From 67de54d70ee918bbaf537cb2c119990c4a70c9a7 Mon Sep 17 00:00:00 2001 From: Ellie Date: Thu, 22 Aug 2024 16:55:48 +0100 Subject: add convert parquet to df function --- src/load_lambda.py | 50 ++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 48 insertions(+), 2 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index c6a8e60..2f0c33a 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -1,2 +1,48 @@ -def lambda_handler(): - pass +import boto3 +from botocore.exceptions import ClientError +from pg8000.native import Connection, InterfaceError, identifier +import pandas as pd +import pyarrow.parquet as pq +from io import BytesIO + +from botocore.exceptions import ClientError +import logging + + +logger = logging.getLogger(__name__) + +logging.basicConfig( + format="{asctime} - {levelname} - {message}", + style="{", + datefmt="%Y-%m-%d %H:%M", + level=logging.DEBUG, +) + +logging.getLogger("botocore").setLevel(logging.WARNING) + +def convert_parquet_files_to_dfs(bucket_name=None, client=None): + try: + if client is None: + client = boto3.client("s3") + if bucket_name is None: + bucket_name = "transform_bucket" + files = client.list_objects_v2(Bucket=bucket_name) + + dfs = [] + for file in files: + file_key = file['Key'] + try: + file_obj = client.get_object(Bucket=bucket_name, Key=file_key) + parquet_file = pq.ParquetFile(BytesIO(file_obj['body'].read())) + df = parquet_file.read().to_pandas() + dfs.append(df) + except ClientError as e: + logger.error(f"Unable to retrieve S3 object {file_key}: {e}") + except ValueError as value_error: + logger.error(f"Unable to list objects: {value_error}") + raise + except ClientError as client_error: + logger.error(f"Unable to list objects: {client_error}") + + return dfs + \ No newline at end of file -- cgit v1.2.3 From 828e8292440d4395fbb00afff4e35ff194f07a95 Mon Sep 17 00:00:00 2001 From: Ellie Date: Thu, 22 Aug 2024 16:56:15 +0100 Subject: wip: add test file for load lambda --- tests/test_load_lambda.py | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 tests/test_load_lambda.py diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py new file mode 100644 index 0000000..0572340 --- /dev/null +++ b/tests/test_load_lambda.py @@ -0,0 +1,9 @@ +import boto3 +import pandas as pd +import pyarrow.parquet as pq +from io import BytesIO +from src.load_lambda import convert_parquet_files_to_dataframes + +class TestConvertParquetToDFs: + def test_convert_parquet_to_dfs_returns_df(): + \ No newline at end of file -- cgit v1.2.3 From a5b4056961ae65b4b2b1fe3afaf1561b2ba749ae Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 09:39:44 +0100 Subject: add pyarrow to requirements --- requirements.txt | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index 62ebbf4..6ba2cf6 100644 --- a/requirements.txt +++ b/requirements.txt @@ -29,4 +29,5 @@ urllib3==2.2.2 Werkzeug==3.0.3 xmltodict==0.13.0 s3fs -pandas \ No newline at end of file +pandas +pyarrow \ No newline at end of file -- cgit v1.2.3 From 6bf831c5387408e92a63cb5667aab8f415b536e4 Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 09:40:08 +0100 Subject: add improved convert parquet files to df function --- src/load_lambda.py | 33 +++++++++++++++++++-------------- 1 file changed, 19 insertions(+), 14 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 2f0c33a..1813db4 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -1,11 +1,8 @@ import boto3 from botocore.exceptions import ClientError -from pg8000.native import Connection, InterfaceError, identifier import pandas as pd import pyarrow.parquet as pq from io import BytesIO - -from botocore.exceptions import ClientError import logging @@ -19,7 +16,9 @@ logging.basicConfig( ) logging.getLogger("botocore").setLevel(logging.WARNING) - + +# list and then retrieve parquet files from S3 bucket +# convert parquet files into dataframes and return a list of dataframes def convert_parquet_files_to_dfs(bucket_name=None, client=None): try: if client is None: @@ -29,20 +28,26 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): files = client.list_objects_v2(Bucket=bucket_name) dfs = [] - for file in files: - file_key = file['Key'] - try: - file_obj = client.get_object(Bucket=bucket_name, Key=file_key) - parquet_file = pq.ParquetFile(BytesIO(file_obj['body'].read())) - df = parquet_file.read().to_pandas() - dfs.append(df) - except ClientError as e: - logger.error(f"Unable to retrieve S3 object {file_key}: {e}") + if "Contents" in files: + for file in files["Contents"]: + file_key = file['Key'] + try: + file_obj = client.get_object(Bucket=bucket_name, Key=file_key) + parquet_file = pq.ParquetFile(BytesIO(file_obj['Body'].read())) + df = parquet_file.read().to_pandas() + dfs.append(df) + except ClientError as e: + logger.error(f"Unable to retrieve S3 object {file_key}: {e}") + except Exception as e: + logger.error(f"Unable to process file {file_key}: {e}") + else: + logger.error(f"No files found in {bucket_name}.") + return [] except ValueError as value_error: logger.error(f"Unable to list objects: {value_error}") raise except ClientError as client_error: logger.error(f"Unable to list objects: {client_error}") + raise return dfs - \ No newline at end of file -- cgit v1.2.3 From 265d61c34c3a56b7e74333911e65d3148b2945b4 Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 09:47:52 +0100 Subject: add get transform bucket function --- src/load_lambda.py | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 1813db4..a3fd996 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -17,6 +17,20 @@ logging.basicConfig( logging.getLogger("botocore").setLevel(logging.WARNING) +# get transform bucket +def transform_bucket(client=None): + if client is None: + client = boto3.client("s3") + response = client.list_buckets() + transform_bucket_filter = [ + bucket["Name"] for bucket in response["Buckets"] if "transform" in bucket["Name"] + ] + + if not transform_bucket_filter: + raise ValueError("No transform_bucket found") + + return transform_bucket_filter[0] + # list and then retrieve parquet files from S3 bucket # convert parquet files into dataframes and return a list of dataframes def convert_parquet_files_to_dfs(bucket_name=None, client=None): @@ -24,7 +38,7 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): if client is None: client = boto3.client("s3") if bucket_name is None: - bucket_name = "transform_bucket" + bucket_name = transform_bucket(client) files = client.list_objects_v2(Bucket=bucket_name) dfs = [] -- cgit v1.2.3 From 09c8191ce983e4335cfb131d21ddb5413b849cfb Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 11:18:24 +0100 Subject: add tests --- src/load_lambda.py | 61 ++++++++++++++++++++++++++++++++++++++++++++--- tests/test_load_lambda.py | 3 +-- 2 files changed, 59 insertions(+), 5 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index a3fd996..d95c27a 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -4,6 +4,9 @@ import pandas as pd import pyarrow.parquet as pq from io import BytesIO import logging +import json +from src.extract_lambda import retrieve_secrets, connect_to_database +from sqlalchemy import create_engine logger = logging.getLogger(__name__) @@ -17,6 +20,43 @@ logging.basicConfig( logging.getLogger("botocore").setLevel(logging.WARNING) +def lambda_handler(event, context): + db = None + try: + uploaded_tables = upload_dfs_to_database() + if uploaded_tables == []: + return { + "statusCode": 200, + "body": json.dumps("No datframes were uploaded."), + } + return { + "statusCode": 200, + "body": json.dumps( + f"""The following dataframes were uploaded successfully: + {', '.join(upload_dfs_to_database['updated'])}.""" + ), + } + except Exception as e: + logger.error(f"Error: {e}", exc_info=True) + return {"statusCode": 500, "body": json.dumps("Internal server error.")} + finally: + if db: + db.close() + +# connect to database, slightly different way of doing it, to allow manipulation through pandas +def connect_to_db_and_return_engine(): + secrets = json.loads(retrieve_secrets("bentley-RDS-credentials")) #need to amend retrieve secrets function + host = secrets["host"] + port = secrets["port"] + user = secrets["user"] + password = secrets["password"] + database = secrets["database"] + conn_str = f'postgresql+pg8000://{user}:{password}@{host}:{port}/{database}' + engine = create_engine(conn_str) #interface between python (pandas) and SQL + return engine + + + # get transform bucket def transform_bucket(client=None): if client is None: @@ -41,7 +81,7 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): bucket_name = transform_bucket(client) files = client.list_objects_v2(Bucket=bucket_name) - dfs = [] + dfs = {} if "Contents" in files: for file in files["Contents"]: file_key = file['Key'] @@ -49,7 +89,7 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): file_obj = client.get_object(Bucket=bucket_name, Key=file_key) parquet_file = pq.ParquetFile(BytesIO(file_obj['Body'].read())) df = parquet_file.read().to_pandas() - dfs.append(df) + dfs[file_key] = df except ClientError as e: logger.error(f"Unable to retrieve S3 object {file_key}: {e}") except Exception as e: @@ -64,4 +104,19 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): logger.error(f"Unable to list objects: {client_error}") raise - return dfs + return dfs + +def upload_dfs_to_database(): + uploaded = [] + dict_of_dfs = convert_parquet_files_to_dfs() + db_engine = connect_to_db_and_return_engine() + try: + for table_name, df in dict_of_dfs: + df.to_sql(table_name, con=db_engine, ifexists="replace", index=False) + uploaded.append(table_name) + except Exception as e: + logger.error(f"Error uploading dataframes: {e}") + db_engine.dispose() + return uploaded + + # aiming to return a list of uploaded tables \ No newline at end of file diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 0572340..d9ea918 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -1,8 +1,7 @@ -import boto3 import pandas as pd import pyarrow.parquet as pq from io import BytesIO -from src.load_lambda import convert_parquet_files_to_dataframes +from src.load_lambda import convert_parquet_files_to_dfs class TestConvertParquetToDFs: def test_convert_parquet_to_dfs_returns_df(): -- cgit v1.2.3 From 535e3cd919613d4cadfbb42ea8f2ecdd7678f38c Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 11:18:55 +0100 Subject: add SQLalchemy to requirements --- requirements.txt | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index 6ba2cf6..614a0ab 100644 --- a/requirements.txt +++ b/requirements.txt @@ -30,4 +30,5 @@ Werkzeug==3.0.3 xmltodict==0.13.0 s3fs pandas -pyarrow \ No newline at end of file +pyarrow +SQLAlchemy \ No newline at end of file -- cgit v1.2.3 From 65289cdd17359c6a29560339e134e0ddf9461ce0 Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 12:08:09 +0100 Subject: add amendments to load lambda --- src/load_lambda.py | 66 ++++++++++++++++++++++++++++++------------------------ 1 file changed, 37 insertions(+), 29 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index d95c27a..f92bb45 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -1,11 +1,11 @@ import boto3 -from botocore.exceptions import ClientError +from botocore.exceptions import ClientError, InterfaceError import pandas as pd import pyarrow.parquet as pq from io import BytesIO import logging import json -from src.extract_lambda import retrieve_secrets, connect_to_database +from src.extract_lambda import retrieve_secrets from sqlalchemy import create_engine @@ -18,67 +18,74 @@ logging.basicConfig( level=logging.DEBUG, ) -logging.getLogger("botocore").setLevel(logging.WARNING) +logging.getLogger("botocore").setLevel(logging.INFO) + def lambda_handler(event, context): - db = None try: uploaded_tables = upload_dfs_to_database() - if uploaded_tables == []: + if not uploaded_tables: return { "statusCode": 200, - "body": json.dumps("No datframes were uploaded."), + "body": json.dumps("No dataframes were uploaded."), } return { "statusCode": 200, "body": json.dumps( f"""The following dataframes were uploaded successfully: - {', '.join(upload_dfs_to_database['updated'])}.""" + {', '.join(uploaded_tables)} .""" ), } except Exception as e: logger.error(f"Error: {e}", exc_info=True) return {"statusCode": 500, "body": json.dumps("Internal server error.")} - finally: - if db: - db.close() # connect to database, slightly different way of doing it, to allow manipulation through pandas def connect_to_db_and_return_engine(): - secrets = json.loads(retrieve_secrets("bentley-RDS-credentials")) #need to amend retrieve secrets function - host = secrets["host"] - port = secrets["port"] - user = secrets["user"] - password = secrets["password"] - database = secrets["database"] - conn_str = f'postgresql+pg8000://{user}:{password}@{host}:{port}/{database}' - engine = create_engine(conn_str) #interface between python (pandas) and SQL - return engine - - + try: + secrets = json.loads(retrieve_secrets("bentley-RDS-credentials")) #need to amend retrieve secrets function + host = secrets["host"] + port = secrets["port"] + user = secrets["user"] + password = secrets["password"] + database = secrets["database"] + conn_str = f'postgresql+pg8000://{user}:{password}@{host}:{port}/{database}' + engine = create_engine(conn_str) #interface between python (pandas) and SQL + return engine + except Exception as e: + logger.error(f"Interface error: {e}") + raise RuntimeError("Failed to create database engine") + # get transform bucket -def transform_bucket(client=None): +def get_transform_bucket(client=None): if client is None: client = boto3.client("s3") - response = client.list_buckets() + try: + response = client.list_buckets() + except ClientError as e: + logger.error(f"Error listing S3 buckets: {e}") + raise RuntimeError("Error listing S3 buckets") + transform_bucket_filter = [ bucket["Name"] for bucket in response["Buckets"] if "transform" in bucket["Name"] ] if not transform_bucket_filter: - raise ValueError("No transform_bucket found") + logger.error("No transform bucket found") + raise ValueError("No transform bucket found") return transform_bucket_filter[0] # list and then retrieve parquet files from S3 bucket -# convert parquet files into dataframes and return a list of dataframes +# convert parquet files into dataframes +# return a dictionary of dataframes with name as key, and dataframe object as value def convert_parquet_files_to_dfs(bucket_name=None, client=None): try: if client is None: client = boto3.client("s3") if bucket_name is None: - bucket_name = transform_bucket(client) + bucket_name = get_transform_bucket() files = client.list_objects_v2(Bucket=bucket_name) dfs = {} @@ -96,7 +103,7 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): logger.error(f"Unable to process file {file_key}: {e}") else: logger.error(f"No files found in {bucket_name}.") - return [] + return {} except ValueError as value_error: logger.error(f"Unable to list objects: {value_error}") raise @@ -111,11 +118,12 @@ def upload_dfs_to_database(): dict_of_dfs = convert_parquet_files_to_dfs() db_engine = connect_to_db_and_return_engine() try: - for table_name, df in dict_of_dfs: - df.to_sql(table_name, con=db_engine, ifexists="replace", index=False) + for table_name, df in dict_of_dfs.items(): + df.to_sql(table_name, con=db_engine, if_exists="replace", index=False) uploaded.append(table_name) except Exception as e: logger.error(f"Error uploading dataframes: {e}") + raise db_engine.dispose() return uploaded -- cgit v1.2.3 From f3bb705a31ab9d94dc856c2de0da4b7b73a57fae Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 12:38:25 +0100 Subject: add get transform bucket test --- src/load_lambda.py | 2 +- tests/test_load_lambda.py | 48 +++++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 45 insertions(+), 5 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index f92bb45..a9d5ac5 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -1,5 +1,5 @@ import boto3 -from botocore.exceptions import ClientError, InterfaceError +from botocore.exceptions import ClientError import pandas as pd import pyarrow.parquet as pq from io import BytesIO diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index d9ea918..2392f10 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -1,8 +1,48 @@ import pandas as pd import pyarrow.parquet as pq from io import BytesIO -from src.load_lambda import convert_parquet_files_to_dfs +from moto import mock_aws +import boto3 +import os +import pytest +from src.load_lambda import lambda_handler, connect_to_db_and_return_engine, get_transform_bucket, convert_parquet_files_to_dfs, upload_dfs_to_database -class TestConvertParquetToDFs: - def test_convert_parquet_to_dfs_returns_df(): - \ No newline at end of file +@pytest.fixture(scope="class") +def aws_credentials(): + os.environ["AWS_ACCESS_KEY_ID"] = "testing" + os.environ["AWS_SECRET_ACCESS_KEY"] = "testing" + os.environ["AWS_SECURIT_TOKEN"] = "testing" + os.environ["AWS_SESSION_TOKEN"] = "testing" + os.environ["AWS_DEFAULT_REGION"] = "eu-west-2" + + +@pytest.fixture(scope="class") +def s3_client(aws_credentials): + with mock_aws(): + yield boto3.client("s3") + +@pytest.fixture(scope="function") +def s3_mock_bucket(s3_client): + bucket = s3_client.create_bucket( + Bucket="transform_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) + return bucket + + +class TestLambdaHandler: + pass + +class TestConnectToDBAndReturnEngine: + pass + +class TestGetTransformBucket: + def test_get_transform_bucket_returns_string(self, s3_client, s3_mock_bucket): + result = get_transform_bucket(s3_client) + assert result == "transform_bucket" + +class TestConvertParquetToDfs: + pass + +class TestUploadDfsToDatabase: + pass \ No newline at end of file -- cgit v1.2.3 From 2e85e8f14f35bebb7e96a9dff7bc59ebaefe32f6 Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 13:15:35 +0100 Subject: adds passing transform bucket tests --- tests/test_load_lambda.py | 30 +++++++++++++++++++----------- 1 file changed, 19 insertions(+), 11 deletions(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 2392f10..7f001df 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -17,18 +17,10 @@ def aws_credentials(): @pytest.fixture(scope="class") -def s3_client(aws_credentials): +def mock_s3_client(aws_credentials): with mock_aws(): yield boto3.client("s3") -@pytest.fixture(scope="function") -def s3_mock_bucket(s3_client): - bucket = s3_client.create_bucket( - Bucket="transform_bucket", - CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, - ) - return bucket - class TestLambdaHandler: pass @@ -37,8 +29,24 @@ class TestConnectToDBAndReturnEngine: pass class TestGetTransformBucket: - def test_get_transform_bucket_returns_string(self, s3_client, s3_mock_bucket): - result = get_transform_bucket(s3_client) + def test_get_transform_bucket_raises_error_if_no_buckets(self, mock_s3_client): + with pytest.raises(ValueError, match="No transform bucket found"): + get_transform_bucket(mock_s3_client) + + def test_get_transform_bucket_returns_transform_bucket_if_one_bucket(self, mock_s3_client): + mock_s3_client.create_bucket( + Bucket="transform_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) + result = get_transform_bucket(mock_s3_client) + assert result == "transform_bucket" + + def test_get_transform_bucket_only_returns_transform_bucket_if_several_buckets(self, mock_s3_client): + mock_s3_client.create_bucket( + Bucket="extract_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) + result = get_transform_bucket(mock_s3_client) assert result == "transform_bucket" class TestConvertParquetToDfs: -- cgit v1.2.3 From 0c95b93303dea04e18aefe57e3b6fef7e4127c3c Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 13:22:23 +0100 Subject: add working completed tests for get transform bucket --- tests/test_load_lambda.py | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 7f001df..f1c2b01 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -29,11 +29,19 @@ class TestConnectToDBAndReturnEngine: pass class TestGetTransformBucket: - def test_get_transform_bucket_raises_error_if_no_buckets(self, mock_s3_client): + def test_raises_value_error_if_no_buckets(self, mock_s3_client): with pytest.raises(ValueError, match="No transform bucket found"): get_transform_bucket(mock_s3_client) - def test_get_transform_bucket_returns_transform_bucket_if_one_bucket(self, mock_s3_client): + def test_raises_value_error_if_no_transform_bucket(self, mock_s3_client): + mock_s3_client.create_bucket( + Bucket="extract_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) + with pytest.raises(ValueError, match="No transform bucket found"): + get_transform_bucket(mock_s3_client) + + def test_returns_transform_bucket_if_one_bucket(self, mock_s3_client): mock_s3_client.create_bucket( Bucket="transform_bucket", CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, @@ -41,16 +49,16 @@ class TestGetTransformBucket: result = get_transform_bucket(mock_s3_client) assert result == "transform_bucket" - def test_get_transform_bucket_only_returns_transform_bucket_if_several_buckets(self, mock_s3_client): + def test_only_returns_transform_bucket_if_several_buckets(self, mock_s3_client): mock_s3_client.create_bucket( - Bucket="extract_bucket", + Bucket="another_test_bucket", CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, ) result = get_transform_bucket(mock_s3_client) assert result == "transform_bucket" class TestConvertParquetToDfs: - pass + pass class TestUploadDfsToDatabase: pass \ No newline at end of file -- cgit v1.2.3 From 0f8f376fe806ea72f056356cc043213f61159697 Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 14:35:36 +0100 Subject: add retrieve secrets function --- src/load_lambda.py | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index a9d5ac5..2dc90ba 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -40,10 +40,29 @@ def lambda_handler(event, context): logger.error(f"Error: {e}", exc_info=True) return {"statusCode": 500, "body": json.dumps("Internal server error.")} +def retrieve_secrets(): + secret_name = "bentley-RDS-credentials" + region_name = "eu-west-2" + + # Create a Secrets Manager client + session = boto3.session.Session() + client = session.client(service_name="secretsmanager", region_name=region_name) + + try: + get_secret_value_response = client.get_secret_value(SecretId=secret_name) + except ClientError as e: + logger.error(f"Failed to retrieve secret {secret_name}: {str(e)}") + raise e + except KeyError: + logger.error(f"Secret {secret_name} does not contain a SecretString") + raise ValueError(f"Secret {secret_name} does not contain a SecretString") + + return get_secret_value_response["SecretString"] + # connect to database, slightly different way of doing it, to allow manipulation through pandas def connect_to_db_and_return_engine(): try: - secrets = json.loads(retrieve_secrets("bentley-RDS-credentials")) #need to amend retrieve secrets function + secrets = json.loads(retrieve_secrets()) host = secrets["host"] port = secrets["port"] user = secrets["user"] -- cgit v1.2.3 From 500ebf24c746ec87c9c846f5a82d638cc23983b9 Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 17:04:08 +0100 Subject: add amendendments for upload_dfs_to_db --- src/load_lambda.py | 47 ++++++++++++++++++++++++++++++++++------------- 1 file changed, 34 insertions(+), 13 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 2dc90ba..8eaea32 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -24,7 +24,7 @@ logging.getLogger("botocore").setLevel(logging.INFO) def lambda_handler(event, context): try: uploaded_tables = upload_dfs_to_database() - if not uploaded_tables: + if not uploaded_tables["uploaded"]: return { "statusCode": 200, "body": json.dumps("No dataframes were uploaded."), @@ -33,7 +33,7 @@ def lambda_handler(event, context): "statusCode": 200, "body": json.dumps( f"""The following dataframes were uploaded successfully: - {', '.join(uploaded_tables)} .""" + {uploaded_tables["uploaded"]} .""" ), } except Exception as e: @@ -133,17 +133,38 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): return dfs def upload_dfs_to_database(): - uploaded = [] + upload_status = {"uploaded": [], "not_uploaded": []} dict_of_dfs = convert_parquet_files_to_dfs() db_engine = connect_to_db_and_return_engine() - try: - for table_name, df in dict_of_dfs.items(): - df.to_sql(table_name, con=db_engine, if_exists="replace", index=False) - uploaded.append(table_name) - except Exception as e: - logger.error(f"Error uploading dataframes: {e}") - raise + immutable_df_dict = ["dim_counterparty.parquet", + "dim_date.parquet", #this needs to be mutable + "dim_location.parquet", + "dim_staff.parquet", + "dim_design.parquet"] + mutable_df_dict = ["fact_sales_order", + "fact_purchase_order", + "fact_payment", + "dim_currency"] + + for file_name, df in dict_of_dfs.items(): + if file_name in immutable_df_dict: + table_name = file_name.split(".")