From 82a835363953538e506f91eb3199d835f0624975 Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Thu, 22 Aug 2024 12:03:38 +0100 Subject: fix: change default parameters for bucket_name and client --- src/extract_lambda.py | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'src') diff --git a/src/extract_lambda.py b/src/extract_lambda.py index 24f0981..0e6dd8c 100644 --- a/src/extract_lambda.py +++ b/src/extract_lambda.py @@ -99,7 +99,9 @@ def connect_to_database() -> Connection: raise DBConnectionException("Failed to connect to database") -def extract_bucket(client=boto3.client("s3")): +def extract_bucket(client=None): + if client is None: + client = boto3.client("s3") response = client.list_buckets() extract_bucket_filter = [ bucket["Name"] for bucket in response["Buckets"] if "extract" in bucket["Name"] @@ -108,11 +110,16 @@ def extract_bucket(client=boto3.client("s3")): return extract_bucket_filter[0] -def list_existing_s3_files(bucket_name=extract_bucket(), client=boto3.client("s3")): +def list_existing_s3_files(bucket_name=None, client=None): """Creates a dictionary and populates it with the results of listing the contents of the s3 bucket, then returns the populated dictionary """ + if client is None: + client = boto3.client("s3") + if bucket_name is None: + bucket_name = extract_bucket(client) + logging.info("Listing existing S3 files") existing_files = {} -- cgit v1.2.3 From dc7dfe29ce977f3038fb3affd617683e8f163dc8 Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Thu, 22 Aug 2024 12:27:55 +0100 Subject: fix: handle no buckets properly --- src/extract_lambda.py | 3 +++ tests/test_extract_lambda.py | 10 +++++----- 2 files changed, 8 insertions(+), 5 deletions(-) (limited to 'src') diff --git a/src/extract_lambda.py b/src/extract_lambda.py index 0e6dd8c..874098b 100644 --- a/src/extract_lambda.py +++ b/src/extract_lambda.py @@ -107,6 +107,9 @@ def extract_bucket(client=None): bucket["Name"] for bucket in response["Buckets"] if "extract" in bucket["Name"] ] + if not extract_bucket_filter: + raise ValueError("No extract_bucket found") + return extract_bucket_filter[0] diff --git a/tests/test_extract_lambda.py b/tests/test_extract_lambda.py index 1266cbb..bba433c 100644 --- a/tests/test_extract_lambda.py +++ b/tests/test_extract_lambda.py @@ -184,10 +184,8 @@ class TestExtractBucket: result = extract_bucket(s3_client) assert result == "extract_bucket" - def test_returns_index_error_if_no_buckets(self, s3_client): - # We don't even need to delete the bucket as there are no buckets - # due to the mock being reset for each test function now - with pytest.raises(IndexError, match="list index out of range"): + def test_raises_value_error_if_no_buckets(self, s3_client): + with pytest.raises(ValueError, match="No extract_bucket found"): extract_bucket(s3_client) @@ -196,7 +194,9 @@ class TestListExistingS3Files: logger = logging.getLogger() logger.info("Testing now.") caplog.set_level(logging.ERROR) - list_existing_s3_files(client=s3_client) + + with pytest.raises(ValueError, match="No extract_bucket found"): + list_existing_s3_files(client=s3_client) assert "Error listing S3 objects" in caplog.text def test_error_if_bucket_is_empty(self, s3_client, caplog, s3_mock_bucket): -- cgit v1.2.3 From 053e75bca8ef34a655bb4afda5f479f112dfb002 Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Thu, 22 Aug 2024 12:33:00 +0100 Subject: fix: improve error handling for list_existing_s3_files and tests --- src/extract_lambda.py | 16 ++++++++++------ tests/test_extract_lambda.py | 10 ++++++++-- 2 files changed, 18 insertions(+), 8 deletions(-) (limited to 'src') diff --git a/src/extract_lambda.py b/src/extract_lambda.py index 874098b..b20c99d 100644 --- a/src/extract_lambda.py +++ b/src/extract_lambda.py @@ -118,15 +118,16 @@ def list_existing_s3_files(bucket_name=None, client=None): results of listing the contents of the s3 bucket, then returns the populated dictionary """ - if client is None: - client = boto3.client("s3") - if bucket_name is None: - bucket_name = extract_bucket(client) logging.info("Listing existing S3 files") existing_files = {} try: + if client is None: + client = boto3.client("s3") + if bucket_name is None: + bucket_name = extract_bucket(client) + response = client.list_objects_v2(Bucket=bucket_name) if "Contents" in response: @@ -142,8 +143,11 @@ def list_existing_s3_files(bucket_name=None, client=None): logger.error("The bucket is empty") return None - except ClientError as e: - logger.error(f"Error listing S3 objects: {e}") + except ValueError as ve: + logger.error(f"Error listing S3 objects: {ve}") + raise + except ClientError as ce: + logger.error(f"Error listing S3 objects: {ce}") return existing_files diff --git a/tests/test_extract_lambda.py b/tests/test_extract_lambda.py index bba433c..8fa0e88 100644 --- a/tests/test_extract_lambda.py +++ b/tests/test_extract_lambda.py @@ -195,8 +195,14 @@ class TestListExistingS3Files: logger.info("Testing now.") caplog.set_level(logging.ERROR) - with pytest.raises(ValueError, match="No extract_bucket found"): - list_existing_s3_files(client=s3_client) + # Mock the extract_bucket function to raise a ValueError! + with patch( + "src.extract_lambda.extract_bucket", + side_effect=ValueError("No extract_bucket found"), + ): + with pytest.raises(ValueError, match="No extract_bucket found"): + list_existing_s3_files(client=s3_client) + assert "Error listing S3 objects" in caplog.text def test_error_if_bucket_is_empty(self, s3_client, caplog, s3_mock_bucket): -- cgit v1.2.3 From 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') 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') 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') 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') 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') 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