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 +++++++++ 1 file changed, 9 insertions(+) (limited to 'src/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 -- 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(-) (limited to 'src/transform_lambda.py') 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(-) (limited to 'src/transform_lambda.py') 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(-) (limited to 'src/transform_lambda.py') 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 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(-) (limited to 'src/transform_lambda.py') 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 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 (limited to 'src/transform_lambda.py') 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(-) (limited to 'src/transform_lambda.py') 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(-) (limited to 'src/transform_lambda.py') 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 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 (limited to 'src/transform_lambda.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 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 (limited to 'src/transform_lambda.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 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 (limited to 'src/transform_lambda.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(-) (limited to 'src/transform_lambda.py') 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 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(-) (limited to 'src/transform_lambda.py') 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(-) (limited to 'src/transform_lambda.py') 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 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(-) (limited to 'src/transform_lambda.py') 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 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(-) (limited to 'src/transform_lambda.py') 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(-) (limited to 'src/transform_lambda.py') 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(-) (limited to 'src/transform_lambda.py') 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 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(-) (limited to 'src/transform_lambda.py') 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 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(-) (limited to 'src/transform_lambda.py') 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 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 (limited to 'src/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