[0] + try: + df.to_sql(table_name, con=db_engine, schema="project_team_2", if_exists="overwrite", index=False) + upload_status["uploaded"].append(table_name) + except Exception as e: + logger.error(f"Error uploading dataframe {file_name} to database: {e}") + raise + elif file_name.rsplit('_', 1)[0] in mutable_df_dict: + table_name = file_name.rsplit('_', 1)[0] + try: + df.to_sql(table_name, con=db_engine, schema="project_team_2", if_exists="overwrite", index=False) + upload_status["uploaded"].append(table_name) + except Exception as e: + logger.error(f"Error uploading dataframe {file_name} to database: {e}") + raise + else: + upload_status["not_uploaded"].append(file_name) + logger.error(f"{file_name} does not correspond with table in database") db_engine.dispose() - return uploaded - - # aiming to return a list of uploaded tables \ No newline at end of file + return upload_status \ No newline at end of file -- cgit v1.2.3 From e26b7be8331d89826fbf95e1b1bd4fe88186c307 Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 17:04:29 +0100 Subject: add updated tests --- tests/test_load_lambda.py | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index f1c2b01..3e42c2a 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -25,6 +25,9 @@ def mock_s3_client(aws_credentials): class TestLambdaHandler: pass +class TestRetrieveSecrets: + pass + class TestConnectToDBAndReturnEngine: pass @@ -58,7 +61,18 @@ class TestGetTransformBucket: assert result == "transform_bucket" class TestConvertParquetToDfs: - pass + def test_function_returns_empty_dictionary_if_no_files(self, mock_s3_client): + mock_s3_client.create_bucket( + Bucket="transform_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) + result = convert_parquet_files_to_dfs(bucket_name="transform_bucket", client=mock_s3_client) + assert result == {} + + def test_function_returns_dictionary_with_table_with_file_key(): + # need to mock parquet file and upload to mock bucket + result = convert_parquet_files_to_dfs(bucket_name="transform_bucket", client=mock_s3_client) + assert "dim_staff" in result class TestUploadDfsToDatabase: pass \ No newline at end of file -- cgit v1.2.3 From 0ff29566a1eb9551bb83bcc07705c932d22f8c08 Mon Sep 17 00:00:00 2001 From: Ellie Date: Fri, 23 Aug 2024 17:06:59 +0100 Subject: add updated test --- tests/test_load_lambda.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 3e42c2a..e04ccec 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -69,10 +69,10 @@ class TestConvertParquetToDfs: result = convert_parquet_files_to_dfs(bucket_name="transform_bucket", client=mock_s3_client) assert result == {} - def test_function_returns_dictionary_with_table_with_file_key(): - # need to mock parquet file and upload to mock bucket - result = convert_parquet_files_to_dfs(bucket_name="transform_bucket", client=mock_s3_client) - assert "dim_staff" in result + # def test_function_returns_dictionary_with_table_with_file_key(): + # # need to mock parquet file and upload to mock bucket + # result = convert_parquet_files_to_dfs(bucket_name="transform_bucket", client=mock_s3_client) + # assert "dim_staff" in result class TestUploadDfsToDatabase: pass \ No newline at end of file -- cgit v1.2.3 From 69edb14dad584d45fa6a83a90c08292b84795507 Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Fri, 23 Aug 2024 16:11:45 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 0ff2956 according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/95 --- src/load_lambda.py | 75 ++++++++++++++++++++++++++++++++--------------- tests/test_load_lambda.py | 44 +++++++++++++++++---------- 2 files changed, 80 insertions(+), 39 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 8eaea32..6e6bc80 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -40,6 +40,7 @@ def lambda_handler(event, context): logger.error(f"Error: {e}", exc_info=True) return {"statusCode": 500, "body": json.dumps("Internal server error.")} + def retrieve_secrets(): secret_name = "bentley-RDS-credentials" region_name = "eu-west-2" @@ -59,7 +60,10 @@ def retrieve_secrets(): return get_secret_value_response["SecretString"] + # connect to database, slightly different way of doing it, to allow manipulation through pandas + + def connect_to_db_and_return_engine(): try: secrets = json.loads(retrieve_secrets()) @@ -68,13 +72,14 @@ def connect_to_db_and_return_engine(): user = secrets["user"] password = secrets["password"] database = secrets["database"] - conn_str = f'postgresql+pg8000://{user}:{password}@{host}:{port}/{database}' - engine = create_engine(conn_str) #interface between python (pandas) and SQL + conn_str = f"postgresql+pg8000://{user}:{password}@{host}:{port}/{database}" + # interface between python (pandas) and SQL + engine = create_engine(conn_str) return engine except Exception as e: logger.error(f"Interface error: {e}") raise RuntimeError("Failed to create database engine") - + # get transform bucket def get_transform_bucket(client=None): @@ -85,9 +90,11 @@ def get_transform_bucket(client=None): except ClientError as e: logger.error(f"Error listing S3 buckets: {e}") raise RuntimeError("Error listing S3 buckets") - + transform_bucket_filter = [ - bucket["Name"] for bucket in response["Buckets"] if "transform" in bucket["Name"] + bucket["Name"] + for bucket in response["Buckets"] + if "transform" in bucket["Name"] ] if not transform_bucket_filter: @@ -96,9 +103,12 @@ def get_transform_bucket(client=None): return transform_bucket_filter[0] + # list and then retrieve parquet files from S3 bucket # convert parquet files into dataframes -# return a dictionary of dataframes with name as key, and dataframe object as value +# return a dictionary of dataframes with name as key, and dataframe object as value + + def convert_parquet_files_to_dfs(bucket_name=None, client=None): try: if client is None: @@ -110,10 +120,10 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): dfs = {} if "Contents" in files: for file in files["Contents"]: - file_key = file['Key'] + file_key = file["Key"] try: file_obj = client.get_object(Bucket=bucket_name, Key=file_key) - parquet_file = pq.ParquetFile(BytesIO(file_obj['Body'].read())) + parquet_file = pq.ParquetFile(BytesIO(file_obj["Body"].read())) df = parquet_file.read().to_pandas() dfs[file_key] = df except ClientError as e: @@ -132,34 +142,51 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None): return dfs + def upload_dfs_to_database(): upload_status = {"uploaded": [], "not_uploaded": []} dict_of_dfs = convert_parquet_files_to_dfs() db_engine = connect_to_db_and_return_engine() - immutable_df_dict = ["dim_counterparty.parquet", - "dim_date.parquet", #this needs to be mutable - "dim_location.parquet", - "dim_staff.parquet", - "dim_design.parquet"] - mutable_df_dict = ["fact_sales_order", - "fact_purchase_order", - "fact_payment", - "dim_currency"] - + immutable_df_dict = [ + "dim_counterparty.parquet", + "dim_date.parquet", # this needs to be mutable + "dim_location.parquet", + "dim_staff.parquet", + "dim_design.parquet", + ] + mutable_df_dict = [ + "fact_sales_order", + "fact_purchase_order", + "fact_payment", + "dim_currency", + ] + for file_name, df in dict_of_dfs.items(): if file_name in immutable_df_dict: table_name = file_name.split(".")[0] try: - df.to_sql(table_name, con=db_engine, schema="project_team_2", if_exists="overwrite", index=False) + df.to_sql( + table_name, + con=db_engine, + schema="project_team_2", + if_exists="overwrite", + index=False, + ) upload_status["uploaded"].append(table_name) except Exception as e: logger.error(f"Error uploading dataframe {file_name} to database: {e}") raise - elif file_name.rsplit('_', 1)[0] in mutable_df_dict: - table_name = file_name.rsplit('_', 1)[0] + elif file_name.rsplit("_", 1)[0] in mutable_df_dict: + table_name = file_name.rsplit("_", 1)[0] try: - df.to_sql(table_name, con=db_engine, schema="project_team_2", if_exists="overwrite", index=False) - upload_status["uploaded"].append(table_name) + df.to_sql( + table_name, + con=db_engine, + schema="project_team_2", + if_exists="overwrite", + index=False, + ) + upload_status["uploaded"].append(table_name) except Exception as e: logger.error(f"Error uploading dataframe {file_name} to database: {e}") raise @@ -167,4 +194,4 @@ def upload_dfs_to_database(): upload_status["not_uploaded"].append(file_name) logger.error(f"{file_name} does not correspond with table in database") db_engine.dispose() - return upload_status \ No newline at end of file + return upload_status diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index e04ccec..88c71e4 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -5,7 +5,14 @@ from moto import mock_aws import boto3 import os import pytest -from src.load_lambda import lambda_handler, connect_to_db_and_return_engine, get_transform_bucket, convert_parquet_files_to_dfs, upload_dfs_to_database +from src.load_lambda import ( + lambda_handler, + connect_to_db_and_return_engine, + get_transform_bucket, + convert_parquet_files_to_dfs, + upload_dfs_to_database, +) + @pytest.fixture(scope="class") def aws_credentials(): @@ -25,12 +32,15 @@ def mock_s3_client(aws_credentials): class TestLambdaHandler: pass + class TestRetrieveSecrets: pass + class TestConnectToDBAndReturnEngine: pass + class TestGetTransformBucket: def test_raises_value_error_if_no_buckets(self, mock_s3_client): with pytest.raises(ValueError, match="No transform bucket found"): @@ -38,35 +48,38 @@ class TestGetTransformBucket: def test_raises_value_error_if_no_transform_bucket(self, mock_s3_client): mock_s3_client.create_bucket( - Bucket="extract_bucket", - CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, - ) + Bucket="extract_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) with pytest.raises(ValueError, match="No transform bucket found"): get_transform_bucket(mock_s3_client) def test_returns_transform_bucket_if_one_bucket(self, mock_s3_client): mock_s3_client.create_bucket( - Bucket="transform_bucket", - CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, - ) + Bucket="transform_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) result = get_transform_bucket(mock_s3_client) assert result == "transform_bucket" def test_only_returns_transform_bucket_if_several_buckets(self, mock_s3_client): mock_s3_client.create_bucket( - Bucket="another_test_bucket", - CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, - ) + Bucket="another_test_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) result = get_transform_bucket(mock_s3_client) assert result == "transform_bucket" + class TestConvertParquetToDfs: def test_function_returns_empty_dictionary_if_no_files(self, mock_s3_client): mock_s3_client.create_bucket( - Bucket="transform_bucket", - CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, - ) - result = convert_parquet_files_to_dfs(bucket_name="transform_bucket", client=mock_s3_client) + Bucket="transform_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, + ) + result = convert_parquet_files_to_dfs( + bucket_name="transform_bucket", client=mock_s3_client + ) assert result == {} # def test_function_returns_dictionary_with_table_with_file_key(): @@ -74,5 +87,6 @@ class TestConvertParquetToDfs: # result = convert_parquet_files_to_dfs(bucket_name="transform_bucket", client=mock_s3_client) # assert "dim_staff" in result + class TestUploadDfsToDatabase: - pass \ No newline at end of file + pass -- cgit v1.2.3 From 151429859bca904cbacf18f4b169f1f768fa212a Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 12:01:53 +0100 Subject: remove import as not required --- src/load_lambda.py | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 6e6bc80..685c562 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -5,7 +5,6 @@ import pyarrow.parquet as pq from io import BytesIO import logging import json -from src.extract_lambda import retrieve_secrets from sqlalchemy import create_engine @@ -169,7 +168,7 @@ def upload_dfs_to_database(): table_name, con=db_engine, schema="project_team_2", - if_exists="overwrite", + if_exists="append", index=False, ) upload_status["uploaded"].append(table_name) @@ -183,7 +182,7 @@ def upload_dfs_to_database(): table_name, con=db_engine, schema="project_team_2", - if_exists="overwrite", + if_exists="append", index=False, ) upload_status["uploaded"].append(table_name) @@ -195,3 +194,6 @@ def upload_dfs_to_database(): logger.error(f"{file_name} does not correspond with table in database") db_engine.dispose() return upload_status + +if __name__ == "__main__": + lambda_handler(None, None) -- cgit v1.2.3 From a6765659cbeffeae48111f0797d3b4d0752ae80c Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 12:02:19 +0100 Subject: add test progress --- tests/test_load_lambda.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 88c71e4..30e55f3 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -18,7 +18,7 @@ from src.load_lambda import ( def aws_credentials(): os.environ["AWS_ACCESS_KEY_ID"] = "testing" os.environ["AWS_SECRET_ACCESS_KEY"] = "testing" - os.environ["AWS_SECURIT_TOKEN"] = "testing" + os.environ["AWS_SECURITY_TOKEN"] = "testing" os.environ["AWS_SESSION_TOKEN"] = "testing" os.environ["AWS_DEFAULT_REGION"] = "eu-west-2" @@ -88,5 +88,6 @@ class TestConvertParquetToDfs: # assert "dim_staff" in result -class TestUploadDfsToDatabase: - pass +@pytest.fixture +def mock_parquet_file(mocker): + return mocker.patch(src.load_lambda.convert_parquet_files_to_dfs()) -- cgit v1.2.3 From ec4a953ac73e6b828c61defe4d234a690461fcb6 Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 12:28:27 +0100 Subject: add first retrieve secrets test --- tests/test_load_lambda.py | 44 +++++++++++++++++++++++++++++++++----------- 1 file changed, 33 insertions(+), 11 deletions(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 30e55f3..3df94e4 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -5,13 +5,7 @@ from moto import mock_aws import boto3 import os import pytest -from src.load_lambda import ( - lambda_handler, - connect_to_db_and_return_engine, - get_transform_bucket, - convert_parquet_files_to_dfs, - upload_dfs_to_database, -) +from src.load_lambda import * @pytest.fixture(scope="class") @@ -27,14 +21,43 @@ def aws_credentials(): def mock_s3_client(aws_credentials): with mock_aws(): yield boto3.client("s3") + +@pytest.fixture(scope="class") +def mock_sm_client(aws_credentials): + with mock_aws(): + yield boto3.client("secretsmanager") + + +@pytest.fixture +def mock_parquet_file(mocker): + return mocker.patch("src.load_lambda.convert_parquet_files_to_dfs") class TestLambdaHandler: pass class TestRetrieveSecrets: - pass + def test_retrieve_secrets_returns_dictionary(self, mock_sm_client): + secret = { + "cohort_id": "test_cohort_id", + "user": "test_user_id", + "password": "test_password", + "host": "test_host", + "database": "test_database", + "port": "test_port", + } + + secret_name = "test_secret" + + mock_sm_client.create_secret( + Name=secret_name, SecretString=json.dumps(secret) + ) + + result = retrieve_secrets(mock_sm_client, secret_name) + + assert isinstance(result, dict) + class TestConnectToDBAndReturnEngine: @@ -88,6 +111,5 @@ class TestConvertParquetToDfs: # assert "dim_staff" in result -@pytest.fixture -def mock_parquet_file(mocker): - return mocker.patch(src.load_lambda.convert_parquet_files_to_dfs()) +def mock_connect_db(mocker): + return mocker.patch("src.load_lambda.connect_to_db_and_return_engine") \ No newline at end of file -- cgit v1.2.3 From 8cd9edde84f4ca706ad93b143c5ff7e3397ce981 Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 12:28:58 +0100 Subject: add json.loads to retrieve secrests function --- src/load_lambda.py | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 685c562..f08e335 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -40,16 +40,19 @@ def lambda_handler(event, context): return {"statusCode": 500, "body": json.dumps("Internal server error.")} -def retrieve_secrets(): - secret_name = "bentley-RDS-credentials" +def retrieve_secrets(client=None, secret_name=None): + session = boto3.session.Session() region_name = "eu-west-2" - # Create a Secrets Manager client - session = boto3.session.Session() - client = session.client(service_name="secretsmanager", region_name=region_name) + if secret_name == None: + secret_name = "bentley-RDS-credentials" + if client == None: + client = session.client(service_name="secretsmanager", region_name=region_name) + try: get_secret_value_response = client.get_secret_value(SecretId=secret_name) + print(get_secret_value_response) except ClientError as e: logger.error(f"Failed to retrieve secret {secret_name}: {str(e)}") raise e @@ -57,7 +60,7 @@ def retrieve_secrets(): logger.error(f"Secret {secret_name} does not contain a SecretString") raise ValueError(f"Secret {secret_name} does not contain a SecretString") - return get_secret_value_response["SecretString"] + return json.loads(get_secret_value_response["SecretString"]) # connect to database, slightly different way of doing it, to allow manipulation through pandas -- cgit v1.2.3 From a05a3718621b2c30b4357e2b90af6da0d89c6990 Mon Sep 17 00:00:00 2001 From: Ang Bel Date: Tue, 27 Aug 2024 12:42:25 +0100 Subject: test: fact transformation function for payment test passes, other fact functions are equivalent, no tests written --- src/dataframes.py | 251 ++++++++++++++--------------------------- tests/test_dataframes.py | 144 +++++++++++++++++++++++ tests/test_fact_sales_order.py | 246 ---------------------------------------- 3 files changed, 229 insertions(+), 412 deletions(-) create mode 100644 tests/test_dataframes.py delete mode 100644 tests/test_fact_sales_order.py diff --git a/src/dataframes.py b/src/dataframes.py index ab53063..41f39b8 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -2,7 +2,7 @@ import pandas as pd from bs4 import BeautifulSoup import requests -# Table names: +#Table names: # fact_sales_order # fact_purchase_orders # fact_payment @@ -16,214 +16,133 @@ import requests # dim_counterparty +#no test, same as fact_payment def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - df_sales["created_date"] = pd.to_datetime(df_sales["created_at"]).dt.date - df_sales["created_time"] = pd.to_datetime(df_sales["created_at"]).dt.time - df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"]).dt.date - df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time - fact_sales_order = df_sales.loc[ - :, - [ - "sales_record_id", - "sales_order_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "sales_staff_id", - "counterparty_id", - "units_sold", - "unit_price", - "currency_id", - "design_id", - "agreed_payment_date", - "agreed_delivery_date", - "agreed_delivery_location_id", - ], - ] - return fact_sales_order - - -# fact_purchase_order from purchase_order - - + df_sales["created_date"] = pd.to_datetime(df_sales["created_at"],format='%Y-%m-%d') + df_sales["created_time"] = pd.to_datetime(df_sales["created_at"],format='%H-%M-%S') + df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"],format='%Y-%m-%d') + df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"],format='%H-%M-%S') + df_sales['agreed_delivery_date'] = pd.to_datetime(df_sales['agreed_delivery_date'],format="%Y-%m-%d") + df_sales['agreed_payment_date'] = pd.to_datetime(df_sales['agreed_payment_date'],format="%Y-%m-%d") + df_sales.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_sales.reset_index(inplace=True) + return df_sales + +#no test, same as fact_payment def create_fact_purchase_orders(dict_of_df): - df_po = dict_of_df["purchase_order"] - df_po.index.name = "purchase_record_id" - df_po["created_date"] = df_po["created_at"].date() - df_po["created_time"] = df_po["created_at"].dt.time - df_po["last_updated_date"] = df_po["last_updated_at"].date() - df_po["last_updated_time"] = df_po["last_updated_at"].dt.time - df_po["agreed_delivery_date"] = pd.to_datetime( - df_po["agreed_delivery_date"], format="%Y-%m-%d" - ) - df_po["agreed_payment_date"] = pd.to_datetime( - df_po["agreed_payment_date"], format="%Y-%m-%d" - ) - df_po.drop(labels=["created_at", "last_updated_at"], axis=1, inplace=True) + df_po = dict_of_df['purchase_order'] + df_po.index.name = 'purchase_record_id' + df_po['created_date'] = pd.to_datetime(df_po['created_at'],format='%Y-%m-%d') + df_po['created_time'] = pd.to_datetime(df_po['created_at'],format='%H-%M-%S') + df_po['last_updated_date'] = pd.to_datetime(df_po['last_updated'],format='%Y-%m-%d') + df_po['last_updated_time'] = pd.to_datetime(df_po['last_updated'],format='%H-%M-%S') + df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") + df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") + df_po.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_po.reset_index(inplace=True) return df_po - +#test passed def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = df_payment["created_at"].date() - df_payment["created_time"] = df_payment["created_at"].time - df_payment["last_updated_date"] = df_payment["last_updated"].date() - df_payment["last_updated_time"] = df_payment["last_updated"].time - df_payment["payment_date"] = pd.to_datetime( - df_payment["payment_date"], format="%Y-%m-%d" - ) - fact_payment = df_payment.loc[ - :, - [ - "payment_record_id", - "payment_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "transaction_id", - "counterparty_id", - "payment_amount", - "currency_id", - "payment_type_id", - "paid", - "payment_date", - ], - ] - return fact_payment - - -# test passed - - + df_payment["created_date"] = pd.to_datetime(df_payment["created_at"],format='%Y-%m-%d') + df_payment["created_time"] = pd.to_datetime(df_payment["created_at"],format='%H-%M-%S') + df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"],format='%Y-%m-%d') + df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"],format='%H-%M-%S') + df_payment['payment_date'] = pd.to_datetime(df_payment['payment_date'],format="%Y-%m-%d") + df_payment.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_payment.reset_index(inplace=True) + return df_payment + +#test passed def create_dim_transaction(dict_of_df): - df_transaction = dict_of_df["transaction"].drop( - labels=["created_at", "last_updated"], axis=1 - ) + df_transaction = dict_of_df["transaction"].drop(labels=['created_at', 'last_updated'], axis=1) return df_transaction - -# test passed +#test passed def create_dim_location(dict_of_df): - df_loc = ( - dict_of_df["address"] - .drop(labels=["created_at", "last_updated"], axis=1) - .rename(columns={"address_id": "location_id"}) - ) + df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}) return df_loc def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df["address"].add_prefix( - "counterparty_legal_", axis=1 - ) - df_cp = pd.merge( - dict_of_df["counterparty"], - df_prefixed_address, - left_on="legal_address_id", - right_on="counterparty_legal_address_id", - how="outer", - ) - df_cp.drop( - columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True - ) + df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) + df_cp = pd.merge(dict_of_df['counterparty'], + df_prefixed_address, + left_on="legal_address_id", + right_on="counterparty_legal_address_id", + how="outer") + df_cp.drop(columns=["legal_address_id","counterparty_legal_address_id"],inplace=True) return df_cp - -# test passed - - +#test passed def create_dim_date(dict_of_df): - fact_dfs = [ - create_fact_payment(dict_of_df), - create_fact_purchase_orders(dict_of_df), - create_fact_sales_order(dict_of_df), - ] - date_col_names = [ - col_name for col_name in list(fact_dfs[0].columns) if "date" in col_name - ] + fact_dfs = [create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df)] list_of_date_columns = [] for df in fact_dfs: + date_col_names = [col_name for col_name in list(df.columns) if 'date' in col_name] for col in date_col_names: list_of_date_columns.append(df[col]) - sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") - df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) + sr_date = pd.array(pd.concat(list_of_date_columns),dtype='datetime64[ns]') + df_date = pd.DataFrame(data=sr_date,columns=['date_id']) df_date.drop_duplicates(inplace=True) - df_date["year"] = df_date["date_id"].dt.year - df_date["month"] = df_date["date_id"].dt.month - df_date["day"] = df_date["date_id"].dt.day - df_date["day_of_week"] = df_date["date_id"].dt.dayofweek - df_date["day_name"] = df_date["date_id"].dt.day_name() - df_date["month_name"] = df_date["date_id"].dt.month_name() - df_date["quarter"] = df_date["date_id"].dt.quarter + df_date['year'] = df_date['date_id'].dt.year + df_date['month'] = df_date['date_id'].dt.month + df_date['day'] = df_date['date_id'].dt.day + df_date['day_of_week'] = df_date['date_id'].dt.dayofweek + df_date['day_name'] = df_date['date_id'].dt.day_name() + df_date['month_name'] = df_date['date_id'].dt.month_name() + df_date['quarter'] = df_date['date_id'].dt.quarter return df_date - -# tests passed +#tests passed def scrape_currency_names(): - response = requests.get("https://www.xe.com/currency/").content - soup = BeautifulSoup(response, "html.parser") - currency = [ - item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) - ] + response = requests.get('https://www.xe.com/currency/').content + soup = BeautifulSoup(response,'html.parser') + currency = [item.text for item in soup.findAll('a', attrs={'class' : "sc-299dec64-6 fZPTSw"})] sr = pd.Series(currency) - df_cur = sr.str.split(pat=" - ", expand=True).rename( - {0: "currency_code", 1: "currency_name"}, axis=1 - ) + df_cur = sr.str.split(pat=" - ",expand=True).rename({0:'currency_code',1:'currency_name'},axis=1) return df_cur +#tests passed +def create_dim_currency(dict_of_df,names=scrape_currency_names()): + df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1) + dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner') + return dim_cur + +#tests passed +def create_dim_payment_type(dict_of_df): + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + return dim_payment_type + +#tests passed +def create_dim_design(dict_of_df): + df_design = dict_of_df["design"] + dim_design = df_design.loc[:, ["design_id", "design_name", "file_name", "file_location"]] + return dim_design +#tests passed +def create_dim_staff(dict_of_df): + staff_department = pd.merge(dict_of_df["staff"], dict_of_df["department"], on='department_id', how="left") + dim_staff = staff_department.loc[:, ['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address']] + return dim_staff + + -# tests passed -def create_dim_currency(dict_of_df, names=scrape_currency_names()): - df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) - dim_cur = pd.merge( - df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" - ) - return dim_cur -# tests passed -def create_dim_payment_type(dict_of_df): - df_payment_type = dict_of_df["payment_type"] - dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] - return dim_payment_type -# tests passed -def create_dim_design(dict_of_df): - df_design = dict_of_df["design"] - dim_design = df_design.loc[ - :, ["design_id", "design_name", "file_name", "file_location"] - ] - return dim_design -# tests passed -def create_dim_staff(dict_of_df): - staff_department = pd.merge( - dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" - ) - dim_staff = staff_department.loc[ - :, - [ - "staff_id", - "first_name", - "last_name", - "department_name", - "location", - "email_address", - ], - ] - return dim_staff diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py new file mode 100644 index 0000000..8f32b1d --- /dev/null +++ b/tests/test_dataframes.py @@ -0,0 +1,144 @@ +from src.dataframes import * +import pandas as pd +from unittest.mock import patch +from datetime import datetime as dt + +class TestCreateDimDesign: + def test_dim_design_returns_dataframe(self): + d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + test_df = {"design": pd.DataFrame(data=d)} + result = create_dim_design(test_df) + assert isinstance(result, pd.DataFrame) + + def test_dim_design_returns_correct_columns_and_values(self): + d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + test_df = {"design": pd.DataFrame(data=d)} + result = create_dim_design(test_df) + d2 = {"design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"]} + expected_df = pd.DataFrame(data=d2) + expected_result = expected_df.copy() + assert result.equals(expected_result) + +class TestCreateDimStaff: + def test_dim_staff_returns_dataframe(self): + d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} + result = create_dim_staff(test_df) + assert isinstance(result, pd.DataFrame) + + def test_dim_staff_returns_correct_columns_and_values(self): + d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} + result = create_dim_staff(test_df) + expected_d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"]} + expected_df = pd.DataFrame(data=expected_d) + expected_result = expected_df.copy() + assert result.equals(expected_result) + +class TestCreatePaymentType: + def test_create_dim_payment_type_returns_correct_columns_and_values(self): + d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} + test_df = {"payment_type": pd.DataFrame(data=d)} + result = create_dim_payment_type(test_df) + expected_columns = ["payment_type_id", "payment_type_name"] + expected_d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} + expected_df = pd.DataFrame(data=expected_d) + assert isinstance(result, pd.DataFrame) + assert list(result.columns) == expected_columns + assert result.equals(expected_df) + +class TestCreateDimCounterparty: + + def test_create_dim_counterparty_type_returns_correct_columns_and_object(self): + data_l = pd.DataFrame(data={"counterparty_id": ["Hello", "Bye"], + "counterparty_legal_name": ["Hello", "Bye"], + "commercial_contact": ["Hello", "Bye"], + "legal_address_id": ["bond street", "regent street"]}) + data_a = pd.DataFrame(data={"address_id":["bond street", "regent street"], + "postcode":[98365,93753]}) + test_df = {"address": data_a,"counterparty":data_l} + result = create_dim_counterparty(test_df) + + expected_columns = ["counterparty_id", "counterparty_legal_name", + "commercial_contact", "counterparty_legal_postcode"] + print(data_l) + print(data_a) + assert isinstance(result, pd.DataFrame) + assert list(result.columns) == expected_columns + +class TestCreateDimCurrency: + + def test_dim_currency_returns_columns_and_values(self): + nones = [None,None,None] + d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"],"created_at":nones,"last_updated":nones} + test_df = {"currency": pd.DataFrame(data=d)} + scraper_output = pd.DataFrame({"currency_code":["RUS","USD","PHP","GBP","EUR"],"currency_name":["Rubble","US Dollar","Peso","Pound","Euro"]}) + result = create_dim_currency(test_df,names=scraper_output).sort_values(by="currency_code",axis=0) + expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} + expected_df = pd.DataFrame(data=expected_d).sort_values(by="currency_code",axis=0) + assert isinstance(result, pd.DataFrame) + assert result.equals(expected_df) + + def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self): + result = scrape_currency_names() + assert isinstance(result,pd.DataFrame) + assert list(result.columns) == ['currency_code', 'currency_name'] + +class TestCreateDimDate: + + def test_returns_required_columns(self): + df_one = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 5, 13),'not_dat':None},index=[0]) + df_two = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 9, 13)},index=[0]) + df_three = pd.DataFrame(data={'updated_date':dt(2022, 5, 17),'created_date':dt(2023, 5, 13)},index=[0]) + expected_df = pd.DataFrame(data= + [[dt(2020,5,17),2020,5,17,6,'Sunday','May',2], + [dt(2021,5,13),2021,5,13,3,'Thursday','May',2], + [dt(2021,9,13),2021,9,13,0,'Monday','September',3], + [dt(2022,5,17),2022,5,17,1,'Tuesday','May',2], + [dt(2023,5,13),2023,5,13,5,'Saturday','May',2]], + columns=['date_id','year','month','day','day_of_week','day_name','month_name','quarter']) + with patch("src.dataframes.create_fact_payment") as mock_fp: + with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo: + with patch("src.dataframes.create_fact_sales_order") as mock_fso: + mock_fp.return_value = df_one + mock_fpo.return_value = df_two + mock_fso.return_value = df_three + result = create_dim_date({'dum':0}) + result.reset_index(inplace=True,drop=True) + assert result.eq(expected_df, axis="columns").all(axis=None) + +class TestCreateDimLocation: + + def test_returns_correct_columns_lo(self): + dict_df = {'address':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], + columns=['created_at','last_updated','address_id','postal_code'])} + result = create_dim_location(dict_df) + assert list(result.columns) == ['location_id','postal_code'] + +class TestCreateDimTransaction: + def test_returns_correct_columns_tr(self): + dict_df = {'transaction':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], + columns=['created_at','last_updated','transaction_id','some_other_id'])} + result = create_dim_transaction(dict_df) + assert list(result.columns) == ['transaction_id','some_other_id'] + +class TestCreateFactPayment: + def test_returns_correct_columns_payment(self): + dict_df = {'payment':pd.DataFrame(data=[[dt(2020,5,17,6,15,20),dt(2020,5,20,8,19,30),1,'SE18 9QO','2020-7-16']], + columns=['created_at','last_updated','payment_id','some_other_id','payment_date'])} + expected_cols = ['payment_record_id','created_date','created_time','last_updated_date', + 'last_updated_time','payment_date','payment_id','some_other_id'] + result = create_fact_payment(dict_df) + assert isinstance(result,pd.DataFrame) + for col in list(result.columns): + assert col in expected_cols + for col in expected_cols: + if 'date' in col: + assert result[col].dtype == 'datetime64[ns]' + + \ No newline at end of file diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py deleted file mode 100644 index a245379..0000000 --- a/tests/test_fact_sales_order.py +++ /dev/null @@ -1,246 +0,0 @@ -from src.dataframes import * -import pandas as pd -from unittest.mock import patch -from datetime import datetime as dt - - -class TestCreateDimDesign: - def test_dim_design_returns_dataframe(self): - d = { - "test": ["Hello", "Bye"], - "design_id": ["Hello", "Bye"], - "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"], - "Hello": ["Hello", "Bye"], - } - test_df = {"design": pd.DataFrame(data=d)} - result = create_dim_design(test_df) - assert isinstance(result, pd.DataFrame) - - def test_dim_design_returns_correct_columns_and_values(self): - d = { - "test": ["Hello", "Bye"], - "design_id": ["Hello", "Bye"], - "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"], - "Hello": ["Hello", "Bye"], - } - test_df = {"design": pd.DataFrame(data=d)} - result = create_dim_design(test_df) - d2 = { - "design_id": ["Hello", "Bye"], - "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"], - } - expected_df = pd.DataFrame(data=d2) - expected_result = expected_df.copy() - assert result.equals(expected_result) - - -class TestCreateDimStaff: - def test_dim_staff_returns_dataframe(self): - d = { - "staff_id": ["Hello", "Bye"], - "first_name": ["Hello", "Bye"], - "last_name": ["Hello", "Bye"], - "department_id": ["Hello", "Bye"], - } - d2 = { - "department_name": ["Hello", "Bye"], - "location": ["Hello", "Bye"], - "email_address": ["Hello", "Bye"], - "department_id": ["Hello", "Bye"], - } - test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} - result = create_dim_staff(test_df) - assert isinstance(result, pd.DataFrame) - - def test_dim_staff_returns_correct_columns_and_values(self): - d = { - "staff_id": ["Hello", "Bye"], - "first_name": ["Hello", "Bye"], - "last_name": ["Hello", "Bye"], - "department_id": ["Hello", "Bye"], - } - d2 = { - "department_name": ["Hello", "Bye"], - "location": ["Hello", "Bye"], - "email_address": ["Hello", "Bye"], - "department_id": ["Hello", "Bye"], - } - test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} - result = create_dim_staff(test_df) - expected_d = { - "staff_id": ["Hello", "Bye"], - "first_name": ["Hello", "Bye"], - "last_name": ["Hello", "Bye"], - "department_name": ["Hello", "Bye"], - "location": ["Hello", "Bye"], - "email_address": ["Hello", "Bye"], - } - expected_df = pd.DataFrame(data=expected_d) - expected_result = expected_df.copy() - assert result.equals(expected_result) - - -class TestCreatePaymentType: - def test_create_dim_payment_type_returns_correct_columns_and_values(self): - d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} - test_df = {"payment_type": pd.DataFrame(data=d)} - result = create_dim_payment_type(test_df) - expected_columns = ["payment_type_id", "payment_type_name"] - expected_d = { - "payment_type_id": ["Hello", "Bye"], - "payment_type_name": ["Hello", "Bye"], - } - expected_df = pd.DataFrame(data=expected_d) - assert isinstance(result, pd.DataFrame) - assert list(result.columns) == expected_columns - assert result.equals(expected_df) - - -class TestCreateDimCounterparty: - def test_create_dim_counterparty_type_returns_correct_columns_and_object(self): - data_l = pd.DataFrame( - data={ - "counterparty_id": ["Hello", "Bye"], - "counterparty_legal_name": ["Hello", "Bye"], - "commercial_contact": ["Hello", "Bye"], - "legal_address_id": ["bond street", "regent street"], - } - ) - data_a = pd.DataFrame( - data={ - "address_id": ["bond street", "regent street"], - "postcode": [98365, 93753], - } - ) - test_df = {"address": data_a, "counterparty": data_l} - result = create_dim_counterparty(test_df) - - expected_columns = [ - "counterparty_id", - "counterparty_legal_name", - "commercial_contact", - "counterparty_legal_postcode", - ] - print(data_l) - print(data_a) - assert isinstance(result, pd.DataFrame) - assert list(result.columns) == expected_columns - - -class TestCreateDimCurrency: - def test_dim_currency_returns_columns_and_values(self): - nones = [None, None, None] - d = { - "currency_id": [1, 2, 3], - "currency_code": ["USD", "EUR", "GBP"], - "created_at": nones, - "last_updated": nones, - } - test_df = {"currency": pd.DataFrame(data=d)} - scraper_output = pd.DataFrame( - { - "currency_code": ["RUS", "USD", "PHP", "GBP", "EUR"], - "currency_name": ["Rubble", "US Dollar", "Peso", "Pound", "Euro"], - } - ) - result = create_dim_currency(test_df, names=scraper_output).sort_values( - by="currency_code", axis=0 - ) - expected_d = { - "currency_id": [1, 2, 3], - "currency_code": ["USD", "EUR", "GBP"], - "currency_name": ["US Dollar", "Euro", "Pound"], - } - expected_df = pd.DataFrame(data=expected_d).sort_values( - by="currency_code", axis=0 - ) - assert isinstance(result, pd.DataFrame) - assert result.equals(expected_df) - - def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self): - result = scrape_currency_names() - assert isinstance(result, pd.DataFrame) - assert list(result.columns) == ["currency_code", "currency_name"] - - -class TestCreateDimDate: - def test_returns_required_columns(self): - df_one = pd.DataFrame( - data={ - "updated_date": dt(2020, 5, 17), - "created_date": dt(2021, 5, 13), - "not_dat": None, - }, - index=[0], - ) - df_two = pd.DataFrame( - data={"updated_date": dt(2020, 5, 17), "created_date": dt(2021, 9, 13)}, - index=[0], - ) - df_three = pd.DataFrame( - data={"updated_date": dt(2022, 5, 17), "created_date": dt(2023, 5, 13)}, - index=[0], - ) - expected_df = pd.DataFrame( - data=[ - [dt(2020, 5, 17), 2020, 5, 17, 6, "Sunday", "May", 2], - [dt(2021, 5, 13), 2021, 5, 13, 3, "Thursday", "May", 2], - [dt(2021, 9, 13), 2021, 9, 13, 0, "Monday", "September", 3], - [dt(2022, 5, 17), 2022, 5, 17, 1, "Tuesday", "May", 2], - [dt(2023, 5, 13), 2023, 5, 13, 5, "Saturday", "May", 2], - ], - columns=[ - "date_id", - "year", - "month", - "day", - "day_of_week", - "day_name", - "month_name", - "quarter", - ], - ) - with patch("src.dataframes.create_fact_payment") as mock_fp: - with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo: - with patch("src.dataframes.create_fact_sales_order") as mock_fso: - mock_fp.return_value = df_one - mock_fpo.return_value = df_two - mock_fso.return_value = df_three - result = create_dim_date({"dum": 0}) - result.reset_index(inplace=True, drop=True) - assert result.eq(expected_df, axis="columns").all(axis=None) - - -class TestCreateDimLocation: - def test_returns_correct_columns_lo(self): - dict_df = { - "address": pd.DataFrame( - data=[["some_time", "some_other_time", 1, "SE18 9QO"]], - columns=["created_at", "last_updated", "address_id", "postal_code"], - ) - } - result = create_dim_location(dict_df) - assert list(result.columns) == ["location_id", "postal_code"] - - -class TestCreateDimTransaction: - def test_returns_correct_columns_tr(self): - dict_df = { - "transaction": pd.DataFrame( - data=[["some_time", "some_other_time", 1, "SE18 9QO"]], - columns=[ - "created_at", - "last_updated", - "transaction_id", - "some_other_id", - ], - ) - } - result = create_dim_transaction(dict_df) - assert list(result.columns) == ["transaction_id", "some_other_id"] -- cgit v1.2.3 From 5db3f61032221331855ff3bc5a5d3362506c0d29 Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Tue, 27 Aug 2024 11:44:00 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in a05a371 according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/98 --- src/dataframes.py | 234 ++++++++++++++++++++++++++------------- tests/test_dataframes.py | 277 +++++++++++++++++++++++++++++++++++------------ 2 files changed, 366 insertions(+), 145 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 41f39b8..e60123a 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -2,7 +2,7 @@ import pandas as pd from bs4 import BeautifulSoup import requests -#Table names: +# Table names: # fact_sales_order # fact_purchase_orders # fact_payment @@ -16,133 +16,211 @@ import requests # dim_counterparty -#no test, same as fact_payment +# no test, same as fact_payment def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - df_sales["created_date"] = pd.to_datetime(df_sales["created_at"],format='%Y-%m-%d') - df_sales["created_time"] = pd.to_datetime(df_sales["created_at"],format='%H-%M-%S') - df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"],format='%Y-%m-%d') - df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"],format='%H-%M-%S') - df_sales['agreed_delivery_date'] = pd.to_datetime(df_sales['agreed_delivery_date'],format="%Y-%m-%d") - df_sales['agreed_payment_date'] = pd.to_datetime(df_sales['agreed_payment_date'],format="%Y-%m-%d") - df_sales.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_sales["created_date"] = pd.to_datetime(df_sales["created_at"], format="%Y-%m-%d") + df_sales["created_time"] = pd.to_datetime(df_sales["created_at"], format="%H-%M-%S") + df_sales["last_updated_date"] = pd.to_datetime( + df_sales["last_updated"], format="%Y-%m-%d" + ) + df_sales["last_updated_time"] = pd.to_datetime( + df_sales["last_updated"], format="%H-%M-%S" + ) + df_sales["agreed_delivery_date"] = pd.to_datetime( + df_sales["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_sales["agreed_payment_date"] = pd.to_datetime( + df_sales["agreed_payment_date"], format="%Y-%m-%d" + ) + df_sales.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) df_sales.reset_index(inplace=True) return df_sales -#no test, same as fact_payment + +# no test, same as fact_payment + + def create_fact_purchase_orders(dict_of_df): - df_po = dict_of_df['purchase_order'] - df_po.index.name = 'purchase_record_id' - df_po['created_date'] = pd.to_datetime(df_po['created_at'],format='%Y-%m-%d') - df_po['created_time'] = pd.to_datetime(df_po['created_at'],format='%H-%M-%S') - df_po['last_updated_date'] = pd.to_datetime(df_po['last_updated'],format='%Y-%m-%d') - df_po['last_updated_time'] = pd.to_datetime(df_po['last_updated'],format='%H-%M-%S') - df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") - df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") - df_po.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_po = dict_of_df["purchase_order"] + df_po.index.name = "purchase_record_id" + df_po["created_date"] = pd.to_datetime(df_po["created_at"], format="%Y-%m-%d") + df_po["created_time"] = pd.to_datetime(df_po["created_at"], format="%H-%M-%S") + df_po["last_updated_date"] = pd.to_datetime( + df_po["last_updated"], format="%Y-%m-%d" + ) + df_po["last_updated_time"] = pd.to_datetime( + df_po["last_updated"], format="%H-%M-%S" + ) + df_po["agreed_delivery_date"] = pd.to_datetime( + df_po["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_po["agreed_payment_date"] = pd.to_datetime( + df_po["agreed_payment_date"], format="%Y-%m-%d" + ) + df_po.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) df_po.reset_index(inplace=True) return df_po -#test passed + +# test passed + + def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = pd.to_datetime(df_payment["created_at"],format='%Y-%m-%d') - df_payment["created_time"] = pd.to_datetime(df_payment["created_at"],format='%H-%M-%S') - df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"],format='%Y-%m-%d') - df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"],format='%H-%M-%S') - df_payment['payment_date'] = pd.to_datetime(df_payment['payment_date'],format="%Y-%m-%d") - df_payment.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_payment["created_date"] = pd.to_datetime( + df_payment["created_at"], format="%Y-%m-%d" + ) + df_payment["created_time"] = pd.to_datetime( + df_payment["created_at"], format="%H-%M-%S" + ) + df_payment["last_updated_date"] = pd.to_datetime( + df_payment["last_updated"], format="%Y-%m-%d" + ) + df_payment["last_updated_time"] = pd.to_datetime( + df_payment["last_updated"], format="%H-%M-%S" + ) + df_payment["payment_date"] = pd.to_datetime( + df_payment["payment_date"], format="%Y-%m-%d" + ) + df_payment.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) df_payment.reset_index(inplace=True) return df_payment -#test passed + +# test passed + + def create_dim_transaction(dict_of_df): - df_transaction = dict_of_df["transaction"].drop(labels=['created_at', 'last_updated'], axis=1) + df_transaction = dict_of_df["transaction"].drop( + labels=["created_at", "last_updated"], axis=1 + ) return df_transaction -#test passed + +# test passed + + def create_dim_location(dict_of_df): - df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}) + df_loc = ( + dict_of_df["address"] + .drop(labels=["created_at", "last_updated"], axis=1) + .rename(columns={"address_id": "location_id"}) + ) return df_loc def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) - df_cp = pd.merge(dict_of_df['counterparty'], - df_prefixed_address, - left_on="legal_address_id", - right_on="counterparty_legal_address_id", - how="outer") - df_cp.drop(columns=["legal_address_id","counterparty_legal_address_id"],inplace=True) + df_prefixed_address = dict_of_df["address"].add_prefix( + "counterparty_legal_", axis=1 + ) + df_cp = pd.merge( + dict_of_df["counterparty"], + df_prefixed_address, + left_on="legal_address_id", + right_on="counterparty_legal_address_id", + how="outer", + ) + df_cp.drop( + columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True + ) return df_cp -#test passed + +# test passed + + def create_dim_date(dict_of_df): - fact_dfs = [create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df)] + fact_dfs = [ + create_fact_payment(dict_of_df), + create_fact_purchase_orders(dict_of_df), + create_fact_sales_order(dict_of_df), + ] list_of_date_columns = [] for df in fact_dfs: - date_col_names = [col_name for col_name in list(df.columns) if 'date' in col_name] + date_col_names = [ + col_name for col_name in list(df.columns) if "date" in col_name + ] for col in date_col_names: list_of_date_columns.append(df[col]) - sr_date = pd.array(pd.concat(list_of_date_columns),dtype='datetime64[ns]') - df_date = pd.DataFrame(data=sr_date,columns=['date_id']) + sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") + df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) df_date.drop_duplicates(inplace=True) - df_date['year'] = df_date['date_id'].dt.year - df_date['month'] = df_date['date_id'].dt.month - df_date['day'] = df_date['date_id'].dt.day - df_date['day_of_week'] = df_date['date_id'].dt.dayofweek - df_date['day_name'] = df_date['date_id'].dt.day_name() - df_date['month_name'] = df_date['date_id'].dt.month_name() - df_date['quarter'] = df_date['date_id'].dt.quarter + df_date["year"] = df_date["date_id"].dt.year + df_date["month"] = df_date["date_id"].dt.month + df_date["day"] = df_date["date_id"].dt.day + df_date["day_of_week"] = df_date["date_id"].dt.dayofweek + df_date["day_name"] = df_date["date_id"].dt.day_name() + df_date["month_name"] = df_date["date_id"].dt.month_name() + df_date["quarter"] = df_date["date_id"].dt.quarter return df_date -#tests passed -def scrape_currency_names(): - response = requests.get('https://www.xe.com/currency/').content - soup = BeautifulSoup(response,'html.parser') - currency = [item.text for item in soup.findAll('a', attrs={'class' : "sc-299dec64-6 fZPTSw"})] - sr = pd.Series(currency) - df_cur = sr.str.split(pat=" - ",expand=True).rename({0:'currency_code',1:'currency_name'},axis=1) - return df_cur - -#tests passed -def create_dim_currency(dict_of_df,names=scrape_currency_names()): - df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1) - dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner') - return dim_cur -#tests passed -def create_dim_payment_type(dict_of_df): - df_payment_type = dict_of_df["payment_type"] - dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] - return dim_payment_type +# tests passed -#tests passed -def create_dim_design(dict_of_df): - df_design = dict_of_df["design"] - dim_design = df_design.loc[:, ["design_id", "design_name", "file_name", "file_location"]] - return dim_design -#tests passed -def create_dim_staff(dict_of_df): - staff_department = pd.merge(dict_of_df["staff"], dict_of_df["department"], on='department_id', how="left") - dim_staff = staff_department.loc[:, ['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address']] - return dim_staff +def scrape_currency_names(): + response = requests.get("https://www.xe.com/currency/").content + soup = BeautifulSoup(response, "html.parser") + currency = [ + item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) + ] + sr = pd.Series(currency) + df_cur = sr.str.split(pat=" - ", expand=True).rename( + {0: "currency_code", 1: "currency_name"}, axis=1 + ) + return df_cur +# tests passed +def create_dim_currency(dict_of_df, names=scrape_currency_names()): + df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) + dim_cur = pd.merge( + df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" + ) + return dim_cur +# tests passed +def create_dim_payment_type(dict_of_df): + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + return dim_payment_type +# tests passed +def create_dim_design(dict_of_df): + df_design = dict_of_df["design"] + dim_design = df_design.loc[ + :, ["design_id", "design_name", "file_name", "file_location"] + ] + return dim_design +# tests passed +def create_dim_staff(dict_of_df): + staff_department = pd.merge( + dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" + ) + dim_staff = staff_department.loc[ + :, + [ + "staff_id", + "first_name", + "last_name", + "department_name", + "location", + "email_address", + ], + ] + return dim_staff diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index 8f32b1d..584ab27 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -3,42 +3,88 @@ import pandas as pd from unittest.mock import patch from datetime import datetime as dt + class TestCreateDimDesign: def test_dim_design_returns_dataframe(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) assert isinstance(result, pd.DataFrame) def