needs to be mutable - "dim_location.parquet", - "dim_staff.parquet", - "dim_design.parquet" + # #"dim_counterparty.parquet", + # "dim_date.parquet", # this needs to be mutable + # "dim_location.parquet", + # "dim_staff.parquet", + # "dim_design.parquet" ] mutable_df_dict = [ + "dim_currency", "fact_sales_order", "fact_purchase_order", - "fact_payment", - "dim_currency" + "fact_payment" + ] - - for file_name, df in dict_of_dfs.items(): - print(df) - if file_name in immutable_df_dict: - table_name = file_name.split(".")[0] - print(table_name, "<<<<<") - try: - df.to_sql( - table_name, - con=db_engine, - schema="project_team_2", - if_exists="append", - index=False, - ) - upload_status["uploaded"].append(table_name) - except Exception as e: - logger.error(f"Error uploading dataframe {file_name} to database: {e}") - raise - elif file_name.rsplit("_", 1)[0] in mutable_df_dict: - table_name = file_name.rsplit("_", 1)[0] - try: - df.to_sql( - table_name, - con=db_engine, - schema="project_team_2", - if_exists="append", - index=False, - ) - upload_status["uploaded"].append(table_name) - except Exception as e: - logger.error(f"Error uploading dataframe {file_name} to database: {e}") - raise - else: - upload_status["not_uploaded"].append(file_name) - logger.error(f"{file_name} does not correspond with table in database") + with db_engine.begin() as connection: + for file_name, df in dict_of_dfs.items(): + print(df.dtypes, "dtypes") + print(df.head()) + if file_name in immutable_df_dict: + table_name = file_name.split(".")[0] + print(table_name, "<<<<<") + try: + df.to_sql( + table_name, + con=connection, + schema="project_team_2", + if_exists="append", + index=False, + ) + upload_status["uploaded"].append(table_name) + print(upload_status) + except Exception as e: + logger.error(f"Error uploading dataframe {file_name} to database: {e}", exc_info=True) + raise + elif file_name.split("/")[0] in mutable_df_dict: + table_name = file_name.split("/")[0] + print(table_name, "<<<<<< Date: Wed, 28 Aug 2024 22:46:00 +0100 Subject: fix: adds missing dataframes and resolves tables upload to end data warehouse in case the table is empty --- .gitignore | 6 +++++- src/load_lambda.py | 24 +++++++++++++----------- src/transform_lambda/dataframes.py | 19 ++++++++++++++----- src/transform_lambda/transform_lambda.py | 4 +++- 4 files changed, 35 insertions(+), 18 deletions(-) diff --git a/.gitignore b/.gitignore index 6aa03fc..480ae4b 100644 --- a/.gitignore +++ b/.gitignore @@ -14,4 +14,8 @@ __pycache__/ # OS-Related Files .DS_Store -venv \ No newline at end of file +venv + +#files +/dim_* +/fact_* \ No newline at end of file diff --git a/src/load_lambda.py b/src/load_lambda.py index cdcf105..8f921b8 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -161,18 +161,15 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): else: continue immutables_l = list(set(immutables_l)) - print(mutables_d,'mutables_d') latest_s3_keys = [] for k,v in mutables_d.items(): latest_s3_keys.append(dt.strftime(get_latest_timestamp(v), f"{k}/%Y/%m/%d/{k}_%H:%M:%S.parquet")) - print(latest_s3_keys,'latest') - print(immutables_l,'immutables_l') - for file_key in latest_s3_keys+immutables_l: + for file_key in immutables_l+latest_s3_keys: try: file_obj = client.get_object(Bucket=bucket_name, Key=file_key) parquet_file = pq.ParquetFile(BytesIO(file_obj["Body"].read())) df = parquet_file.read().to_pandas() - df_without_nulls = df.dropna() + df_without_nulls = df.dropna(how='all') #>> can't do 'any' (default) because we lose rows in dim_location #print("df_without_nulls", df_without_nulls) #print("type", type(df_without_nulls)) #print(df_without_nulls.columns) @@ -202,12 +199,14 @@ def upload_dfs_to_database(): # "dim_date.parquet", # this needs to be mutable # "dim_location.parquet", # "dim_staff.parquet", - # "dim_design.parquet" + # "dim_design.parquet", + # 'dim_transaction.parquet' #This one was missing, + 'dim_payment_type.parquet' ] mutable_df_dict = [ - "dim_currency", - "fact_sales_order", - "fact_purchase_order", + # "dim_currency", + # "fact_sales_order", + # "fact_purchase_order", "fact_payment" ] @@ -215,7 +214,9 @@ def upload_dfs_to_database(): for file_name, df in dict_of_dfs.items(): print(df.dtypes, "dtypes") print(df.head()) - if file_name in immutable_df_dict: + print(file_name,"<<< FILE NAME") + print(immutable_df_dict,"<< Date: Thu, 29 Aug 2024 09:47:58 +0100 Subject: fix: added comma. Code complete and uploads all tables in one go if no data exists per each table --- src/load_lambda.py | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 8f921b8..941ae97 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -57,7 +57,6 @@ def retrieve_secrets(client=None, secret_name=None): try: get_secret_value_response = client.get_secret_value(SecretId=secret_name) - print(get_secret_value_response) except ClientError as e: logger.error(f"Failed to retrieve secret {secret_name}: {str(e)}", exc_info=True) raise e @@ -195,18 +194,18 @@ def upload_dfs_to_database(): dict_of_dfs = convert_parquet_files_to_dfs() db_engine = connect_to_db_and_return_engine() immutable_df_dict = [ - # #"dim_counterparty.parquet", - # "dim_date.parquet", # this needs to be mutable - # "dim_location.parquet", - # "dim_staff.parquet", - # "dim_design.parquet", - # 'dim_transaction.parquet' #This one was