test_dim_design_returns_correct_columns_and_values(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) - d2 = {"design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"]} + d2 = { + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=d2) expected_result = expected_df.copy() assert result.equals(expected_result) + class TestCreateDimStaff: def test_dim_staff_returns_dataframe(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - assert isinstance(result, pd.DataFrame) + assert isinstance(result, pd.DataFrame) def test_dim_staff_returns_correct_columns_and_values(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - expected_d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"]} + expected_d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) expected_result = expected_df.copy() - assert result.equals(expected_result) + assert result.equals(expected_result) + class TestCreatePaymentType: def test_create_dim_payment_type_returns_correct_columns_and_values(self): @@ -46,99 +92,196 @@ class TestCreatePaymentType: test_df = {"payment_type": pd.DataFrame(data=d)} result = create_dim_payment_type(test_df) expected_columns = ["payment_type_id", "payment_type_name"] - expected_d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} + expected_d = { + "payment_type_id": ["Hello", "Bye"], + "payment_type_name": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns assert result.equals(expected_df) + class TestCreateDimCounterparty: - def test_create_dim_counterparty_type_returns_correct_columns_and_object(self): - data_l = pd.DataFrame(data={"counterparty_id": ["Hello", "Bye"], - "counterparty_legal_name": ["Hello", "Bye"], - "commercial_contact": ["Hello", "Bye"], - "legal_address_id": ["bond street", "regent street"]}) - data_a = pd.DataFrame(data={"address_id":["bond street", "regent street"], - "postcode":[98365,93753]}) - test_df = {"address": data_a,"counterparty":data_l} + data_l = pd.DataFrame( + data={ + "counterparty_id": ["Hello", "Bye"], + "counterparty_legal_name": ["Hello", "Bye"], + "commercial_contact": ["Hello", "Bye"], + "legal_address_id": ["bond street", "regent street"], + } + ) + data_a = pd.DataFrame( + data={ + "address_id": ["bond street", "regent street"], + "postcode": [98365, 93753], + } + ) + test_df = {"address": data_a, "counterparty": data_l} result = create_dim_counterparty(test_df) - expected_columns = ["counterparty_id", "counterparty_legal_name", - "commercial_contact", "counterparty_legal_postcode"] + expected_columns = [ + "counterparty_id", + "counterparty_legal_name", + "commercial_contact", + "counterparty_legal_postcode", + ] print(data_l) print(data_a) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns + class TestCreateDimCurrency: - def test_dim_currency_returns_columns_and_values(self): - nones = [None,None,None] - d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"],"created_at":nones,"last_updated":nones} + nones = [None, None, None] + d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "created_at": nones, + "last_updated": nones, + } test_df = {"currency": pd.DataFrame(data=d)} - scraper_output = pd.DataFrame({"currency_code":["RUS","USD","PHP","GBP","EUR"],"currency_name":["Rubble","US Dollar","Peso","Pound","Euro"]}) - result = create_dim_currency(test_df,names=scraper_output).sort_values(by="currency_code",axis=0) - expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} - expected_df = pd.DataFrame(data=expected_d).sort_values(by="currency_code",axis=0) - assert isinstance(result, pd.DataFrame) - assert result.equals(expected_df) + scraper_output = pd.DataFrame( + { + "currency_code": ["RUS", "USD", "PHP", "GBP", "EUR"], + "currency_name": ["Rubble", "US Dollar", "Peso", "Pound", "Euro"], + } + ) + result = create_dim_currency(test_df, names=scraper_output).sort_values( + by="currency_code", axis=0 + ) + expected_d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "currency_name": ["US Dollar", "Euro", "Pound"], + } + expected_df = pd.DataFrame(data=expected_d).sort_values( + by="currency_code", axis=0 + ) + assert isinstance(result, pd.DataFrame) + assert result.equals(expected_df) def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self): result = scrape_currency_names() - assert isinstance(result,pd.DataFrame) - assert list(result.columns) == ['currency_code', 'currency_name'] + assert isinstance(result, pd.DataFrame) + assert list(result.columns) == ["currency_code", "currency_name"] -class TestCreateDimDate: +class TestCreateDimDate: def test_returns_required_columns(self): - df_one = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 5, 13),'not_dat':None},index=[0]) - df_two = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 9, 13)},index=[0]) - df_three = pd.DataFrame(data={'updated_date':dt(2022, 5, 17),'created_date':dt(2023, 5, 13)},index=[0]) - expected_df = pd.DataFrame(data= - [[dt(2020,5,17),2020,5,17,6,'Sunday','May',2], - [dt(2021,5,13),2021,5,13,3,'Thursday','May',2], - [dt(2021,9,13),2021,9,13,0,'Monday','September',3], - [dt(2022,5,17),2022,5,17,1,'Tuesday','May',2], - [dt(2023,5,13),2023,5,13,5,'Saturday','May',2]], - columns=['date_id','year','month','day','day_of_week','day_name','month_name','quarter']) + df_one = pd.DataFrame( + data={ + "updated_date": dt(2020, 5, 17), + "created_date": dt(2021, 5, 13), + "not_dat": None, + }, + index=[0], + ) + df_two = pd.DataFrame( + data={"updated_date": dt(2020, 5, 17), "created_date": dt(2021, 9, 13)}, + index=[0], + ) + df_three = pd.DataFrame( + data={"updated_date": dt(2022, 5, 17), "created_date": dt(2023, 5, 13)}, + index=[0], + ) + expected_df = pd.DataFrame( + data=[ + [dt(2020, 5, 17), 2020, 5, 17, 6, "Sunday", "May", 2], + [dt(2021, 5, 13), 2021, 5, 13, 3, "Thursday", "May", 2], + [dt(2021, 9, 13), 2021, 9, 13, 0, "Monday", "September", 3], + [dt(2022, 5, 17), 2022, 5, 17, 1, "Tuesday", "May", 2], + [dt(2023, 5, 13), 2023, 5, 13, 5, "Saturday", "May", 2], + ], + columns=[ + "date_id", + "year", + "month", + "day", + "day_of_week", + "day_name", + "month_name", + "quarter", + ], + ) with patch("src.dataframes.create_fact_payment") as mock_fp: with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo: with patch("src.dataframes.create_fact_sales_order") as mock_fso: mock_fp.return_value = df_one mock_fpo.return_value = df_two mock_fso.return_value = df_three - result = create_dim_date({'dum':0}) - result.reset_index(inplace=True,drop=True) + result = create_dim_date({"dum": 0}) + result.reset_index(inplace=True, drop=True) assert result.eq(expected_df, axis="columns").all(axis=None) - -class TestCreateDimLocation: + +class TestCreateDimLocation: def test_returns_correct_columns_lo(self): - dict_df = {'address':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], - columns=['created_at','last_updated','address_id','postal_code'])} + dict_df = { + "address": pd.DataFrame( + data=[["some_time", "some_other_time", 1, "SE18 9QO"]], + columns=["created_at", "last_updated", "address_id", "postal_code"], + ) + } result = create_dim_location(dict_df) - assert list(result.columns) == ['location_id','postal_code'] - + assert list(result.columns) == ["location_id", "postal_code"] + + class TestCreateDimTransaction: - def test_returns_correct_columns_tr(self): - dict_df = {'transaction':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], - columns=['created_at','last_updated','transaction_id','some_other_id'])} + def test_returns_correct_columns_tr(self): + dict_df = { + "transaction": pd.DataFrame( + data=[["some_time", "some_other_time", 1, "SE18 9QO"]], + columns=[ + "created_at", + "last_updated", + "transaction_id", + "some_other_id", + ], + ) + } result = create_dim_transaction(dict_df) - assert list(result.columns) == ['transaction_id','some_other_id'] + assert list(result.columns) == ["transaction_id", "some_other_id"] + class TestCreateFactPayment: def test_returns_correct_columns_payment(self): - dict_df = {'payment':pd.DataFrame(data=[[dt(2020,5,17,6,15,20),dt(2020,5,20,8,19,30),1,'SE18 9QO','2020-7-16']], - columns=['created_at','last_updated','payment_id','some_other_id','payment_date'])} - expected_cols = ['payment_record_id','created_date','created_time','last_updated_date', - 'last_updated_time','payment_date','payment_id','some_other_id'] + dict_df = { + "payment": pd.DataFrame( + data=[ + [ + dt(2020, 5, 17, 6, 15, 20), + dt(2020, 5, 20, 8, 19, 30), + 1, + "SE18 9QO", + "2020-7-16", + ] + ], + columns=[ + "created_at", + "last_updated", + "payment_id", + "some_other_id", + "payment_date", + ], + ) + } + expected_cols = [ + "payment_record_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "payment_date", + "payment_id", + "some_other_id", + ] result = create_fact_payment(dict_df) - assert isinstance(result,pd.DataFrame) + assert isinstance(result, pd.DataFrame) for col in list(result.columns): assert col in expected_cols for col in expected_cols: - if 'date' in col: - assert result[col].dtype == 'datetime64[ns]' - - \ No newline at end of file + if "date" in col: + assert result[col].dtype == "datetime64[ns]" -- cgit v1.2.3 From c7bc31ec5e3d838b3d48791ad13dd20600d7578f Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 14:14:43 +0100 Subject: add passing retrieve secrets tests --- tests/test_load_lambda.py | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 3df94e4..9b0a271 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -3,6 +3,7 @@ import pyarrow.parquet as pq from io import BytesIO from moto import mock_aws import boto3 +import botocore.exceptions import os import pytest from src.load_lambda import * @@ -29,10 +30,6 @@ def mock_sm_client(aws_credentials): yield boto3.client("secretsmanager") -@pytest.fixture -def mock_parquet_file(mocker): - return mocker.patch("src.load_lambda.convert_parquet_files_to_dfs") - class TestLambdaHandler: pass @@ -58,6 +55,19 @@ class TestRetrieveSecrets: assert isinstance(result, dict) + def test_retrieve_secrets_returns_correct_keys_and_values(self, mock_sm_client): + secret_name = "test_secret" + + result = retrieve_secrets(mock_sm_client, secret_name) + + assert result["user"] == "test_user_id" + assert result["password"] == "test_password" + + def test_retrieve_secrets_returns_client_error_if_no_secret(self, mock_sm_client): + secret_name = "another_test_secret" + + with pytest.raises(botocore.exceptions.ClientError) as error: + retrieve_secrets(mock_sm_client, secret_name) class TestConnectToDBAndReturnEngine: @@ -112,4 +122,7 @@ class TestConvertParquetToDfs: def mock_connect_db(mocker): - return mocker.patch("src.load_lambda.connect_to_db_and_return_engine") \ No newline at end of file + return mocker.patch("src.load_lambda.connect_to_db_and_return_engine") + +class TestUploadDfsToDatabase: + pass \ No newline at end of file -- cgit v1.2.3 From 22df92bcce7ec2d9e713b9609ffdd604d207e713 Mon Sep 17 00:00:00 2001 From: Ang Bel Date: Tue, 27 Aug 2024 15:18:54 +0100 Subject: test: refactored fact functions with test passing --- src/dataframes.py | 24 ++++++++++++------------ tests/test_dataframes.py | 9 +++++++-- 2 files changed, 19 insertions(+), 14 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 41f39b8..1f445a4 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -20,10 +20,10 @@ import requests def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - df_sales["created_date"] = pd.to_datetime(df_sales["created_at"],format='%Y-%m-%d') - df_sales["created_time"] = pd.to_datetime(df_sales["created_at"],format='%H-%M-%S') - df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"],format='%Y-%m-%d') - df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"],format='%H-%M-%S') + df_sales["created_date"] = pd.to_datetime(df_sales["created_at"].dt.date,format='%Y-%m-%d') + df_sales["created_time"] = df_sales["created_at"].dt.floor('s').dt.time + df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"].dt.date,format='%Y-%m-%d') + df_sales["last_updated_time"] = df_sales["last_updated"].dt.floor('s').dt.time df_sales['agreed_delivery_date'] = pd.to_datetime(df_sales['agreed_delivery_date'],format="%Y-%m-%d") df_sales['agreed_payment_date'] = pd.to_datetime(df_sales['agreed_payment_date'],format="%Y-%m-%d") df_sales.drop(labels=['created_at','last_updated'],axis=1,inplace=True) @@ -34,10 +34,10 @@ def create_fact_sales_order(dict_of_df): def create_fact_purchase_orders(dict_of_df): df_po = dict_of_df['purchase_order'] df_po.index.name = 'purchase_record_id' - df_po['created_date'] = pd.to_datetime(df_po['created_at'],format='%Y-%m-%d') - df_po['created_time'] = pd.to_datetime(df_po['created_at'],format='%H-%M-%S') - df_po['last_updated_date'] = pd.to_datetime(df_po['last_updated'],format='%Y-%m-%d') - df_po['last_updated_time'] = pd.to_datetime(df_po['last_updated'],format='%H-%M-%S') + df_po['created_date'] = pd.to_datetime(df_po['created_at'].dt.date,format='%Y-%m-%d') + df_po['created_time'] = df_po['created_at'].dt.floor('s').dt.time + df_po['last_updated_date'] = pd.to_datetime(df_po['last_updated'].dt.date,format='%Y-%m-%d') + df_po['last_updated_time'] = df_po['last_updated'].dt.floor('s').dt.time df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") df_po.drop(labels=['created_at','last_updated'],axis=1,inplace=True) @@ -48,10 +48,10 @@ def create_fact_purchase_orders(dict_of_df): def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = pd.to_datetime(df_payment["created_at"],format='%Y-%m-%d') - df_payment["created_time"] = pd.to_datetime(df_payment["created_at"],format='%H-%M-%S') - df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"],format='%Y-%m-%d') - df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"],format='%H-%M-%S') + df_payment["created_date"] = pd.to_datetime(df_payment["created_at"].dt.date,format='%Y-%m-%d') + df_payment["created_time"] = df_payment["created_at"].dt.floor('s').dt.time + df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"].dt.date,format='%Y-%m-%d') + df_payment["last_updated_time"] = df_payment["last_updated"].dt.floor('s').dt.time df_payment['payment_date'] = pd.to_datetime(df_payment['payment_date'],format="%Y-%m-%d") df_payment.drop(labels=['created_at','last_updated'],axis=1,inplace=True) df_payment.reset_index(inplace=True) diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index 8f32b1d..70aefe8 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -129,7 +129,8 @@ class TestCreateDimTransaction: class TestCreateFactPayment: def test_returns_correct_columns_payment(self): - dict_df = {'payment':pd.DataFrame(data=[[dt(2020,5,17,6,15,20),dt(2020,5,20,8,19,30),1,'SE18 9QO','2020-7-16']], + dict_df = {'payment':pd.DataFrame(data=[[dt.strptime('2022-11-03 14:20:49.962846','%Y-%m-%d %H:%M:%S.%f'), + dt.strptime('2022-12-14 16:20:49.962194','%Y-%m-%d %H:%M:%S.%f'),1,'SE18 9QO','2020-07-16']], columns=['created_at','last_updated','payment_id','some_other_id','payment_date'])} expected_cols = ['payment_record_id','created_date','created_time','last_updated_date', 'last_updated_time','payment_date','payment_id','some_other_id'] @@ -138,7 +139,11 @@ class TestCreateFactPayment: for col in list(result.columns): assert col in expected_cols for col in expected_cols: - if 'date' in col: + if '_date' in col: + print(col) assert result[col].dtype == 'datetime64[ns]' + if '_time' in col: + print(col) + assert result[col].dtype == 'O' #<< O for object \ No newline at end of file -- cgit v1.2.3 From d623c42a891f2fe8a26493354af0d9e299f3c526 Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Tue, 27 Aug 2024 15:19:14 +0100 Subject: refactor: add parameter for sm_secret --- src/load_lambda.py | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index f08e335..11d1d70 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -49,7 +49,6 @@ def retrieve_secrets(client=None, secret_name=None): if client == None: client = session.client(service_name="secretsmanager", region_name=region_name) - try: get_secret_value_response = client.get_secret_value(SecretId=secret_name) print(get_secret_value_response) @@ -66,9 +65,12 @@ def retrieve_secrets(client=None, secret_name=None): # connect to database, slightly different way of doing it, to allow manipulation through pandas -def connect_to_db_and_return_engine(): +def connect_to_db_and_return_engine(sm_secret=None): + if sm_secret is None: + sm_secret = retrieve_secrets() + try: - secrets = json.loads(retrieve_secrets()) + secrets = json.loads(sm_secret) host = secrets["host"] port = secrets["port"] user = secrets["user"] @@ -198,5 +200,6 @@ def upload_dfs_to_database(): db_engine.dispose() return upload_status + if __name__ == "__main__": lambda_handler(None, None) -- cgit v1.2.3 From fbfbc61d847187b09ec4d59928a0f853b916115f Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Tue, 27 Aug 2024 14:19:49 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 22df92b according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/99 --- src/dataframes.py | 230 ++++++++++++++++++++++++------------- tests/test_dataframes.py | 286 +++++++++++++++++++++++++++++++++++------------ 2 files changed, 368 insertions(+), 148 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 1f445a4..da0b170 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -2,7 +2,7 @@ import pandas as pd from bs4 import BeautifulSoup import requests -#Table names: +# Table names: # fact_sales_order # fact_purchase_orders # fact_payment @@ -16,133 +16,207 @@ import requests # dim_counterparty -#no test, same as fact_payment +# no test, same as fact_payment def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - df_sales["created_date"] = pd.to_datetime(df_sales["created_at"].dt.date,format='%Y-%m-%d') - df_sales["created_time"] = df_sales["created_at"].dt.floor('s').dt.time - df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"].dt.date,format='%Y-%m-%d') - df_sales["last_updated_time"] = df_sales["last_updated"].dt.floor('s').dt.time - df_sales['agreed_delivery_date'] = pd.to_datetime(df_sales['agreed_delivery_date'],format="%Y-%m-%d") - df_sales['agreed_payment_date'] = pd.to_datetime(df_sales['agreed_payment_date'],format="%Y-%m-%d") - df_sales.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_sales["created_date"] = pd.to_datetime( + df_sales["created_at"].dt.date, format="%Y-%m-%d" + ) + df_sales["created_time"] = df_sales["created_at"].dt.floor("s").dt.time + df_sales["last_updated_date"] = pd.to_datetime( + df_sales["last_updated"].dt.date, format="%Y-%m-%d" + ) + df_sales["last_updated_time"] = df_sales["last_updated"].dt.floor("s").dt.time + df_sales["agreed_delivery_date"] = pd.to_datetime( + df_sales["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_sales["agreed_payment_date"] = pd.to_datetime( + df_sales["agreed_payment_date"], format="%Y-%m-%d" + ) + df_sales.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) df_sales.reset_index(inplace=True) return df_sales -#no test, same as fact_payment + +# no test, same as fact_payment + + def create_fact_purchase_orders(dict_of_df): - df_po = dict_of_df['purchase_order'] - df_po.index.name = 'purchase_record_id' - df_po['created_date'] = pd.to_datetime(df_po['created_at'].dt.date,format='%Y-%m-%d') - df_po['created_time'] = df_po['created_at'].dt.floor('s').dt.time - df_po['last_updated_date'] = pd.to_datetime(df_po['last_updated'].dt.date,format='%Y-%m-%d') - df_po['last_updated_time'] = df_po['last_updated'].dt.floor('s').dt.time - df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") - df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") - df_po.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_po = dict_of_df["purchase_order"] + df_po.index.name = "purchase_record_id" + df_po["created_date"] = pd.to_datetime( + df_po["created_at"].dt.date, format="%Y-%m-%d" + ) + df_po["created_time"] = df_po["created_at"].dt.floor("s").dt.time + df_po["last_updated_date"] = pd.to_datetime( + df_po["last_updated"].dt.date, format="%Y-%m-%d" + ) + df_po["last_updated_time"] = df_po["last_updated"].dt.floor("s").dt.time + df_po["agreed_delivery_date"] = pd.to_datetime( + df_po["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_po["agreed_payment_date"] = pd.to_datetime( + df_po["agreed_payment_date"], format="%Y-%m-%d" + ) + df_po.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) df_po.reset_index(inplace=True) return df_po -#test passed + +# test passed + + def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = pd.to_datetime(df_payment["created_at"].dt.date,format='%Y-%m-%d') - df_payment["created_time"] = df_payment["created_at"].dt.floor('s').dt.time - df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"].dt.date,format='%Y-%m-%d') - df_payment["last_updated_time"] = df_payment["last_updated"].dt.floor('s').dt.time - df_payment['payment_date'] = pd.to_datetime(df_payment['payment_date'],format="%Y-%m-%d") - df_payment.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_payment["created_date"] = pd.to_datetime( + df_payment["created_at"].dt.date, format="%Y-%m-%d" + ) + df_payment["created_time"] = df_payment["created_at"].dt.floor("s").dt.time + df_payment["last_updated_date"] = pd.to_datetime( + df_payment["last_updated"].dt.date, format="%Y-%m-%d" + ) + df_payment["last_updated_time"] = df_payment["last_updated"].dt.floor("s").dt.time + df_payment["payment_date"] = pd.to_datetime( + df_payment["payment_date"], format="%Y-%m-%d" + ) + df_payment.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) df_payment.reset_index(inplace=True) return df_payment -#test passed + +# test passed + + def create_dim_transaction(dict_of_df): - df_transaction = dict_of_df["transaction"].drop(labels=['created_at', 'last_updated'], axis=1) + df_transaction = dict_of_df["transaction"].drop( + labels=["created_at", "last_updated"], axis=1 + ) return df_transaction -#test passed + +# test passed + + def create_dim_location(dict_of_df): - df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}) + df_loc = ( + dict_of_df["address"] + .drop(labels=["created_at", "last_updated"], axis=1) + .rename(columns={"address_id": "location_id"}) + ) return df_loc def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) - df_cp = pd.merge(dict_of_df['counterparty'], - df_prefixed_address, - left_on="legal_address_id", - right_on="counterparty_legal_address_id", - how="outer") - df_cp.drop(columns=["legal_address_id","counterparty_legal_address_id"],inplace=True) + df_prefixed_address = dict_of_df["address"].add_prefix( + "counterparty_legal_", axis=1 + ) + df_cp = pd.merge( + dict_of_df["counterparty"], + df_prefixed_address, + left_on="legal_address_id", + right_on="counterparty_legal_address_id", + how="outer", + ) + df_cp.drop( + columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True + ) return df_cp -#test passed + +# test passed + + def create_dim_date(dict_of_df): - fact_dfs = [create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df)] + fact_dfs = [ + create_fact_payment(dict_of_df), + create_fact_purchase_orders(dict_of_df), + create_fact_sales_order(dict_of_df), + ] list_of_date_columns = [] for df in fact_dfs: - date_col_names = [col_name for col_name in list(df.columns) if 'date' in col_name] + date_col_names = [ + col_name for col_name in list(df.columns) if "date" in col_name + ] for col in date_col_names: list_of_date_columns.append(df[col]) - sr_date = pd.array(pd.concat(list_of_date_columns),dtype='datetime64[ns]') - df_date = pd.DataFrame(data=sr_date,columns=['date_id']) + sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") + df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) df_date.drop_duplicates(inplace=True) - df_date['year'] = df_date['date_id'].dt.year - df_date['month'] = df_date['date_id'].dt.month - df_date['day'] = df_date['date_id'].dt.day - df_date['day_of_week'] = df_date['date_id'].dt.dayofweek - df_date['day_name'] = df_date['date_id'].dt.day_name() - df_date['month_name'] = df_date['date_id'].dt.month_name() - df_date['quarter'] = df_date['date_id'].dt.quarter + df_date["year"] = df_date["date_id"].dt.year + df_date["month"] = df_date["date_id"].dt.month + df_date["day"] = df_date["date_id"].dt.day + df_date["day_of_week"] = df_date["date_id"].dt.dayofweek + df_date["day_name"] = df_date["date_id"].dt.day_name() + df_date["month_name"] = df_date["date_id"].dt.month_name() + df_date["quarter"] = df_date["date_id"].dt.quarter return df_date -#tests passed -def scrape_currency_names(): - response = requests.get('https://www.xe.com/currency/').content - soup = BeautifulSoup(response,'html.parser') - currency = [item.text for item in soup.findAll('a', attrs={'class' : "sc-299dec64-6 fZPTSw"})] - sr = pd.Series(currency) - df_cur = sr.str.split(pat=" - ",expand=True).rename({0:'currency_code',1:'currency_name'},axis=1) - return df_cur - -#tests passed -def create_dim_currency(dict_of_df,names=scrape_currency_names()): - df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1) - dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner') - return dim_cur -#tests passed -def create_dim_payment_type(dict_of_df): - df_payment_type = dict_of_df["payment_type"] - dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] - return dim_payment_type +# tests passed -#tests passed -def create_dim_design(dict_of_df): - df_design = dict_of_df["design"] - dim_design = df_design.loc[:, ["design_id", "design_name", "file_name", "file_location"]] - return dim_design -#tests passed -def create_dim_staff(dict_of_df): - staff_department = pd.merge(dict_of_df["staff"], dict_of_df["department"], on='department_id', how="left") - dim_staff = staff_department.loc[:, ['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address']] - return dim_staff +def scrape_currency_names(): + response = requests.get("https://www.xe.com/currency/").content + soup = BeautifulSoup(response, "html.parser") + currency = [ + item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) + ] + sr = pd.Series(currency) + df_cur = sr.str.split(pat=" - ", expand=True).rename( + {0: "currency_code", 1: "currency_name"}, axis=1 + ) + return df_cur +# tests passed +def create_dim_currency(dict_of_df, names=scrape_currency_names()): + df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) + dim_cur = pd.merge( + df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" + ) + return dim_cur +# tests passed +def create_dim_payment_type(dict_of_df): + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + return dim_payment_type +# tests passed +def create_dim_design(dict_of_df): + df_design = dict_of_df["design"] + dim_design = df_design.loc[ + :, ["design_id", "design_name", "file_name", "file_location"] + ] + return dim_design +# tests passed +def create_dim_staff(dict_of_df): + staff_department = pd.merge( + dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" + ) + dim_staff = staff_department.loc[ + :, + [ + "staff_id", + "first_name", + "last_name", + "department_name", + "location", + "email_address", + ], + ] + return dim_staff diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index 70aefe8..bd81f73 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -3,42 +3,88 @@ import pandas as pd from unittest.mock import patch from datetime import datetime as dt + class TestCreateDimDesign: def test_dim_design_returns_dataframe(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) assert isinstance(result, pd.DataFrame) def test_dim_design_returns_correct_columns_and_values(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) - d2 = {"design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"]} + d2 = { + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=d2) expected_result = expected_df.copy() assert result.equals(expected_result) + class TestCreateDimStaff: def test_dim_staff_returns_dataframe(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - assert isinstance(result, pd.DataFrame) + assert isinstance(result, pd.DataFrame) def test_dim_staff_returns_correct_columns_and_values(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - expected_d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"]} + expected_d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) expected_result = expected_df.copy() - assert result.equals(expected_result) + assert result.equals(expected_result) + class TestCreatePaymentType: def test_create_dim_payment_type_returns_correct_columns_and_values(self): @@ -46,104 +92,204 @@ class TestCreatePaymentType: test_df = {"payment_type": pd.DataFrame(data=d)} result = create_dim_payment_type(test_df) expected_columns = ["payment_type_id", "payment_type_name"] - expected_d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} + expected_d = { + "payment_type_id": ["Hello", "Bye"], + "payment_type_name": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns assert result.equals(expected_df) + class TestCreateDimCounterparty: - def test_create_dim_counterparty_type_returns_correct_columns_and_object(self): - data_l = pd.DataFrame(data={"counterparty_id": ["Hello", "Bye"], - "counterparty_legal_name": ["Hello", "Bye"], - "commercial_contact": ["Hello", "Bye"], - "legal_address_id": ["bond street", "regent street"]}) - data_a = pd.DataFrame(data={"address_id":["bond street", "regent street"], - "postcode":[98365,93753]}) - test_df = {"address": data_a,"counterparty":data_l} + data_l = pd.DataFrame( + data={ + "counterparty_id": ["Hello", "Bye"], + "counterparty_legal_name": ["Hello", "Bye"], + "commercial_contact": ["Hello", "Bye"], + "legal_address_id": ["bond street", "regent street"], + } + ) + data_a = pd.DataFrame( + data={ + "address_id": ["bond street", "regent street"], + "postcode": [98365, 93753], + } + ) + test_df = {"address": data_a, "counterparty": data_l} result = create_dim_counterparty(test_df) - expected_columns = ["counterparty_id", "counterparty_legal_name", - "commercial_contact", "counterparty_legal_postcode"] + expected_columns = [ + "counterparty_id", + "counterparty_legal_name", + "commercial_contact", + "counterparty_legal_postcode", + ] print(data_l) print(data_a) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns + class TestCreateDimCurrency: - def test_dim_currency_returns_columns_and_values(self): - nones = [None,None,None] - d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"],"created_at":nones,"last_updated":nones} + nones = [None, None, None] + d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "created_at": nones, + "last_updated": nones, + } test_df = {"currency": pd.DataFrame(data=d)} - scraper_output = pd.DataFrame({"currency_code":["RUS","USD","PHP","GBP","EUR"],"currency_name":["Rubble","US Dollar","Peso","Pound","Euro"]}) - result = create_dim_currency(test_df,names=scraper_output).sort_values(by="currency_code",axis=0) - expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} - expected_df = pd.DataFrame(data=expected_d).sort_values(by="currency_code",axis=0) - assert isinstance(result, pd.DataFrame) - assert result.equals(expected_df) + scraper_output = pd.DataFrame( + { + "currency_code": ["RUS", "USD", "PHP", "GBP", "EUR"], + "currency_name": ["Rubble", "US Dollar", "Peso", "Pound", "Euro"], + } + ) + result = create_dim_currency(test_df, names=scraper_output).sort_values( + by="currency_code", axis=0 + ) + expected_d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "currency_name": ["US Dollar", "Euro", "Pound"], + } + expected_df = pd.DataFrame(data=expected_d).sort_values( + by="currency_code", axis=0 + ) + assert isinstance(result, pd.DataFrame) + assert result.equals(expected_df) def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self): result = scrape_currency_names() - assert isinstance(result,pd.DataFrame) - assert list(result.columns) == ['currency_code', 'currency_name'] + assert isinstance(result, pd.DataFrame) + assert list(result.columns) == ["currency_code", "currency_name"] -class TestCreateDimDate: +class TestCreateDimDate: def test_returns_required_columns(self): - df_one = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 5, 13),'not_dat':None},index=[0]) - df_two = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 9, 13)},index=[0]) - df_three = pd.DataFrame(data={'updated_date':dt(2022, 5, 17),'created_date':dt(2023, 5, 13)},index=[0]) - expected_df = pd.DataFrame(data= - [[dt(2020,5,17),2020,5,17,6,'Sunday','May',2], - [dt(2021,5,13),2021,5,13,3,'Thursday','May',2], - [dt(2021,9,13),2021,9,13,0,'Monday','September',3], - [dt(2022,5,17),2022,5,17,1,'Tuesday','May',2], - [dt(2023,5,13),2023,5,13,5,'Saturday','May',2]], - columns=['date_id','year','month','day','day_of_week','day_name','month_name','quarter']) + df_one = pd.DataFrame( + data={ + "updated_date": dt(2020, 5, 17), + "created_date": dt(2021, 5, 13), + "not_dat": None, + }, + index=[0], + ) + df_two = pd.DataFrame( + data={"updated_date": dt(2020, 5, 17), "created_date": dt(2021, 9, 13)}, + index=[0], + ) + df_three = pd.DataFrame( + data={"updated_date": dt(2022, 5, 17), "created_date": dt(2023, 5, 13)}, + index=[0], + ) + expected_df = pd.DataFrame( + data=[ + [dt(2020, 5, 17), 2020, 5, 17, 6, "Sunday", "May", 2], + [dt(2021, 5, 13), 2021, 5, 13, 3, "Thursday", "May", 2], + [dt(2021, 9, 13), 2021, 9, 13, 0, "Monday", "September", 3], + [dt(2022, 5, 17), 2022, 5, 17, 1, "Tuesday", "May", 2], + [dt(2023, 5, 13), 2023, 5, 13, 5, "Saturday", "May", 2], + ], + columns=[ + "date_id", + "year", + "month", + "day", + "day_of_week", + "day_name", + "month_name", + "quarter", + ], + ) with patch("src.dataframes.create_fact_payment") as mock_fp: with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo: with patch("src.dataframes.create_fact_sales_order") as mock_fso: mock_fp.return_value = df_one mock_fpo.return_value = df_two mock_fso.return_value = df_three - result = create_dim_date({'dum':0}) - result.reset_index(inplace=True,drop=True) + result = create_dim_date({"dum": 0}) + result.reset_index(inplace=True, drop=True) assert result.eq(expected_df, axis="columns").all(axis=None) - -class TestCreateDimLocation: + +class TestCreateDimLocation: def test_returns_correct_columns_lo(self): - dict_df = {'address':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], - columns=['created_at','last_updated','address_id','postal_code'])} + dict_df = { + "address": pd.DataFrame( + data=[["some_time", "some_other_time", 1, "SE18 9QO"]], + columns=["created_at", "last_updated", "address_id", "postal_code"], + ) + } result = create_dim_location(dict_df) - assert list(result.columns) == ['location_id','postal_code'] - + assert list(result.columns) == ["location_id", "postal_code"] + + class TestCreateDimTransaction: - def test_returns_correct_columns_tr(self): - dict_df = {'transaction':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], - columns=['created_at','last_updated','transaction_id','some_other_id'])} + def test_returns_correct_columns_tr(self): + dict_df = { + "transaction": pd.DataFrame( + data=[["some_time", "some_other_time", 1, "SE18 9QO"]], + columns=[ + "created_at", + "last_updated", + "transaction_id", + "some_other_id", + ], + ) + } result = create_dim_transaction(dict_df) - assert list(result.columns) == ['transaction_id','some_other_id'] + assert list(result.columns) == ["transaction_id", "some_other_id"] + class TestCreateFactPayment: def test_returns_correct_columns_payment(self): - dict_df = {'payment':pd.DataFrame(data=[[dt.strptime('2022-11-03 14:20:49.962846','%Y-%m-%d %H:%M:%S.%f'), - dt.strptime('2022-12-14 16:20:49.962194','%Y-%m-%d %H:%M:%S.%f'),1,'SE18 9QO','2020-07-16']], - columns=['created_at','last_updated','payment_id','some_other_id','payment_date'])} - expected_cols = ['payment_record_id','created_date','created_time','last_updated_date', - 'last_updated_time','payment_date','payment_id','some_other_id'] + dict_df = { + "payment": pd.DataFrame( + data=[ + [ + dt.strptime( + "2022-11-03 14:20:49.962846", "%Y-%m-%d %H:%M:%S.%f" + ), + dt.strptime( + "2022-12-14 16:20:49.962194", "%Y-%m-%d %H:%M:%S.%f" + ), + 1, + "SE18 9QO", + "2020-07-16", + ] + ], + columns=[ + "created_at", + "last_updated", + "payment_id", + "some_other_id", + "payment_date", + ], + ) + } + expected_cols = [ + "payment_record_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "payment_date", + "payment_id", + "some_other_id", + ] result = create_fact_payment(dict_df) - assert isinstance(result,pd.DataFrame) + assert isinstance(result, pd.DataFrame) for col in list(result.columns): assert col in expected_cols for col in expected_cols: - if '_date' in col: + if "_date" in col: print(col) - assert result[col].dtype == 'datetime64[ns]' - if '_time' in col: + assert result[col].dtype == "datetime64[ns]" + if "_time" in col: print(col) - assert result[col].dtype == 'O' #<< O for object - - \ No newline at end of file + assert result[col].dtype == "O" # << O for object -- cgit v1.2.3 From f6584f5f52bc8731a2076e2d692faf28b107647d Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Tue, 27 Aug 2024 15:20:13 +0100 Subject: wip: add test for parquet file conversion --- tests/test_load_lambda.py | 59 ++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 51 insertions(+), 8 deletions(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 9b0a271..b5821a4 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -7,6 +7,7 @@ import botocore.exceptions import os import pytest from src.load_lambda import * +import tempfile @pytest.fixture(scope="class") @@ -22,7 +23,7 @@ def aws_credentials(): def mock_s3_client(aws_credentials): with mock_aws(): yield boto3.client("s3") - + @pytest.fixture(scope="class") def mock_sm_client(aws_credentials): @@ -30,6 +31,11 @@ def mock_sm_client(aws_credentials): yield boto3.client("secretsmanager") +@pytest.fixture(scope="class") +def mock_connect_db(mocker): + return mocker.patch("src.load_lambda.connect_to_db_and_return_engine") + + class TestLambdaHandler: pass @@ -47,9 +53,7 @@ class TestRetrieveSecrets: secret_name = "test_secret" - mock_sm_client.create_secret( - Name=secret_name, SecretString=json.dumps(secret) - ) + mock_sm_client.create_secret(Name=secret_name, SecretString=json.dumps(secret)) result = retrieve_secrets(mock_sm_client, secret_name) @@ -71,7 +75,17 @@ class TestRetrieveSecrets: class TestConnectToDBAndReturnEngine: - pass + def test_returns_unsuccessful_connection_when_wrong_credentials(self): + sm_secret = { + "host": "host", + "port": "port", + "user": "user", + "password": "password", + "database": "database", + } + + with pytest.raises(Exception): + connect_to_db_and_return_engine(json.dumps(sm_secret)) class TestGetTransformBucket: @@ -120,9 +134,38 @@ class TestConvertParquetToDfs: # result = convert_parquet_files_to_dfs(bucket_name="transform_bucket", client=mock_s3_client) # assert "dim_staff" in result + def test_function_returns_dictionary_with_file_key_and_dataframe( + self, mock_s3_client + ): + with tempfile.TemporaryDirectory() as tmp: + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } + + test_df = pd.DataFrame(data=d) + + path = os.path.join(tmp, "test_parquet.parquet") + + test_df.to_parquet(path, engine="pyarrow") + + with open(path, "rb") as p: + mock_s3_client.put_object( + Bucket="transform_bucket", Key="test_parquet.parquet", Body=p.read() + ) + + result = convert_parquet_files_to_dfs( + bucket_name="transform_bucket", client=mock_s3_client + ) + + assert "test_parquet.parquet" in result + + pd.testing.assert_frame_equal(result["test_parquet.parquet"], test_df) -def mock_connect_db(mocker): - return mocker.patch("src.load_lambda.connect_to_db_and_return_engine") class TestUploadDfsToDatabase: - pass \ No newline at end of file + pass -- cgit v1.2.3 From f5bccf178ea1ebce213efd0518af63d74b00a11c Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Tue, 27 Aug 2024 15:34:35 +0100 Subject: test: add lambda_handler tests --- tests/test_load_lambda.py | 27 +++++++++++++++++++++------ 1 file changed, 21 insertions(+), 6 deletions(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index b5821a4..98ab36b 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -31,13 +31,28 @@ def mock_sm_client(aws_credentials): yield boto3.client("secretsmanager") -@pytest.fixture(scope="class") -def mock_connect_db(mocker): - return mocker.patch("src.load_lambda.connect_to_db_and_return_engine") - - class TestLambdaHandler: - pass + def test_lambda_handler_returns_success(self, mocker): + mocker.patch( + "src.load_lambda.upload_dfs_to_database", + return_value={"uploaded": ["table_one", "table_two"]}, + ) + result = lambda_handler(None, None) + assert result["statusCode"] == 200 + assert "table_one" in result["body"] + assert "table_two" in result["body"] + + def test_lambda_handler_does_not_upload_anything(self, mocker): + mocker.patch( + "src.load_lambda.upload_dfs_to_database", + return_value={"uploaded": []}, + ) + result = lambda_handler(None, None) + assert result["statusCode"] == 200 + assert "No dataframes were uploaded" in result["body"] + + def test_lambda_handler_returns_exception(self, mocker): + pass class TestRetrieveSecrets: -- cgit v1.2.3 From 843f11c302a2a9089c3726342cd1231015f074f7 Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Tue, 27 Aug 2024 15:36:12 +0100 Subject: docs: add comments for upload tests --- tests/test_load_lambda.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 98ab36b..a29b75a 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -183,4 +183,7 @@ class TestConvertParquetToDfs: class TestUploadDfsToDatabase: + # Full success test + # Partial success test + # Failure test pass -- cgit v1.2.3 From cbfc98a9f43b5a0dae95337057c18c9dc2a298e3 Mon Sep 17 00:00:00 2001 From: Alex Schofield Date: Tue, 27 Aug 2024 16:00:29 +0100 Subject: wip: update TestLambdaHandler & lambda_handler function --- src/load_lambda.py | 19 +++++++++++-------- tests/test_load_lambda.py | 12 +++++++++--- 2 files changed, 20 insertions(+), 11 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 11d1d70..39fa27d 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -23,18 +23,21 @@ logging.getLogger("botocore").setLevel(logging.INFO) def lambda_handler(event, context): try: uploaded_tables = upload_dfs_to_database() - if not uploaded_tables["uploaded"]: + if uploaded_tables["not_uploaded"]: return { "statusCode": 200, "body": json.dumps("No dataframes were uploaded."), } - return { - "statusCode": 200, - "body": json.dumps( - f"""The following dataframes were uploaded successfully: - {uploaded_tables["uploaded"]} .""" - ), - } + + if uploaded_tables["uploaded"]: + return { + "statusCode": 200, + "body": json.dumps( + f"""The following dataframes were uploaded successfully: + {uploaded_tables["uploaded"]} .""" + ), + } + except Exception as e: logger.error(f"Error: {e}", exc_info=True) return {"statusCode": 500, "body": json.dumps("Internal server error.")} diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index a29b75a..9286e48 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -35,7 +35,7 @@ class TestLambdaHandler: def test_lambda_handler_returns_success(self, mocker): mocker.patch( "src.load_lambda.upload_dfs_to_database", - return_value={"uploaded": ["table_one", "table_two"]}, + return_value={"uploaded": ["table_one", "table_two"], "not_uploaded": []}, ) result = lambda_handler(None, None) assert result["statusCode"] == 200 @@ -45,14 +45,20 @@ class TestLambdaHandler: def test_lambda_handler_does_not_upload_anything(self, mocker): mocker.patch( "src.load_lambda.upload_dfs_to_database", - return_value={"uploaded": []}, + return_value={"uploaded": [], "not_uploaded": []}, ) result = lambda_handler(None, None) assert result["statusCode"] == 200 assert "No dataframes were uploaded" in result["body"] def test_lambda_handler_returns_exception(self, mocker): - pass + mocker.patch( + "src.load_lambda.upload_dfs_to_database", + return_value={"test": []}, + ) + + with pytest.raises(Exception): + lambda_handler(None, None) class TestRetrieveSecrets: -- cgit v1.2.3 From 27f89b78775f9b6fd8d3d560689c53db2beb1b64 Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 16:39:38 +0100 Subject: add logger error to lambda handler --- src/load_lambda.py | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 39fa27d..9e15af3 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -5,6 +5,7 @@ import pyarrow.parquet as pq from io import BytesIO import logging import json +import traceback from sqlalchemy import create_engine @@ -28,8 +29,7 @@ def lambda_handler(event, context): "statusCode": 200, "body": json.dumps("No dataframes were uploaded."), } - - if uploaded_tables["uploaded"]: + elif uploaded_tables["uploaded"]: return { "statusCode": 200, "body": json.dumps( @@ -37,10 +37,12 @@ def lambda_handler(event, context): {uploaded_tables["uploaded"]} .""" ), } - + else: + logger.error(f"error") + return {"error"} except Exception as e: - logger.error(f"Error: {e}", exc_info=True) - return {"statusCode": 500, "body": json.dumps("Internal server error.")} + logger.error({e}) + return {"statusCode": 500, "body": {e}} def retrieve_secrets(client=None, secret_name=None): -- cgit v1.2.3 From 0ea88c0216d9e5eca9e4aca4f2fa427d38184648 Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 16:40:21 +0100 Subject: add passing tests for lambda handler --- tests/test_load_lambda.py | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 9286e48..0b13b54 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -32,7 +32,7 @@ def mock_sm_client(aws_credentials): class TestLambdaHandler: - def test_lambda_handler_returns_success(self, mocker): + def test_lambda_handler_returns_200_and_table_name_if_uploaded(self, mocker): mocker.patch( "src.load_lambda.upload_dfs_to_database", return_value={"uploaded": ["table_one", "table_two"], "not_uploaded": []}, @@ -42,23 +42,25 @@ class TestLambdaHandler: assert "table_one" in result["body"] assert "table_two" in result["body"] - def test_lambda_handler_does_not_upload_anything(self, mocker): + def test_lambda_handler_returns_200_and_table_name_if_not_uploaded(self, mocker): mocker.patch( "src.load_lambda.upload_dfs_to_database", - return_value={"uploaded": [], "not_uploaded": []}, + return_value={"uploaded": [], "not_uploaded": ["table_one"]}, ) result = lambda_handler(None, None) assert result["statusCode"] == 200 assert "No dataframes were uploaded" in result["body"] - def test_lambda_handler_returns_exception(self, mocker): + def test_lambda_handler_returns_error_if_both_lists_empty(self, mocker): mocker.patch( "src.load_lambda.upload_dfs_to_database", - return_value={"test": []}, + return_value={"uploaded": [], "not_uploaded": []}, ) - with pytest.raises(Exception): - lambda_handler(None, None) + result = lambda_handler(None, None) + + assert result == {"error"} + class TestRetrieveSecrets: -- cgit v1.2.3 From 1a145a36d524a785c821aafbdb3512c24be6c57e Mon Sep 17 00:00:00 2001 From: Ang Bel Date: Tue, 27 Aug 2024 17:00:04 +0100 Subject: test: transform refactoring - it now loads parquet files into s3 bucket --- src/dataframes.py | 32 ++++++++++++++++---------------- src/transform_lambda.py | 6 +++--- tests/test_dataframes.py | 10 +++------- 3 files changed, 22 insertions(+), 26 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 1f445a4..9d0f2ac 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -20,13 +20,13 @@ import requests def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - df_sales["created_date"] = pd.to_datetime(df_sales["created_at"].dt.date,format='%Y-%m-%d') - df_sales["created_time"] = df_sales["created_at"].dt.floor('s').dt.time - df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"].dt.date,format='%Y-%m-%d') - df_sales["last_updated_time"] = df_sales["last_updated"].dt.floor('s').dt.time + df_sales["created_date"] = df_sales["created_at"].astype('datetime64[ns]').dt.date + df_sales["created_time"] = df_sales["created_at"].astype('datetime64[ns]').dt.floor('s').dt.time + df_sales["last_updated_date"] = df_sales["last_updated"].astype('datetime64[ns]').dt.date + df_sales["last_updated_time"] = df_sales["last_updated"].astype('datetime64[ns]').dt.floor('s').dt.time df_sales['agreed_delivery_date'] = pd.to_datetime(df_sales['agreed_delivery_date'],format="%Y-%m-%d") df_sales['agreed_payment_date'] = pd.to_datetime(df_sales['agreed_payment_date'],format="%Y-%m-%d") - df_sales.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_sales = df_sales.drop(labels=['created_at','last_updated'],axis=1) df_sales.reset_index(inplace=True) return df_sales @@ -34,13 +34,13 @@ def create_fact_sales_order(dict_of_df): def create_fact_purchase_orders(dict_of_df): df_po = dict_of_df['purchase_order'] df_po.index.name = 'purchase_record_id' - df_po['created_date'] = pd.to_datetime(df_po['created_at'].dt.date,format='%Y-%m-%d') - df_po['created_time'] = df_po['created_at'].dt.floor('s').dt.time - df_po['last_updated_date'] = pd.to_datetime(df_po['last_updated'].dt.date,format='%Y-%m-%d') - df_po['last_updated_time'] = df_po['last_updated'].dt.floor('s').dt.time + df_po['created_date'] = df_po['created_at'].astype('datetime64[ns]').dt.date + df_po['created_time'] = df_po['created_at'].astype('datetime64[ns]').dt.floor('s').dt.time + df_po['last_updated_date'] = df_po['last_updated'].astype('datetime64[ns]').dt.date + df_po['last_updated_time'] = df_po['last_updated'].astype('datetime64[ns]').dt.floor('s').dt.time df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") - df_po.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_po = df_po.drop(labels=['created_at','last_updated'],axis=1) df_po.reset_index(inplace=True) return df_po @@ -48,12 +48,12 @@ def create_fact_purchase_orders(dict_of_df): def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = pd.to_datetime(df_payment["created_at"].dt.date,format='%Y-%m-%d') - df_payment["created_time"] = df_payment["created_at"].dt.floor('s').dt.time - df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"].dt.date,format='%Y-%m-%d') - df_payment["last_updated_time"] = df_payment["last_updated"].dt.floor('s').dt.time + df_payment["created_date"] = df_payment["created_at"].astype('datetime64[ns]').dt.date + df_payment["created_time"] = df_payment["created_at"].astype('datetime64[ns]').dt.floor('s').dt.time + df_payment["last_updated_date"] = df_payment["last_updated"].astype('datetime64[ns]').dt.date + df_payment["last_updated_time"] = df_payment["last_updated"].astype('datetime64[ns]').dt.floor('s').dt.time df_payment['payment_date'] = pd.to_datetime(df_payment['payment_date'],format="%Y-%m-%d") - df_payment.