missing, + "dim_counterparty.parquet", + "dim_date.parquet", # this needs to be mutable + "dim_location.parquet", + "dim_staff.parquet", + "dim_design.parquet", + 'dim_transaction.parquet', #This one was missing, 'dim_payment_type.parquet' ] mutable_df_dict = [ - # "dim_currency", - # "fact_sales_order", - # "fact_purchase_order", + "dim_currency", + "fact_sales_order", + "fact_purchase_order", "fact_payment" ] -- cgit v1.2.3 From 42ad135b25044bb1c7ab8a553f038c8da9de0f75 Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Thu, 29 Aug 2024 08:57:48 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 48e7dae according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/107 --- src/load_lambda.py | 78 +++++++++++++-------- src/transform_lambda/dataframes.py | 116 ++++++++++++++----------------- src/transform_lambda/transform_lambda.py | 6 +- 3 files changed, 105 insertions(+), 95 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 941ae97..86189dc 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -58,10 +58,14 @@ def retrieve_secrets(client=None, secret_name=None): try: get_secret_value_response = client.get_secret_value(SecretId=secret_name) except ClientError as e: - logger.error(f"Failed to retrieve secret {secret_name}: {str(e)}", exc_info=True) + logger.error( + f"Failed to retrieve secret {secret_name}: {str(e)}", exc_info=True + ) raise e except KeyError: - logger.error(f"Secret {secret_name} does not contain a SecretString", exc_info=True) + logger.error( + f"Secret {secret_name} does not contain a SecretString", exc_info=True + ) raise ValueError(f"Secret {secret_name} does not contain a SecretString") return get_secret_value_response["SecretString"] @@ -117,6 +121,7 @@ def get_transform_bucket(client=None): # convert parquet files into dataframes # return a dictionary of dataframes with name as key, and dataframe object as value + def get_latest_timestamp(existing_files): if existing_files: all_datetimes = [] @@ -124,19 +129,17 @@ def get_latest_timestamp(existing_files): match = re.search(r"\/(.+/).+_(.+)\.parquet", file_name) if match: datetime_str = "".join(match.group(1, 2)) - all_datetimes.append( - dt.strptime(datetime_str, "%Y/%m/%d/%H:%M:%S") - ) + all_datetimes.append(dt.strptime(datetime_str, "%Y/%m/%d/%H:%M:%S")) return max(all_datetimes) if all_datetimes else dt.min return existing_files + def convert_parquet_files_to_dfs(bucket_name=None, client=None): mutable_df_dict = [ "dim_currency", "fact_sales_order", "fact_purchase_order", - "fact_payment" - + "fact_payment", ] try: @@ -145,12 +148,12 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): if bucket_name is None: bucket_name = get_transform_bucket() files = client.list_objects_v2(Bucket=bucket_name) - + dfs = {} if "Contents" in files: - s3_key_list = [file["Key"]for file in files["Contents"]] + s3_key_list = [file["Key"] for file in files["Contents"]] immutables_l = [] - mutables_d = {prefix:[] for prefix in mutable_df_dict} + mutables_d = {prefix: [] for prefix in mutable_df_dict} for tab, s3_key in mutables_d.items(): for file in s3_key_list: if tab in file: @@ -161,22 +164,31 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): continue immutables_l = list(set(immutables_l)) latest_s3_keys = [] - for k,v in mutables_d.items(): - latest_s3_keys.append(dt.strftime(get_latest_timestamp(v), f"{k}/%Y/%m/%d/{k}_%H:%M:%S.parquet")) - for file_key in immutables_l+latest_s3_keys: + for k, v in mutables_d.items(): + latest_s3_keys.append( + dt.strftime( + get_latest_timestamp(v), f"{k}/%Y/%m/%d/{k}_%H:%M:%S.parquet" + ) + ) + for file_key in immutables_l + latest_s3_keys: try: file_obj = client.get_object(Bucket=bucket_name, Key=file_key) parquet_file = pq.ParquetFile(BytesIO(file_obj["Body"].read())) df = parquet_file.read().to_pandas() - df_without_nulls = df.dropna(how='all') #>> can't do 'any' (default) because we lose rows in dim_location - #print("df_without_nulls", df_without_nulls) - #print("type", type(df_without_nulls)) - #print(df_without_nulls.columns) + # >> can't do 'any' (default) because we lose rows in dim_location + df_without_nulls = df.dropna(how="all") + # print("df_without_nulls", df_without_nulls) + # print("type", type(df_without_nulls)) + # print(df_without_nulls.columns) dfs[file_key] = df_without_nulls except ClientError as e: - logger.error(f"Unable to retrieve S3 object {file_key}: {e}", exc_info=True) + logger.error( + f"Unable to retrieve S3 object {file_key}: {e}", exc_info=True + ) except Exception as e: - logger.error(f"Unable to process file {file_key}: {e}", exc_info=True) + logger.error( + f"Unable to process file {file_key}: {e}", exc_info=True + ) else: logger.error(f"No files found in {bucket_name}.", exc_info=True) return {} @@ -199,23 +211,22 @@ def upload_dfs_to_database(): "dim_location.parquet", "dim_staff.parquet", "dim_design.parquet", - 'dim_transaction.parquet', #This one was missing, - 'dim_payment_type.parquet' + "dim_transaction.parquet", # This one was missing, + "dim_payment_type.parquet", ] mutable_df_dict = [ "dim_currency", "fact_sales_order", "fact_purchase_order", - "fact_payment" - + "fact_payment", ] with db_engine.begin() as connection: for file_name, df in dict_of_dfs.items(): print(df.dtypes, "dtypes") print(df.head()) - print(file_name,"<<< FILE NAME") - print(immutable_df_dict,"<<