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_payment = df_payment.drop(labels=['created_at','last_updated'],axis=1) df_payment.reset_index(inplace=True) return df_payment @@ -83,7 +83,7 @@ def create_dim_date(dict_of_df): fact_dfs = [create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df)] list_of_date_columns = [] for df in fact_dfs: - date_col_names = [col_name for col_name in list(df.columns) if 'date' in col_name] + date_col_names = [col_name for col_name in list(df.columns) if '_date' in col_name] for col in date_col_names: list_of_date_columns.append(df[col]) sr_date = pd.array(pd.concat(list_of_date_columns),dtype='datetime64[ns]') diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 2cd9272..ccf90e5 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -117,7 +117,7 @@ def process_to_parquet_and_upload_to_s3( parquet_file = df.to_parquet( f"{table_name}.parquet", engine="pyarrow" ) # or fastparquet - client.upload_file(parquet_file, bucket, f"{table_name}.parquet") + client.upload_file(f"{table_name}.parquet", bucket, f"{table_name}.parquet") #changed parquet_file variable to the file name status["uploaded"].append(table_name) for table_name, df in mutable_df_dict.items(): @@ -127,7 +127,7 @@ def process_to_parquet_and_upload_to_s3( parquet_file = df.to_parquet( f"{table_name}.parquet", engine="pyarrow" ) # or fastparquet - client.upload_file(parquet_file, bucket, s3_key) + client.upload_file(f"{table_name}.parquet", bucket, s3_key) status["uploaded"].append(table_name) return status @@ -203,7 +203,7 @@ def list_existing_s3_files(bucket_name, client=boto3.client("s3")): existing_files = [obj["Key"] for obj in response["Contents"]] else: logger.error("The bucket is empty") - return None + return [] #changed from None to [] so it is an iterable except ClientError as e: logger.error(f"Error listing S3 objects: {e}") diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index 70aefe8..adbb5ed 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -139,11 +139,7 @@ class TestCreateFactPayment: for col in list(result.columns): assert col in expected_cols for col in expected_cols: - if '_date' in col: - print(col) - assert result[col].dtype == 'datetime64[ns]' - if '_time' in col: - print(col) - assert result[col].dtype == 'O' #<< O for object - + if '_date' or '_time' in col: + assert result[col].dtype == 'O' + \ No newline at end of file -- cgit v1.2.3 From 57617571df0a667aca55fc54184696a19c689524 Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 17:00:08 +0100 Subject: add lambda handler updated tests --- tests/test_load_lambda.py | 1 + 1 file changed, 1 insertion(+) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 0b13b54..829b908 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -63,6 +63,7 @@ class TestLambdaHandler: + class TestRetrieveSecrets: def test_retrieve_secrets_returns_dictionary(self, mock_sm_client): secret = { -- cgit v1.2.3 From dc095acd4d5b9f73a716a076ce601c3810f9635b Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Tue, 27 Aug 2024 16:01:11 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 1a145a3 according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/101 --- src/dataframes.py | 236 ++++++++++++++++++++++++++------------- src/transform_lambda.py | 5 +- tests/test_dataframes.py | 282 +++++++++++++++++++++++++++++++++++------------ 3 files changed, 375 insertions(+), 148 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 9d0f2ac..f122368 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -2,7 +2,7 @@ import pandas as pd from bs4 import BeautifulSoup import requests -#Table names: +# Table names: # fact_sales_order # fact_purchase_orders # fact_payment @@ -16,133 +16,213 @@ import requests # dim_counterparty -#no test, same as fact_payment +# no test, same as fact_payment def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - df_sales["created_date"] = df_sales["created_at"].astype('datetime64[ns]').dt.date - df_sales["created_time"] = df_sales["created_at"].astype('datetime64[ns]').dt.floor('s').dt.time - df_sales["last_updated_date"] = df_sales["last_updated"].astype('datetime64[ns]').dt.date - df_sales["last_updated_time"] = df_sales["last_updated"].astype('datetime64[ns]').dt.floor('s').dt.time - df_sales['agreed_delivery_date'] = pd.to_datetime(df_sales['agreed_delivery_date'],format="%Y-%m-%d") - df_sales['agreed_payment_date'] = pd.to_datetime(df_sales['agreed_payment_date'],format="%Y-%m-%d") - df_sales = df_sales.drop(labels=['created_at','last_updated'],axis=1) + df_sales["created_date"] = df_sales["created_at"].astype("datetime64[ns]").dt.date + df_sales["created_time"] = ( + df_sales["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_sales["last_updated_date"] = ( + df_sales["last_updated"].astype("datetime64[ns]").dt.date + ) + df_sales["last_updated_time"] = ( + df_sales["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_sales["agreed_delivery_date"] = pd.to_datetime( + df_sales["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_sales["agreed_payment_date"] = pd.to_datetime( + df_sales["agreed_payment_date"], format="%Y-%m-%d" + ) + df_sales = df_sales.drop(labels=["created_at", "last_updated"], axis=1) df_sales.reset_index(inplace=True) return df_sales -#no test, same as fact_payment + +# no test, same as fact_payment + + def create_fact_purchase_orders(dict_of_df): - df_po = dict_of_df['purchase_order'] - df_po.index.name = 'purchase_record_id' - df_po['created_date'] = df_po['created_at'].astype('datetime64[ns]').dt.date - df_po['created_time'] = df_po['created_at'].astype('datetime64[ns]').dt.floor('s').dt.time - df_po['last_updated_date'] = df_po['last_updated'].astype('datetime64[ns]').dt.date - df_po['last_updated_time'] = df_po['last_updated'].astype('datetime64[ns]').dt.floor('s').dt.time - df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") - df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") - df_po = df_po.drop(labels=['created_at','last_updated'],axis=1) + df_po = dict_of_df["purchase_order"] + df_po.index.name = "purchase_record_id" + df_po["created_date"] = df_po["created_at"].astype("datetime64[ns]").dt.date + df_po["created_time"] = ( + df_po["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_po["last_updated_date"] = df_po["last_updated"].astype("datetime64[ns]").dt.date + df_po["last_updated_time"] = ( + df_po["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_po["agreed_delivery_date"] = pd.to_datetime( + df_po["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_po["agreed_payment_date"] = pd.to_datetime( + df_po["agreed_payment_date"], format="%Y-%m-%d" + ) + df_po = df_po.drop(labels=["created_at", "last_updated"], axis=1) df_po.reset_index(inplace=True) return df_po -#test passed + +# test passed + + def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = df_payment["created_at"].astype('datetime64[ns]').dt.date - df_payment["created_time"] = df_payment["created_at"].astype('datetime64[ns]').dt.floor('s').dt.time - df_payment["last_updated_date"] = df_payment["last_updated"].astype('datetime64[ns]').dt.date - df_payment["last_updated_time"] = df_payment["last_updated"].astype('datetime64[ns]').dt.floor('s').dt.time - df_payment['payment_date'] = pd.to_datetime(df_payment['payment_date'],format="%Y-%m-%d") - df_payment = df_payment.drop(labels=['created_at','last_updated'],axis=1) + df_payment["created_date"] = ( + df_payment["created_at"].astype("datetime64[ns]").dt.date + ) + df_payment["created_time"] = ( + df_payment["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_payment["last_updated_date"] = ( + df_payment["last_updated"].astype("datetime64[ns]").dt.date + ) + df_payment["last_updated_time"] = ( + df_payment["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_payment["payment_date"] = pd.to_datetime( + df_payment["payment_date"], format="%Y-%m-%d" + ) + df_payment = df_payment.drop(labels=["created_at", "last_updated"], axis=1) df_payment.reset_index(inplace=True) return df_payment -#test passed + +# test passed + + def create_dim_transaction(dict_of_df): - df_transaction = dict_of_df["transaction"].drop(labels=['created_at', 'last_updated'], axis=1) + df_transaction = dict_of_df["transaction"].drop( + labels=["created_at", "last_updated"], axis=1 + ) return df_transaction -#test passed + +# test passed + + def create_dim_location(dict_of_df): - df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}) + df_loc = ( + dict_of_df["address"] + .drop(labels=["created_at", "last_updated"], axis=1) + .rename(columns={"address_id": "location_id"}) + ) return df_loc def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) - df_cp = pd.merge(dict_of_df['counterparty'], - df_prefixed_address, - left_on="legal_address_id", - right_on="counterparty_legal_address_id", - how="outer") - df_cp.drop(columns=["legal_address_id","counterparty_legal_address_id"],inplace=True) + df_prefixed_address = dict_of_df["address"].add_prefix( + "counterparty_legal_", axis=1 + ) + df_cp = pd.merge( + dict_of_df["counterparty"], + df_prefixed_address, + left_on="legal_address_id", + right_on="counterparty_legal_address_id", + how="outer", + ) + df_cp.drop( + columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True + ) return df_cp -#test passed + +# test passed + + def create_dim_date(dict_of_df): - fact_dfs = [create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df)] + fact_dfs = [ + create_fact_payment(dict_of_df), + create_fact_purchase_orders(dict_of_df), + create_fact_sales_order(dict_of_df), + ] list_of_date_columns = [] for df in fact_dfs: - date_col_names = [col_name for col_name in list(df.columns) if '_date' in col_name] + date_col_names = [ + col_name for col_name in list(df.columns) if "_date" in col_name + ] for col in date_col_names: list_of_date_columns.append(df[col]) - sr_date = pd.array(pd.concat(list_of_date_columns),dtype='datetime64[ns]') - df_date = pd.DataFrame(data=sr_date,columns=['date_id']) + sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") + df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) df_date.drop_duplicates(inplace=True) - df_date['year'] = df_date['date_id'].dt.year - df_date['month'] = df_date['date_id'].dt.month - df_date['day'] = df_date['date_id'].dt.day - df_date['day_of_week'] = df_date['date_id'].dt.dayofweek - df_date['day_name'] = df_date['date_id'].dt.day_name() - df_date['month_name'] = df_date['date_id'].dt.month_name() - df_date['quarter'] = df_date['date_id'].dt.quarter + df_date["year"] = df_date["date_id"].dt.year + df_date["month"] = df_date["date_id"].dt.month + df_date["day"] = df_date["date_id"].dt.day + df_date["day_of_week"] = df_date["date_id"].dt.dayofweek + df_date["day_name"] = df_date["date_id"].dt.day_name() + df_date["month_name"] = df_date["date_id"].dt.month_name() + df_date["quarter"] = df_date["date_id"].dt.quarter return df_date -#tests passed -def scrape_currency_names(): - response = requests.get('https://www.xe.com/currency/').content - soup = BeautifulSoup(response,'html.parser') - currency = [item.text for item in soup.findAll('a', attrs={'class' : "sc-299dec64-6 fZPTSw"})] - sr = pd.Series(currency) - df_cur = sr.str.split(pat=" - ",expand=True).rename({0:'currency_code',1:'currency_name'},axis=1) - return df_cur - -#tests passed -def create_dim_currency(dict_of_df,names=scrape_currency_names()): - df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1) - dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner') - return dim_cur -#tests passed -def create_dim_payment_type(dict_of_df): - df_payment_type = dict_of_df["payment_type"] - dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] - return dim_payment_type +# tests passed -#tests passed -def create_dim_design(dict_of_df): - df_design = dict_of_df["design"] - dim_design = df_design.loc[:, ["design_id", "design_name", "file_name", "file_location"]] - return dim_design -#tests passed -def create_dim_staff(dict_of_df): - staff_department = pd.merge(dict_of_df["staff"], dict_of_df["department"], on='department_id', how="left") - dim_staff = staff_department.loc[:, ['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address']] - return dim_staff +def scrape_currency_names(): + response = requests.get("https://www.xe.com/currency/").content + soup = BeautifulSoup(response, "html.parser") + currency = [ + item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) + ] + sr = pd.Series(currency) + df_cur = sr.str.split(pat=" - ", expand=True).rename( + {0: "currency_code", 1: "currency_name"}, axis=1 + ) + return df_cur +# tests passed +def create_dim_currency(dict_of_df, names=scrape_currency_names()): + df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) + dim_cur = pd.merge( + df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" + ) + return dim_cur +# tests passed +def create_dim_payment_type(dict_of_df): + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + return dim_payment_type +# tests passed +def create_dim_design(dict_of_df): + df_design = dict_of_df["design"] + dim_design = df_design.loc[ + :, ["design_id", "design_name", "file_name", "file_location"] + ] + return dim_design +# tests passed +def create_dim_staff(dict_of_df): + staff_department = pd.merge( + dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" + ) + dim_staff = staff_department.loc[ + :, + [ + "staff_id", + "first_name", + "last_name", + "department_name", + "location", + "email_address", + ], + ] + return dim_staff diff --git a/src/transform_lambda.py b/src/transform_lambda.py index ccf90e5..93b2284 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -117,7 +117,8 @@ def process_to_parquet_and_upload_to_s3( parquet_file = df.to_parquet( f"{table_name}.parquet", engine="pyarrow" ) # or fastparquet - client.upload_file(f"{table_name}.parquet", bucket, f"{table_name}.parquet") #changed parquet_file variable to the file name + # changed parquet_file variable to the file name + client.upload_file(f"{table_name}.parquet", bucket, f"{table_name}.parquet") status["uploaded"].append(table_name) for table_name, df in mutable_df_dict.items(): @@ -203,7 +204,7 @@ def list_existing_s3_files(bucket_name, client=boto3.client("s3")): existing_files = [obj["Key"] for obj in response["Contents"]] else: logger.error("The bucket is empty") - return [] #changed from None to [] so it is an iterable + return [] # changed from None to [] so it is an iterable except ClientError as e: logger.error(f"Error listing S3 objects: {e}") diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index adbb5ed..c9ff43f 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -3,42 +3,88 @@ import pandas as pd from unittest.mock import patch from datetime import datetime as dt + class TestCreateDimDesign: def test_dim_design_returns_dataframe(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) assert isinstance(result, pd.DataFrame) def test_dim_design_returns_correct_columns_and_values(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) - d2 = {"design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"]} + d2 = { + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=d2) expected_result = expected_df.copy() assert result.equals(expected_result) + class TestCreateDimStaff: def test_dim_staff_returns_dataframe(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - assert isinstance(result, pd.DataFrame) + assert isinstance(result, pd.DataFrame) def test_dim_staff_returns_correct_columns_and_values(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - expected_d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"]} + expected_d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) expected_result = expected_df.copy() - assert result.equals(expected_result) + assert result.equals(expected_result) + class TestCreatePaymentType: def test_create_dim_payment_type_returns_correct_columns_and_values(self): @@ -46,100 +92,200 @@ class TestCreatePaymentType: test_df = {"payment_type": pd.DataFrame(data=d)} result = create_dim_payment_type(test_df) expected_columns = ["payment_type_id", "payment_type_name"] - expected_d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} + expected_d = { + "payment_type_id": ["Hello", "Bye"], + "payment_type_name": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns assert result.equals(expected_df) + class TestCreateDimCounterparty: - def test_create_dim_counterparty_type_returns_correct_columns_and_object(self): - data_l = pd.DataFrame(data={"counterparty_id": ["Hello", "Bye"], - "counterparty_legal_name": ["Hello", "Bye"], - "commercial_contact": ["Hello", "Bye"], - "legal_address_id": ["bond street", "regent street"]}) - data_a = pd.DataFrame(data={"address_id":["bond street", "regent street"], - "postcode":[98365,93753]}) - test_df = {"address": data_a,"counterparty":data_l} + data_l = pd.DataFrame( + data={ + "counterparty_id": ["Hello", "Bye"], + "counterparty_legal_name": ["Hello", "Bye"], + "commercial_contact": ["Hello", "Bye"], + "legal_address_id": ["bond street", "regent street"], + } + ) + data_a = pd.DataFrame( + data={ + "address_id": ["bond street", "regent street"], + "postcode": [98365, 93753], + } + ) + test_df = {"address": data_a, "counterparty": data_l} result = create_dim_counterparty(test_df) - expected_columns = ["counterparty_id", "counterparty_legal_name", - "commercial_contact", "counterparty_legal_postcode"] + expected_columns = [ + "counterparty_id", + "counterparty_legal_name", + "commercial_contact", + "counterparty_legal_postcode", + ] print(data_l) print(data_a) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns + class TestCreateDimCurrency: - def test_dim_currency_returns_columns_and_values(self): - nones = [None,None,None] - d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"],"created_at":nones,"last_updated":nones} + nones = [None, None, None] + d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "created_at": nones, + "last_updated": nones, + } test_df = {"currency": pd.DataFrame(data=d)} - scraper_output = pd.DataFrame({"currency_code":["RUS","USD","PHP","GBP","EUR"],"currency_name":["Rubble","US Dollar","Peso","Pound","Euro"]}) - result = create_dim_currency(test_df,names=scraper_output).sort_values(by="currency_code",axis=0) - expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} - expected_df = pd.DataFrame(data=expected_d).sort_values(by="currency_code",axis=0) - assert isinstance(result, pd.DataFrame) - assert result.equals(expected_df) + scraper_output = pd.DataFrame( + { + "currency_code": ["RUS", "USD", "PHP", "GBP", "EUR"], + "currency_name": ["Rubble", "US Dollar", "Peso", "Pound", "Euro"], + } + ) + result = create_dim_currency(test_df, names=scraper_output).sort_values( + by="currency_code", axis=0 + ) + expected_d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "currency_name": ["US Dollar", "Euro", "Pound"], + } + expected_df = pd.DataFrame(data=expected_d).sort_values( + by="currency_code", axis=0 + ) + assert isinstance(result, pd.DataFrame) + assert result.equals(expected_df) def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self): result = scrape_currency_names() - assert isinstance(result,pd.DataFrame) - assert list(result.columns) == ['currency_code', 'currency_name'] + assert isinstance(result, pd.DataFrame) + assert list(result.columns) == ["currency_code", "currency_name"] -class TestCreateDimDate: +class TestCreateDimDate: def test_returns_required_columns(self): - df_one = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 5, 13),'not_dat':None},index=[0]) - df_two = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 9, 13)},index=[0]) - df_three = pd.DataFrame(data={'updated_date':dt(2022, 5, 17),'created_date':dt(2023, 5, 13)},index=[0]) - expected_df = pd.DataFrame(data= - [[dt(2020,5,17),2020,5,17,6,'Sunday','May',2], - [dt(2021,5,13),2021,5,13,3,'Thursday','May',2], - [dt(2021,9,13),2021,9,13,0,'Monday','September',3], - [dt(2022,5,17),2022,5,17,1,'Tuesday','May',2], - [dt(2023,5,13),2023,5,13,5,'Saturday','May',2]], - columns=['date_id','year','month','day','day_of_week','day_name','month_name','quarter']) + df_one = pd.DataFrame( + data={ + "updated_date": dt(2020, 5, 17), + "created_date": dt(2021, 5, 13), + "not_dat": None, + }, + index=[0], + ) + df_two = pd.DataFrame( + data={"updated_date": dt(2020, 5, 17), "created_date": dt(2021, 9, 13)}, + index=[0], + ) + df_three = pd.DataFrame( + data={"updated_date": dt(2022, 5, 17), "created_date": dt(2023, 5, 13)}, + index=[0], + ) + expected_df = pd.DataFrame( + data=[ + [dt(2020, 5, 17), 2020, 5, 17, 6, "Sunday", "May", 2], + [dt(2021, 5, 13), 2021, 5, 13, 3, "Thursday", "May", 2], + [dt(2021, 9, 13), 2021, 9, 13, 0, "Monday", "September", 3], + [dt(2022, 5, 17), 2022, 5, 17, 1, "Tuesday", "May", 2], + [dt(2023, 5, 13), 2023, 5, 13, 5, "Saturday", "May", 2], + ], + columns=[ + "date_id", + "year", + "month", + "day", + "day_of_week", + "day_name", + "month_name", + "quarter", + ], + ) with patch("src.dataframes.create_fact_payment") as mock_fp: with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo: with patch("src.dataframes.create_fact_sales_order") as mock_fso: mock_fp.return_value = df_one mock_fpo.return_value = df_two mock_fso.return_value = df_three - result = create_dim_date({'dum':0}) - result.reset_index(inplace=True,drop=True) + result = create_dim_date({"dum": 0}) + result.reset_index(inplace=True, drop=True) assert result.eq(expected_df, axis="columns").all(axis=None) - -class TestCreateDimLocation: + +class TestCreateDimLocation: def test_returns_correct_columns_lo(self): - dict_df = {'address':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], - columns=['created_at','last_updated','address_id','postal_code'])} + dict_df = { + "address": pd.DataFrame( + data=[["some_time", "some_other_time", 1, "SE18 9QO"]], + columns=["created_at", "last_updated", "address_id", "postal_code"], + ) + } result = create_dim_location(dict_df) - assert list(result.columns) == ['location_id','postal_code'] - + assert list(result.columns) == ["location_id", "postal_code"] + + class TestCreateDimTransaction: - def test_returns_correct_columns_tr(self): - dict_df = {'transaction':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], - columns=['created_at','last_updated','transaction_id','some_other_id'])} + def test_returns_correct_columns_tr(self): + dict_df = { + "transaction": pd.DataFrame( + data=[["some_time", "some_other_time", 1, "SE18 9QO"]], + columns=[ + "created_at", + "last_updated", + "transaction_id", + "some_other_id", + ], + ) + } result = create_dim_transaction(dict_df) - assert list(result.columns) == ['transaction_id','some_other_id'] + assert list(result.columns) == ["transaction_id", "some_other_id"] + class TestCreateFactPayment: def test_returns_correct_columns_payment(self): - dict_df = {'payment':pd.DataFrame(data=[[dt.strptime('2022-11-03 14:20:49.962846','%Y-%m-%d %H:%M:%S.%f'), - dt.strptime('2022-12-14 16:20:49.962194','%Y-%m-%d %H:%M:%S.%f'),1,'SE18 9QO','2020-07-16']], - columns=['created_at','last_updated','payment_id','some_other_id','payment_date'])} - expected_cols = ['payment_record_id','created_date','created_time','last_updated_date', - 'last_updated_time','payment_date','payment_id','some_other_id'] + dict_df = { + "payment": pd.DataFrame( + data=[ + [ + dt.strptime( + "2022-11-03 14:20:49.962846", "%Y-%m-%d %H:%M:%S.%f" + ), + dt.strptime( + "2022-12-14 16:20:49.962194", "%Y-%m-%d %H:%M:%S.%f" + ), + 1, + "SE18 9QO", + "2020-07-16", + ] + ], + columns=[ + "created_at", + "last_updated", + "payment_id", + "some_other_id", + "payment_date", + ], + ) + } + expected_cols = [ + "payment_record_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "payment_date", + "payment_id", + "some_other_id", + ] result = create_fact_payment(dict_df) - assert isinstance(result,pd.DataFrame) + assert isinstance(result, pd.DataFrame) for col in list(result.columns): assert col in expected_cols for col in expected_cols: - if '_date' or '_time' in col: - assert result[col].dtype == 'O' - - \ No newline at end of file + if "_date" or "_time" in col: + assert result[col].dtype == "O" -- cgit v1.2.3 From aed1c19a39062e8fe86cf0a531b8d1486b06d1ac Mon Sep 17 00:00:00 2001 From: Ang Bel Date: Tue, 27 Aug 2024 12:42:25 +0100 Subject: test: fact transformation function for payment test passes, other fact functions are equivalent, no tests written --- src/dataframes.py | 251 ++++++++++++++--------------------------- tests/test_dataframes.py | 144 +++++++++++++++++++++++ tests/test_fact_sales_order.py | 246 ---------------------------------------- 3 files changed, 229 insertions(+), 412 deletions(-) create mode 100644 tests/test_dataframes.py delete mode 100644 tests/test_fact_sales_order.py diff --git a/src/dataframes.py b/src/dataframes.py index ab53063..41f39b8 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -2,7 +2,7 @@ import pandas as pd from bs4 import BeautifulSoup import requests -# Table names: +#Table names: # fact_sales_order # fact_purchase_orders # fact_payment @@ -16,214 +16,133 @@ import requests # dim_counterparty +#no test, same as fact_payment def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - df_sales["created_date"] = pd.to_datetime(df_sales["created_at"]).dt.date - df_sales["created_time"] = pd.to_datetime(df_sales["created_at"]).dt.time - df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"]).dt.date - df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time - fact_sales_order = df_sales.loc[ - :, - [ - "sales_record_id", - "sales_order_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "sales_staff_id", - "counterparty_id", - "units_sold", - "unit_price", - "currency_id", - "design_id", - "agreed_payment_date", - "agreed_delivery_date", - "agreed_delivery_location_id", - ], - ] - return fact_sales_order - - -# fact_purchase_order from purchase_order - - + df_sales["created_date"] = pd.to_datetime(df_sales["created_at"],format='%Y-%m-%d') + df_sales["created_time"] = pd.to_datetime(df_sales["created_at"],format='%H-%M-%S') + df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"],format='%Y-%m-%d') + df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"],format='%H-%M-%S') + df_sales['agreed_delivery_date'] = pd.to_datetime(df_sales['agreed_delivery_date'],format="%Y-%m-%d") + df_sales['agreed_payment_date'] = pd.to_datetime(df_sales['agreed_payment_date'],format="%Y-%m-%d") + df_sales.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_sales.reset_index(inplace=True) + return df_sales + +#no test, same as fact_payment def create_fact_purchase_orders(dict_of_df): - df_po = dict_of_df["purchase_order"] - df_po.index.name = "purchase_record_id" - df_po["created_date"] = df_po["created_at"].date() - df_po["created_time"] = df_po["created_at"].dt.time - df_po["last_updated_date"] = df_po["last_updated_at"].date() - df_po["last_updated_time"] = df_po["last_updated_at"].dt.time - df_po["agreed_delivery_date"] = pd.to_datetime( - df_po["agreed_delivery_date"], format="%Y-%m-%d" - ) - df_po["agreed_payment_date"] = pd.to_datetime( - df_po["agreed_payment_date"], format="%Y-%m-%d" - ) - df_po.drop(labels=["created_at", "last_updated_at"], axis=1, inplace=True) + df_po = dict_of_df['purchase_order'] + df_po.index.name = 'purchase_record_id' + df_po['created_date'] = pd.to_datetime(df_po['created_at'],format='%Y-%m-%d') + df_po['created_time'] = pd.to_datetime(df_po['created_at'],format='%H-%M-%S') + df_po['last_updated_date'] = pd.to_datetime(df_po['last_updated'],format='%Y-%m-%d') + df_po['last_updated_time'] = pd.to_datetime(df_po['last_updated'],format='%H-%M-%S') + df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") + df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") + df_po.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_po.reset_index(inplace=True) return df_po - +#test passed def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = df_payment["created_at"].date() - df_payment["created_time"] = df_payment["created_at"].time - df_payment["last_updated_date"] = df_payment["last_updated"].date() - df_payment["last_updated_time"] = df_payment["last_updated"].time - df_payment["payment_date"] = pd.to_datetime( - df_payment["payment_date"], format="%Y-%m-%d" - ) - fact_payment = df_payment.loc[ - :, - [ - "payment_record_id", - "payment_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "transaction_id", - "counterparty_id", - "payment_amount", - "currency_id", - "payment_type_id", - "paid", - "payment_date", - ], - ] - return fact_payment - - -# test passed - - + df_payment["created_date"] = pd.to_datetime(df_payment["created_at"],format='%Y-%m-%d') + df_payment["created_time"] = pd.to_datetime(df_payment["created_at"],format='%H-%M-%S') + df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"],format='%Y-%m-%d') + df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"],format='%H-%M-%S') + df_payment['payment_date'] = pd.to_datetime(df_payment['payment_date'],format="%Y-%m-%d") + df_payment.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_payment.reset_index(inplace=True) + return df_payment + +#test passed def create_dim_transaction(dict_of_df): - df_transaction = dict_of_df["transaction"].drop( - labels=["created_at", "last_updated"], axis=1 - ) + df_transaction = dict_of_df["transaction"].drop(labels=['created_at', 'last_updated'], axis=1) return df_transaction - -# test passed +#test passed def create_dim_location(dict_of_df): - df_loc = ( - dict_of_df["address"] - .drop(labels=["created_at", "last_updated"], axis=1) - .rename(columns={"address_id": "location_id"}) - ) + df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}) return df_loc def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df["address"].add_prefix( - "counterparty_legal_", axis=1 - ) - df_cp = pd.merge( - dict_of_df["counterparty"], - df_prefixed_address, - left_on="legal_address_id", - right_on="counterparty_legal_address_id", - how="outer", - ) - df_cp.drop( - columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True - ) + df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) + df_cp = pd.merge(dict_of_df['counterparty'], + df_prefixed_address, + left_on="legal_address_id", + right_on="counterparty_legal_address_id", + how="outer") + df_cp.drop(columns=["legal_address_id","counterparty_legal_address_id"],inplace=True) return df_cp - -# test passed - - +#test passed def create_dim_date(dict_of_df): - fact_dfs = [ - create_fact_payment(dict_of_df), - create_fact_purchase_orders(dict_of_df), - create_fact_sales_order(dict_of_df), - ] - date_col_names = [ - col_name for col_name in list(fact_dfs[0].columns) if "date" in col_name - ] + fact_dfs = [create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df)] list_of_date_columns = [] for df in fact_dfs: + date_col_names = [col_name for col_name in list(df.columns) if 'date' in col_name] for col in date_col_names: list_of_date_columns.append(df[col]) - sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") - df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) + sr_date = pd.array(pd.concat(list_of_date_columns),dtype='datetime64[ns]') + df_date = pd.DataFrame(data=sr_date,columns=['date_id']) df_date.drop_duplicates(inplace=True) - df_date["year"] = df_date["date_id"].dt.year - df_date["month"] = df_date["date_id"].dt.month - df_date["day"] = df_date["date_id"].dt.day - df_date["day_of_week"] = df_date["date_id"].dt.dayofweek - df_date["day_name"] = df_date["date_id"].dt.day_name() - df_date["month_name"] = df_date["date_id"].dt.month_name() - df_date["quarter"] = df_date["date_id"].dt.quarter + df_date['year'] = df_date['date_id'].dt.year + df_date['month'] = df_date['date_id'].dt.month + df_date['day'] = df_date['date_id'].dt.day + df_date['day_of_week'] = df_date['date_id'].dt.dayofweek + df_date['day_name'] = df_date['date_id'].dt.day_name() + df_date['month_name'] = df_date['date_id'].dt.month_name() + df_date['quarter'] = df_date['date_id'].dt.quarter return df_date - -# tests passed +#tests passed def scrape_currency_names(): - response = requests.get("https://www.xe.com/currency/").content - soup = BeautifulSoup(response, "html.parser") - currency = [ - item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) - ] + response = requests.get('https://www.xe.com/currency/').content + soup = BeautifulSoup(response,'html.parser') + currency = [item.text for item in soup.findAll('a', attrs={'class' : "sc-299dec64-6 fZPTSw"})] sr = pd.Series(currency) - df_cur = sr.str.split(pat=" - ", expand=True).rename( - {0: "currency_code", 1: "currency_name"}, axis=1 - ) + df_cur = sr.str.split(pat=" - ",expand=True).rename({0:'currency_code',1:'currency_name'},axis=1) return df_cur +#tests passed +def create_dim_currency(dict_of_df,names=scrape_currency_names()): + df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1) + dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner') + return dim_cur + +#tests passed +def create_dim_payment_type(dict_of_df): + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + return dim_payment_type + +#tests passed +def create_dim_design(dict_of_df): + df_design = dict_of_df["design"] + dim_design = df_design.loc[:, ["design_id", "design_name", "file_name", "file_location"]] + return dim_design +#tests passed +def create_dim_staff(dict_of_df): + staff_department = pd.merge(dict_of_df["staff"], dict_of_df["department"], on='department_id', how="left") + dim_staff = staff_department.loc[:, ['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address']] + return dim_staff + + -# tests passed -def create_dim_currency(dict_of_df, names=scrape_currency_names()): - df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) - dim_cur = pd.merge( - df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" - ) - return dim_cur -# tests passed -def create_dim_payment_type(dict_of_df): - df_payment_type = dict_of_df["payment_type"] - dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] - return dim_payment_type -# tests passed -def create_dim_design(dict_of_df): - df_design = dict_of_df["design"] - dim_design = df_design.loc[ - :, ["design_id", "design_name", "file_name", "file_location"] - ] - return dim_design -# tests passed -def create_dim_staff(dict_of_df): - staff_department = pd.merge( - dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" - ) - dim_staff = staff_department.loc[ - :, - [ - "staff_id", - "first_name", - "last_name", - "department_name", - "location", - "email_address", - ], - ] - return dim_staff diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py new file mode 100644 index 0000000..8f32b1d --- /dev/null +++ b/tests/test_dataframes.py @@ -0,0 +1,144 @@ +from src.dataframes import * +import pandas as pd +from unittest.mock import patch +from datetime import datetime as dt + +class TestCreateDimDesign: + def test_dim_design_returns_dataframe(self): + d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + test_df = {"design": pd.DataFrame(data=d)} + result = create_dim_design(test_df) + assert isinstance(result, pd.DataFrame) + + def test_dim_design_returns_correct_columns_and_values(self): + d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + test_df = {"design": pd.DataFrame(data=d)} + result = create_dim_design(test_df) + d2 = {"design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"]} + expected_df = pd.DataFrame(data=d2) + expected_result = expected_df.copy() + assert result.equals(expected_result) + +class TestCreateDimStaff: + def test_dim_staff_returns_dataframe(self): + d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} + result = create_dim_staff(test_df) + assert isinstance(result, pd.DataFrame) + + def test_dim_staff_returns_correct_columns_and_values(self): + d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} + result = create_dim_staff(test_df) + expected_d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"]} + expected_df = pd.DataFrame(data=expected_d) + expected_result = expected_df.copy() + assert result.equals(expected_result) + +class TestCreatePaymentType: + def test_create_dim_payment_type_returns_correct_columns_and_values(self): + d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} + test_df = {"payment_type": pd.DataFrame(data=d)} + result = create_dim_payment_type(test_df) + expected_columns = ["payment_type_id", "payment_type_name"] + expected_d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} + expected_df = pd.DataFrame(data=expected_d) + assert isinstance(result, pd.DataFrame) + assert list(result.columns) == expected_columns + assert result.equals(expected_df) + +class TestCreateDimCounterparty: + + def test_create_dim_counterparty_type_returns_correct_columns_and_object(self): + data_l = pd.DataFrame(data={"counterparty_id": ["Hello", "Bye"], + "counterparty_legal_name": ["Hello", "Bye"], + "commercial_contact": ["Hello", "Bye"], + "legal_address_id": ["bond street", "regent street"]}) + data_a = pd.DataFrame(data={"address_id":["bond street", "regent street"], + "postcode":[98365,93753]}) + test_df = {"address": data_a,"counterparty":data_l} + result = create_dim_counterparty(test_df) + + expected_columns = ["counterparty_id", "counterparty_legal_name", + "commercial_contact", "counterparty_legal_postcode"] + print(data_l) + print(data_a) + assert isinstance(result, pd.DataFrame) + assert list(result.columns) == expected_columns + +class TestCreateDimCurrency: + + def test_dim_currency_returns_columns_and_values(self): + nones = [None,None,None] + d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"],"created_at":nones,"last_updated":nones} + test_df = {"currency": pd.DataFrame(data=d)} + scraper_output = pd.DataFrame({"currency_code":["RUS","USD","PHP","GBP","EUR"],"currency_name":["Rubble","US Dollar","Peso","Pound","Euro"]}) + result = create_dim_currency(test_df,names=scraper_output).sort_values(by="currency_code",axis=0) + expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} + expected_df = pd.DataFrame(data=expected_d).sort_values(by="currency_code",axis=0) + assert isinstance(result, pd.DataFrame) + assert result.equals(expected_df) + + def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self): + result = scrape_currency_names() + assert isinstance(result,pd.DataFrame) + assert list(result.columns) == ['currency_code', 'currency_name'] + +class TestCreateDimDate: + + def test_returns_required_columns(self): + df_one = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 5, 13),'not_dat':None},index=[0]) + df_two = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 9, 13)},index=[0]) + df_three = pd.DataFrame(data={'updated_date':dt(2022, 5, 17),'created_date':dt(2023, 5, 13)},index=[0]) + expected_df = pd.DataFrame(data= + [[dt(2020,5,17),2020,5,17,6,'Sunday','May',2], + [dt(2021,5,13),2021,5,13,3,'Thursday','May',2], + [dt(2021,9,13),2021,9,13,0,'Monday','September',3], + [dt(2022,5,17),2022,5,17,1,'Tuesday','May',2], + [dt(2023,5,13),2023,5,13,5,'Saturday','May',2]], + columns=['date_id','year','month','day','day_of_week','day_name','month_name','quarter']) + with patch("src.dataframes.create_fact_payment") as mock_fp: + with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo: + with patch("src.dataframes.create_fact_sales_order") as mock_fso: + mock_fp.return_value = df_one + mock_fpo.return_value = df_two + mock_fso.return_value = df_three + result = create_dim_date({'dum':0}) + result.reset_index(inplace=True,drop=True) + assert result.eq(expected_df, axis="columns").all(axis=None) + +class TestCreateDimLocation: + + def test_returns_correct_columns_lo(self): + dict_df = {'address':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], + columns=['created_at','last_updated','address_id','postal_code'])} + result = create_dim_location(dict_df) + assert list(result.columns) == ['location_id','postal_code'] + +class TestCreateDimTransaction: + def test_returns_correct_columns_tr(self): + dict_df = {'transaction':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], + columns=['created_at','last_updated','transaction_id','some_other_id'])} + result = create_dim_transaction(dict_df) + assert list(result.columns) == ['transaction_id','some_other_id'] + +class TestCreateFactPayment: + def test_returns_correct_columns_payment(self): + dict_df = {'payment':pd.DataFrame(data=[[dt(2020,5,17,6,15,20),dt(2020,5,20,8,19,30),1,'SE18 9QO','2020-7-16']], + columns=['created_at','last_updated','payment_id','some_other_id','payment_date'])} + expected_cols = ['payment_record_id','created_date','created_time','last_updated_date', + 'last_updated_time','payment_date','payment_id','some_other_id'] + result = create_fact_payment(dict_df) + assert isinstance(result,pd.DataFrame) + for col in list(result.columns): + assert col in expected_cols + for col in expected_cols: + if 'date' in col: + assert result[col].dtype == 'datetime64[ns]' + + \ No newline at end of file diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py deleted file mode 100644 index a245379..0000000 --- a/tests/test_fact_sales_order.py +++ /dev/null @@ -1,246 +0,0 @@ -from src.dataframes import * -import pandas as pd -from unittest.mock import patch -from datetime import datetime as dt - - -class TestCreateDimDesign: - def test_dim_design_returns_dataframe(self): - d = { - "test": ["Hello", "Bye"], - "design_id": ["Hello", "Bye"], - "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"], - "Hello": ["Hello", "Bye"], - } - test_df = {"design": pd.DataFrame(data=d)} - result = create_dim_design(test_df) - assert isinstance(result, pd.DataFrame) - - def test_dim_design_returns_correct_columns_and_values(self): - d = { - "test": ["Hello", "Bye"], - "design_id": ["Hello", "Bye"], - "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"], - "Hello": ["Hello", "Bye"], - } - test_df = {"design": pd.DataFrame(data=d)} - result = create_dim_design(test_df) - d2 = { - "design_id": ["Hello", "Bye"], - "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"], - } - expected_df = pd.DataFrame(data=d2) - expected_result = expected_df.copy() - assert result.equals(expected_result) - - -class TestCreateDimStaff: - def test_dim_staff_returns_dataframe(self): - d = { - "staff_id": ["Hello", "Bye"], - "first_name": ["Hello", "Bye"], - "last_name": ["Hello", "Bye"], - "department_id": ["Hello", "Bye"], - } - d2 = { - "department_name": ["Hello", "Bye"], - "location": ["Hello", "Bye"], - "email_address": ["Hello", "Bye"], - "department_id": ["Hello", "Bye"], - } - test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} - result = create_dim_staff(test_df) - assert isinstance(result, pd.DataFrame) - - def test_dim_staff_returns_correct_columns_and_values(self): - d = { - "staff_id": ["Hello", "Bye"], - "first_name": ["Hello", "Bye"], - "last_name": ["Hello", "Bye"], - "department_id": ["Hello", "Bye"], - } - d2 = { - "department_name": ["Hello", "Bye"], - "location": ["Hello", "Bye"], - "email_address": ["Hello", "Bye"], - "department_id": ["Hello", "Bye"], - } - test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} - result = create_dim_staff(test_df) - expected_d = { - "staff_id": ["Hello", "Bye"], - "first_name": ["Hello", "Bye"], - "last_name": ["Hello", "Bye"], - "department_name": ["Hello", "Bye"], - "location": ["Hello", "Bye"], - "email_address": ["Hello", "Bye"], - } - expected_df = pd.DataFrame(data=expected_d) - expected_result = expected_df.copy() - assert result.equals(expected_result) - - -class TestCreatePaymentType: - def test_create_dim_payment_type_returns_correct_columns_and_values(self): - d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} - test_df = {"payment_type": pd.DataFrame(data=d)} - result = create_dim_payment_type(test_df) - expected_columns = ["payment_type_id", "payment_type_name"] - expected_d = { - "payment_type_id": ["Hello", "Bye"], - "payment_type_name": ["Hello", "Bye"], - } - expected_df = pd.DataFrame(data=expected_d) - assert isinstance(result, pd.DataFrame) - assert list(result.columns) == expected_columns - assert result.equals(expected_df) - - -class TestCreateDimCounterparty: - def test_create_dim_counterparty_type_returns_correct_columns_and_object(self): - data_l = pd.DataFrame( - data={ - "counterparty_id": ["Hello", "Bye"], - "counterparty_legal_name": ["Hello", "Bye"], - "commercial_contact": ["Hello", "Bye"], - "legal_address_id": ["bond street", "regent street"], - } - ) - data_a = pd.DataFrame( - data={ - "address_id": ["bond street", "regent street"], - "postcode": [98365, 93753], - } - ) - test_df = {"address": data_a, "counterparty": data_l} - result = create_dim_counterparty(test_df) - - expected_columns = [ - "counterparty_id", - "counterparty_legal_name", - "commercial_contact", - "counterparty_legal_postcode", - ] - print(data_l) - print(data_a) - assert isinstance(result, pd.DataFrame) - assert list(result.columns) == expected_columns - - -class TestCreateDimCurrency: - def test_dim_currency_returns_columns_and_values(self): - nones = [None, None, None] - d = { - "currency_id": [1, 2, 3], - "currency_code": ["USD", "EUR", "GBP"], - "created_at": nones, - "last_updated": nones, - } - test_df = {"currency": pd.DataFrame(data=d)} - scraper_output = pd.DataFrame( - { - "currency_code": ["RUS", "USD", "PHP", "GBP", "EUR"], - "currency_name": ["Rubble", "US Dollar", "Peso", "Pound", "Euro"], - } - ) - result = create_dim_currency(test_df, names=scraper_output).sort_values( - by="currency_code", axis=0 - ) - expected_d = { - "currency_id": [1, 2, 3], - "currency_code": ["USD", "EUR", "GBP"], - "currency_name": ["US Dollar", "Euro", "Pound"], - } - expected_df = pd.DataFrame(data=expected_d).sort_values( - by="currency_code", axis=0 - ) - assert isinstance(result, pd.DataFrame) - assert result.equals(expected_df) - - def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self): - result = scrape_currency_names() - assert isinstance(result, pd.DataFrame) - assert list(result.columns) == ["currency_code", "currency_name"] - - -class TestCreateDimDate: - def test_returns_required_columns(self): - df_one = pd.DataFrame( - data={ - "updated_date": dt(2020, 5, 17), - "created_date": dt(2021, 5, 13), - "not_dat": None, - }, - index=[0], - ) - df_two = pd.DataFrame( - data={"updated_date": dt(2020, 5, 17), "created_date": dt(2021, 9, 13)}, - index=[0], - ) - df_three = pd.DataFrame( - data={"updated_date": dt(2022, 5, 17), "created_date": dt(2023, 5, 13)}, - index=[0], - ) - expected_df = pd.DataFrame( - data=[ - [dt(2020, 5, 17), 2020, 5, 17, 6, "Sunday", "May", 2], - [dt(2021, 5, 13), 2021, 5, 13, 3, "Thursday", "May", 2], - [dt(2021, 9, 13), 2021, 9, 13, 0, "Monday", "September", 3], - [dt(2022, 5, 17), 2022, 5, 17, 1, "Tuesday", "May", 2], - [dt(2023, 5, 13), 2023, 5, 13, 5, "Saturday", "May", 2], - ], - columns=[ - "date_id", - "year", - "month", - "day", - "day_of_week", - "day_name", - "month_name", - "quarter", - ], - ) - with patch("src.dataframes.create_fact_payment") as mock_fp: - with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo: - with patch("src.dataframes.create_fact_sales_order") as mock_fso: - mock_fp.return_value = df_one - mock_fpo.return_value = df_two - mock_fso.return_value = df_three - result = create_dim_date({"dum": 0}) - result.reset_index(inplace=True, drop=True) - assert result.eq(expected_df, axis="columns").all(axis=None) - - -class TestCreateDimLocation: - def test_returns_correct_columns_lo(self): - dict_df = { - "address": pd.DataFrame( - data=[["some_time", "some_other_time", 1, "SE18 9QO"]], - columns=["created_at", "last_updated", "address_id", "postal_code"], - ) - } - result = create_dim_location(dict_df) - assert list(result.columns) == ["location_id", "postal_code"] - - -class TestCreateDimTransaction: - def test_returns_correct_columns_tr(self): - dict_df = { - "transaction": pd.DataFrame( - data=[["some_time", "some_other_time", 1, "SE18 9QO"]], - columns=[ - "created_at", - "last_updated", - "transaction_id", - "some_other_id", - ], - ) - } - result = create_dim_transaction(dict_df) - assert list(result.columns) == ["transaction_id", "some_other_id"] -- cgit v1.2.3 From 8588d4b318d7732d33a59bc6c8b93870310668c5 Mon Sep 17 00:00:00 2001 From: Ang Bel Date: Tue, 27 Aug 2024 15:18:54 +0100 Subject: test: refactored fact functions with test passing --- src/dataframes.py | 24 ++++++++++++------------ tests/test_dataframes.py | 9 +++++++-- 2 files changed, 19 insertions(+), 14 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 41f39b8..1f445a4 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -20,10 +20,10 @@ import requests def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - df_sales["created_date"] = pd.to_datetime(df_sales["created_at"],format='%Y-%m-%d') - df_sales["created_time"] = pd.to_datetime(df_sales["created_at"],format='%H-%M-%S') - df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"],format='%Y-%m-%d') - df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"],format='%H-%M-%S') + df_sales["created_date"] = pd.to_datetime(df_sales["created_at"].dt.date,format='%Y-%m-%d') + df_sales["created_time"] = df_sales["created_at"].dt.floor('s').dt.time + df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"].dt.date,format='%Y-%m-%d') + df_sales["last_updated_time"] = df_sales["last_updated"].dt.floor('s').dt.time df_sales['agreed_delivery_date'] = pd.to_datetime(df_sales['agreed_delivery_date'],format="%Y-%m-%d") df_sales['agreed_payment_date'] = pd.to_datetime(df_sales['agreed_payment_date'],format="%Y-%m-%d") df_sales.drop(labels=['created_at','last_updated'],axis=1,inplace=True) @@ -34,10 +34,10 @@ def create_fact_sales_order(dict_of_df): def create_fact_purchase_orders(dict_of_df): df_po = dict_of_df['purchase_order'] df_po.index.name = 'purchase_record_id' - df_po['created_date'] = pd.to_datetime(df_po['created_at'],format='%Y-%m-%d') - df_po['created_time'] = pd.to_datetime(df_po['created_at'],format='%H-%M-%S') - df_po['last_updated_date'] = pd.to_datetime(df_po['last_updated'],format='%Y-%m-%d') - df_po['last_updated_time'] = pd.to_datetime(df_po['last_updated'],format='%H-%M-%S') + df_po['created_date'] = pd.to_datetime(df_po['created_at'].dt.date,format='%Y-%m-%d') + df_po['created_time'] = df_po['created_at'].dt.floor('s').dt.time + df_po['last_updated_date'] = pd.to_datetime(df_po['last_updated'].dt.date,format='%Y-%m-%d') + df_po['last_updated_time'] = df_po['last_updated'].dt.floor('s').dt.time df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") df_po.drop(labels=['created_at','last_updated'],axis=1,inplace=True) @@ -48,10 +48,10 @@ def create_fact_purchase_orders(dict_of_df): def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = pd.to_datetime(df_payment["created_at"],format='%Y-%m-%d') - df_payment["created_time"] = pd.to_datetime(df_payment["created_at"],format='%H-%M-%S') - df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"],format='%Y-%m-%d') - df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"],format='%H-%M-%S') + df_payment["created_date"] = pd.to_datetime(df_payment["created_at"].dt.date,format='%Y-%m-%d') + df_payment["created_time"] = df_payment["created_at"].dt.floor('s').dt.time + df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"].dt.date,format='%Y-%m-%d') + df_payment["last_updated_time"] = df_payment["last_updated"].dt.floor('s').dt.time df_payment['payment_date'] = pd.to_datetime(df_payment['payment_date'],format="%Y-%m-%d") df_payment.drop(labels=['created_at','last_updated'],axis=1,inplace=True) df_payment.reset_index(inplace=True) diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index 8f32b1d..70aefe8 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -129,7 +129,8 @@ class TestCreateDimTransaction: class TestCreateFactPayment: def test_returns_correct_columns_payment(self): - dict_df = {'payment':pd.DataFrame(data=[[dt(2020,5,17,6,15,20),dt(2020,5,20,8,19,30),1,'SE18 9QO','2020-7-16']], + dict_df = {'payment':pd.DataFrame(data=[[dt.strptime('2022-11-03 14:20:49.962846','%Y-%m-%d %H:%M:%S.%f'), + dt.strptime('2022-12-14 16:20:49.962194','%Y-%m-%d %H:%M:%S.%f'),1,'SE18 9QO','2020-07-16']], columns=['created_at','last_updated','payment_id','some_other_id','payment_date'])} expected_cols = ['payment_record_id','created_date','created_time','last_updated_date', 'last_updated_time','payment_date','payment_id','some_other_id'] @@ -138,7 +139,11 @@ class TestCreateFactPayment: for col in list(result.columns): assert col in expected_cols for col in expected_cols: - if 'date' in col: + if '_date' in col: + print(col) assert result[col].dtype == 'datetime64[ns]' + if '_time' in col: + print(col) + assert result[col].dtype == 'O' #<< O for object \ No newline at end of file -- cgit v1.2.3 From efab1eccd4e2f0a8069ff4f1c968807a9c1ce05f Mon Sep 17 00:00:00 2001 From: Ang Bel Date: Tue, 27 Aug 2024 17:00:04 +0100 Subject: test: transform refactoring - it now loads parquet files into s3 bucket --- src/dataframes.py | 32 ++++++++++++++++---------------- src/transform_lambda.py | 6 +++--- tests/test_dataframes.py | 10 +++------- 3 files changed, 22 insertions(+), 26 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 1f445a4..9d0f2ac 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -20,13 +20,13 @@ import requests def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - df_sales["created_date"] = pd.to_datetime(df_sales["created_at"].dt.date,format='%Y-%m-%d') - df_sales["created_time"] = df_sales["created_at"].dt.floor('s').dt.time - df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"].dt.date,format='%Y-%m-%d') - df_sales["last_updated_time"] = df_sales["last_updated"].dt.floor('s').dt.time + df_sales["created_date"] = df_sales["created_at"].astype('datetime64[ns]').dt.date + df_sales["created_time"] = df_sales["created_at"].astype('datetime64[ns]').dt.floor('s').dt.time + df_sales["last_updated_date"] = df_sales["last_updated"].astype('datetime64[ns]').dt.date + df_sales["last_updated_time"] = df_sales["last_updated"].astype('datetime64[ns]').dt.floor('s').dt.time df_sales['agreed_delivery_date'] = pd.to_datetime(df_sales['agreed_delivery_date'],format="%Y-%m-%d") df_sales['agreed_payment_date'] = pd.to_datetime(df_sales['agreed_payment_date'],format="%Y-%m-%d") - df_sales.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_sales = df_sales.drop(labels=['created_at','last_updated'],axis=1) df_sales.reset_index(inplace=True) return df_sales @@ -34,13 +34,13 @@ def create_fact_sales_order(dict_of_df): def create_fact_purchase_orders(dict_of_df): df_po = dict_of_df['purchase_order'] df_po.index.name = 'purchase_record_id' - df_po['created_date'] = pd.to_datetime(df_po['created_at'].dt.date,format='%Y-%m-%d') - df_po['created_time'] = df_po['created_at'].dt.floor('s').dt.time - df_po['last_updated_date'] = pd.to_datetime(df_po['last_updated'].dt.date,format='%Y-%m-%d') - df_po['last_updated_time'] = df_po['last_updated'].dt.floor('s').dt.time + df_po['created_date'] = df_po['created_at'].astype('datetime64[ns]').dt.date + df_po['created_time'] = df_po['created_at'].astype('datetime64[ns]').dt.floor('s').dt.time + df_po['last_updated_date'] = df_po['last_updated'].astype('datetime64[ns]').dt.date + df_po['last_updated_time'] = df_po['last_updated'].astype('datetime64[ns]').dt.floor('s').dt.time df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") - df_po.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_po = df_po.drop(labels=['created_at','last_updated'],axis=1) df_po.reset_index(inplace=True) return df_po @@ -48,12 +48,12 @@ def create_fact_purchase_orders(dict_of_df): def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = pd.to_datetime(df_payment["created_at"].dt.date,format='%Y-%m-%d') - df_payment["created_time"] = df_payment["created_at"].dt.floor('s').dt.time - df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"].dt.date,format='%Y-%m-%d') - df_payment["last_updated_time"] = df_payment["last_updated"].dt.floor('s').dt.time + df_payment["created_date"] = df_payment["created_at"].astype('datetime64[ns]').dt.date + df_payment["created_time"] = df_payment["created_at"].astype('datetime64[ns]').dt.floor('s').dt.time + df_payment["last_updated_date"] = df_payment["last_updated"].astype('datetime64[ns]').dt.date + df_payment["last_updated_time"] = df_payment["last_updated"].astype('datetime64[ns]').dt.floor('s').dt.time df_payment['payment_date'] = pd.to_datetime(df_payment['payment_date'],format="%Y-%m-%d") - df_payment.drop(labels=['created_at','last_updated'],axis=1,inplace=True) + df_payment = df_payment.drop(labels=['created_at','last_updated'],axis=1) df_payment.reset_index(inplace=True) return df_payment @@ -83,7 +83,7 @@ def create_dim_date(dict_of_df): fact_dfs = [create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df)] list_of_date_columns = [] for df in fact_dfs: - date_col_names = [col_name for col_name in list(df.columns) if 'date' in col_name] + date_col_names = [col_name for col_name in list(df.columns) if '_date' in col_name] for col in date_col_names: list_of_date_columns.append(df[col]) sr_date = pd.array(pd.concat(list_of_date_columns),dtype='datetime64[ns]') diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 2cd9272..ccf90e5 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -117,7 +117,7 @@ def process_to_parquet_and_upload_to_s3( parquet_file = df.to_parquet( f"{table_name}.parquet", engine="pyarrow" ) # or fastparquet - client.upload_file(parquet_file, bucket, f"{table_name}.parquet") + client.upload_file(f"{table_name}.parquet", bucket, f"{table_name}.parquet") #changed parquet_file variable to the file name status["uploaded"].append(table_name) for table_name, df in mutable_df_dict.items(): @@ -127,7 +127,7 @@ def process_to_parquet_and_upload_to_s3( parquet_file = df.to_parquet( f"{table_name}.parquet", engine="pyarrow" ) # or fastparquet - client.upload_file(parquet_file, bucket, s3_key) + client.upload_file(f"{table_name}.parquet", bucket, s3_key) status["uploaded"].append(table_name) return status @@ -203,7 +203,7 @@ def list_existing_s3_files(bucket_name, client=boto3.client("s3")): existing_files = [obj["Key"] for obj in response["Contents"]] else: logger.error("The bucket is empty") - return None + return [] #changed from None to [] so it is an iterable except ClientError as e: logger.error(f"Error listing S3 objects: {e}") diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index 70aefe8..adbb5ed 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -139,11 +139,7 @@ class TestCreateFactPayment: for col in list(result.columns): assert col in expected_cols for col in expected_cols: - if '_date' in col: - print(col) - assert result[col].dtype == 'datetime64[ns]' - if '_time' in col: - print(col) - assert result[col].dtype == 'O' #<< O for object - + if '_date' or '_time' in col: + assert result[col].dtype == 'O' + \ No newline at end of file -- cgit v1.2.3 From 26902dc234c114382c2926923820c3537490c30e Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Tue, 27 Aug 2024 16:01:11 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 1a145a3 according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/101 --- src/dataframes.py | 236 ++++++++++++++++++++++++++------------- src/transform_lambda.py | 5 +- tests/test_dataframes.py | 282 +++++++++++++++++++++++++++++++++++------------ 3 files changed, 375 insertions(+), 148 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 9d0f2ac..f122368 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -2,7 +2,7 @@ import pandas as pd from bs4 import BeautifulSoup import requests -#Table names: +# Table names: # fact_sales_order # fact_purchase_orders # fact_payment @@ -16,133 +16,213 @@ import requests # dim_counterparty -#no test, same as fact_payment +# no test, same as fact_payment def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - df_sales["created_date"] = df_sales["created_at"].astype('datetime64[ns]').dt.date - df_sales["created_time"] = df_sales["created_at"].astype('datetime64[ns]').dt.floor('s').dt.time - df_sales["last_updated_date"] = df_sales["last_updated"].astype('datetime64[ns]').dt.date - df_sales["last_updated_time"] = df_sales["last_updated"].astype('datetime64[ns]').dt.floor('s').dt.time - df_sales['agreed_delivery_date'] = pd.to_datetime(df_sales['agreed_delivery_date'],format="%Y-%m-%d") - df_sales['agreed_payment_date'] = pd.to_datetime(df_sales['agreed_payment_date'],format="%Y-%m-%d") - df_sales = df_sales.drop(labels=['created_at','last_updated'],axis=1) + df_sales["created_date"] = df_sales["created_at"].astype("datetime64[ns]").dt.date + df_sales["created_time"] = ( + df_sales["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_sales["last_updated_date"] = ( + df_sales["last_updated"].astype("datetime64[ns]").dt.date + ) + df_sales["last_updated_time"] = ( + df_sales["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_sales["agreed_delivery_date"] = pd.to_datetime( + df_sales["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_sales["agreed_payment_date"] = pd.to_datetime( + df_sales["agreed_payment_date"], format="%Y-%m-%d" + ) + df_sales = df_sales.drop(labels=["created_at", "last_updated"], axis=1) df_sales.reset_index(inplace=True) return df_sales -#no test, same as fact_payment + +# no test, same as fact_payment + + def create_fact_purchase_orders(dict_of_df): - df_po = dict_of_df['purchase_order'] - df_po.index.name = 'purchase_record_id' - df_po['created_date'] = df_po['created_at'].astype('datetime64[ns]').dt.date - df_po['created_time'] = df_po['created_at'].astype('datetime64[ns]').dt.floor('s').dt.time - df_po['last_updated_date'] = df_po['last_updated'].astype('datetime64[ns]').dt.date - df_po['last_updated_time'] = df_po['last_updated'].astype('datetime64[ns]').dt.floor('s').dt.time - df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d") - df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d") - df_po = df_po.drop(labels=['created_at','last_updated'],axis=1) + df_po = dict_of_df["purchase_order"] + df_po.index.name = "purchase_record_id" + df_po["created_date"] = df_po["created_at"].astype("datetime64[ns]").dt.date + df_po["created_time"] = ( + df_po["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_po["last_updated_date"] = df_po["last_updated"].astype("datetime64[ns]").dt.date + df_po["last_updated_time"] = ( + df_po["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_po["agreed_delivery_date"] = pd.to_datetime( + df_po["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_po["agreed_payment_date"] = pd.to_datetime( + df_po["agreed_payment_date"], format="%Y-%m-%d" + ) + df_po = df_po.drop(labels=["created_at", "last_updated"], axis=1) df_po.reset_index(inplace=True) return df_po -#test passed + +# test passed + + def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = df_payment["created_at"].astype('datetime64[ns]').dt.date - df_payment["created_time"] = df_payment["created_at"].astype('datetime64[ns]').dt.floor('s').dt.time - df_payment["last_updated_date"] = df_payment["last_updated"].astype('datetime64[ns]').dt.date - df_payment["last_updated_time"] = df_payment["last_updated"].astype('datetime64[ns]').dt.floor('s').dt.time - df_payment['payment_date'] = pd.to_datetime(df_payment['payment_date'],format="%Y-%m-%d") - df_payment = df_payment.drop(labels=['created_at','last_updated'],axis=1) + df_payment["created_date"] = ( + df_payment["created_at"].astype("datetime64[ns]").dt.date + ) + df_payment["created_time"] = ( + df_payment["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_payment["last_updated_date"] = ( + df_payment["last_updated"].astype("datetime64[ns]").dt.date + ) + df_payment["last_updated_time"] = ( + df_payment["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_payment["payment_date"] = pd.to_datetime( + df_payment["payment_date"], format="%Y-%m-%d" + ) + df_payment = df_payment.drop(labels=["created_at", "last_updated"], axis=1) df_payment.reset_index(inplace=True) return df_payment -#test passed + +# test passed + + def create_dim_transaction(dict_of_df): - df_transaction = dict_of_df["transaction"].drop(labels=['created_at', 'last_updated'], axis=1) + df_transaction = dict_of_df["transaction"].drop( + labels=["created_at", "last_updated"], axis=1 + ) return df_transaction -#test passed + +# test passed + + def create_dim_location(dict_of_df): - df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}) + df_loc = ( + dict_of_df["address"] + .drop(labels=["created_at", "last_updated"], axis=1) + .rename(columns={"address_id": "location_id"}) + ) return df_loc def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) - df_cp = pd.merge(dict_of_df['counterparty'], - df_prefixed_address, - left_on="legal_address_id", - right_on="counterparty_legal_address_id", - how="outer") - df_cp.drop(columns=["legal_address_id","counterparty_legal_address_id"],inplace=True) + df_prefixed_address = dict_of_df["address"].add_prefix( + "counterparty_legal_", axis=1 + ) + df_cp = pd.merge( + dict_of_df["counterparty"], + df_prefixed_address, + left_on="legal_address_id", + right_on="counterparty_legal_address_id", + how="outer", + ) + df_cp.drop( + columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True + ) return df_cp -#test passed + +# test passed + + def create_dim_date(dict_of_df): - fact_dfs = [create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df)] + fact_dfs = [ + create_fact_payment(dict_of_df), + create_fact_purchase_orders(dict_of_df), + create_fact_sales_order(dict_of_df), + ] list_of_date_columns = [] for df in fact_dfs: - date_col_names = [col_name for col_name in list(df.columns) if '_date' in col_name] + date_col_names = [ + col_name for col_name in list(df.columns) if "_date" in col_name + ] for col in date_col_names: list_of_date_columns.append(df[col]) - sr_date = pd.array(pd.concat(list_of_date_columns),dtype='datetime64[ns]') - df_date = pd.DataFrame(data=sr_date,columns=['date_id']) + sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") + df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) df_date.drop_duplicates(inplace=True) - df_date['year'] = df_date['date_id'].dt.year - df_date['month'] = df_date['date_id'].dt.month - df_date['day'] = df_date['date_id'].dt.day - df_date['day_of_week'] = df_date['date_id'].dt.dayofweek - df_date['day_name'] = df_date['date_id'].dt.day_name() - df_date['month_name'] = df_date['date_id'].dt.month_name() - df_date['quarter'] = df_date['date_id'].dt.quarter + df_date["year"] = df_date["date_id"].dt.year + df_date["month"] = df_date["date_id"].dt.month + df_date["day"] = df_date["date_id"].dt.day + df_date["day_of_week"] = df_date["date_id"].dt.dayofweek + df_date["day_name"] = df_date["date_id"].dt.day_name() + df_date["month_name"] = df_date["date_id"].dt.month_name() + df_date["quarter"] = df_date["date_id"].dt.quarter return df_date -#tests passed -def scrape_currency_names(): - response = requests.get('https://www.xe.com/currency/').content - soup = BeautifulSoup(response,'html.parser') - currency = [item.text for item in soup.findAll('a', attrs={'class' : "sc-299dec64-6 fZPTSw"})] - sr = pd.Series(currency) - df_cur = sr.str.split(pat=" - ",expand=True).rename({0:'currency_code',1:'currency_name'},axis=1) - return df_cur - -#tests passed -def create_dim_currency(dict_of_df,names=scrape_currency_names()): - df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1) - dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner') - return dim_cur -#tests passed -def create_dim_payment_type(dict_of_df): - df_payment_type = dict_of_df["payment_type"] - dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] - return dim_payment_type +# tests passed -#tests passed -def create_dim_design(dict_of_df): - df_design = dict_of_df["design"] - dim_design = df_design.loc[:, ["design_id", "design_name", "file_name", "file_location"]] - return dim_design -#tests passed -def create_dim_staff(dict_of_df): - staff_department = pd.merge(dict_of_df["staff"], dict_of_df["department"], on='department_id', how="left") - dim_staff = staff_department.loc[:, ['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address']] - return dim_staff +def scrape_currency_names(): + response = requests.get("https://www.xe.com/currency/").content + soup = BeautifulSoup(response, "html.parser") + currency = [ + item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) + ] + sr = pd.Series(currency) + df_cur = sr.str.split(pat=" - ", expand=True).rename( + {0: "currency_code", 1: "currency_name"}, axis=1 + ) + return df_cur +# tests passed +def create_dim_currency(dict_of_df, names=scrape_currency_names()): + df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) + dim_cur = pd.merge( + df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" + ) + return dim_cur +# tests passed +def create_dim_payment_type(dict_of_df): + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + return dim_payment_type +# tests passed +def create_dim_design(dict_of_df): + df_design = dict_of_df["design"] + dim_design = df_design.loc[ + :, ["design_id", "design_name", "file_name", "file_location"] + ] + return dim_design +# tests passed +def create_dim_staff(dict_of_df): + staff_department = pd.merge( + dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" + ) + dim_staff = staff_department.loc[ + :, + [ + "staff_id", + "first_name", + "last_name", + "department_name", + "location", + "email_address", + ], + ] + return dim_staff diff --git a/src/transform_lambda.py b/src/transform_lambda.py index ccf90e5..93b2284 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -117,7 +117,8 @@ def process_to_parquet_and_upload_to_s3( parquet_file = df.to_parquet( f"{table_name}.parquet", engine="pyarrow" ) # or fastparquet - client.upload_file(f"{table_name}.parquet", bucket, f"{table_name}.parquet") #changed parquet_file variable to the file name + # changed parquet_file variable to the file name + client.upload_file(f"{table_name}.parquet", bucket, f"{table_name}.parquet") status["uploaded"].append(table_name) for table_name, df in mutable_df_dict.items(): @@ -203,7 +204,7 @@ def list_existing_s3_files(bucket_name, client=boto3.client("s3")): existing_files = [obj["Key"] for obj in response["Contents"]] else: logger.error("The bucket is empty") - return [] #changed from None to [] so it is an iterable + return [] # changed from None to [] so it is an iterable except ClientError as e: logger.error(f"Error listing S3 objects: {e}") diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index adbb5ed..c9ff43f 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -3,42 +3,88 @@ import pandas as pd from unittest.mock import patch from datetime import datetime as dt + class TestCreateDimDesign: def test_dim_design_returns_dataframe(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) assert isinstance(result, pd.DataFrame) def test_dim_design_returns_correct_columns_and_values(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) - d2 = {"design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"]} + d2 = { + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=d2) expected_result = expected_df.copy() assert result.equals(expected_result) + class TestCreateDimStaff: def test_dim_staff_returns_dataframe(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - assert isinstance(result, pd.DataFrame) + assert isinstance(result, pd.DataFrame) def test_dim_staff_returns_correct_columns_and_values(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - expected_d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"]} + expected_d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) expected_result = expected_df.copy() - assert result.equals(expected_result) + assert result.equals(expected_result) + class TestCreatePaymentType: def test_create_dim_payment_type_returns_correct_columns_and_values(self): @@ -46,100 +92,200 @@ class TestCreatePaymentType: test_df = {"payment_type": pd.DataFrame(data=d)} result = create_dim_payment_type(test_df) expected_columns = ["payment_type_id", "payment_type_name"] - expected_d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} + expected_d = { + "payment_type_id": ["Hello", "Bye"], + "payment_type_name": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns assert result.equals(expected_df) + class TestCreateDimCounterparty: - def test_create_dim_counterparty_type_returns_correct_columns_and_object(self): - data_l = pd.DataFrame(data={"counterparty_id": ["Hello", "Bye"], - "counterparty_legal_name": ["Hello", "Bye"], - "commercial_contact": ["Hello", "Bye"], - "legal_address_id": ["bond street", "regent street"]}) - data_a = pd.DataFrame(data={"address_id":["bond street", "regent street"], - "postcode":[98365,93753]}) - test_df = {"address": data_a,"counterparty":data_l} + data_l = pd.DataFrame( + data={ + "counterparty_id": ["Hello", "Bye"], + "counterparty_legal_name": ["Hello", "Bye"], + "commercial_contact": ["Hello", "Bye"], + "legal_address_id": ["bond street", "regent street"], + } + ) + data_a = pd.DataFrame( + data={ + "address_id": ["bond street", "regent street"], + "postcode": [98365, 93753], + } + ) + test_df = {"address": data_a, "counterparty": data_l} result = create_dim_counterparty(test_df) - expected_columns = ["counterparty_id", "counterparty_legal_name", - "commercial_contact", "counterparty_legal_postcode"] + expected_columns = [ + "counterparty_id", + "counterparty_legal_name", + "commercial_contact", + "counterparty_legal_postcode", + ] print(data_l) print(data_a) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns + class TestCreateDimCurrency: - def test_dim_currency_returns_columns_and_values(self): - nones = [None,None,None] - d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"],"created_at":nones,"last_updated":nones} + nones = [None, None, None] + d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "created_at": nones, + "last_updated": nones, + } test_df = {"currency": pd.DataFrame(data=d)} - scraper_output = pd.DataFrame({"currency_code":["RUS","USD","PHP","GBP","EUR"],"currency_name":["Rubble","US Dollar","Peso","Pound","Euro"]}) - result = create_dim_currency(test_df,names=scraper_output).sort_values(by="currency_code",axis=0) - expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} - expected_df = pd.DataFrame(data=expected_d).sort_values(by="currency_code",axis=0) - assert isinstance(result, pd.DataFrame) - assert result.equals(expected_df) + scraper_output = pd.DataFrame( + { + "currency_code": ["RUS", "USD", "PHP", "GBP", "EUR"], + "currency_name": ["Rubble", "US Dollar", "Peso", "Pound", "Euro"], + } + ) + result = create_dim_currency(test_df, names=scraper_output).sort_values( + by="currency_code", axis=0 + ) + expected_d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "currency_name": ["US Dollar", "Euro", "Pound"], + } + expected_df = pd.DataFrame(data=expected_d).sort_values( + by="currency_code", axis=0 + ) + assert isinstance(result, pd.DataFrame) + assert result.equals(expected_df) def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self): result = scrape_currency_names() - assert isinstance(result,pd.DataFrame) - assert list(result.columns) == ['currency_code', 'currency_name'] + assert isinstance(result, pd.DataFrame) + assert list(result.columns) == ["currency_code", "currency_name"] -class TestCreateDimDate: +class TestCreateDimDate: def test_returns_required_columns(self): - df_one = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 5, 13),'not_dat':None},index=[0]) - df_two = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 9, 13)},index=[0]) - df_three = pd.DataFrame(data={'updated_date':dt(2022, 5, 17),'created_date':dt(2023, 5, 13)},index=[0]) - expected_df = pd.DataFrame(data= - [[dt(2020,5,17),2020,5,17,6,'Sunday','May',2], - [dt(2021,5,13),2021,5,13,3,'Thursday','May',2], - [dt(2021,9,13),2021,9,13,0,'Monday','September',3], - [dt(2022,5,17),2022,5,17,1,'Tuesday','May',2], - [dt(2023,5,13),2023,5,13,5,'Saturday','May',2]], - columns=['date_id','year','month','day','day_of_week','day_name','month_name','quarter']) + df_one = pd.DataFrame( + data={ + "updated_date": dt(2020, 5, 17), + "created_date": dt(2021, 5, 13), + "not_dat": None, + }, + index=[0], + ) + df_two = pd.DataFrame( + data={"updated_date": dt(2020, 5, 17), "created_date": dt(2021, 9, 13)}, + index=[0], + ) + df_three = pd.DataFrame( + data={"updated_date": dt(2022, 5, 17), "created_date": dt(2023, 5, 13)}, + index=[0], + ) + expected_df = pd.DataFrame( + data=[ + [dt(2020, 5, 17), 2020, 5, 17, 6, "Sunday", "May", 2], + [dt(2021, 5, 13), 2021, 5, 13, 3, "Thursday", "May", 2], + [dt(2021, 9, 13), 2021, 9, 13, 0, "Monday", "September", 3], + [dt(2022, 5, 17), 2022, 5, 17, 1, "Tuesday", "May", 2], + [dt(2023, 5, 13), 2023, 5, 13, 5, "Saturday", "May", 2], + ], + columns=[ + "date_id", + "year", + "month", + "day", + "day_of_week", + "day_name", + "month_name", + "quarter", + ], + ) with patch("src.dataframes.create_fact_payment") as mock_fp: with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo: with patch("src.dataframes.create_fact_sales_order") as mock_fso: mock_fp.return_value = df_one mock_fpo.return_value = df_two mock_fso.return_value = df_three - result = create_dim_date({'dum':0}) - result.reset_index(inplace=True,drop=True) + result = create_dim_date({"dum": 0}) + result.reset_index(inplace=True, drop=True) assert result.eq(expected_df, axis="columns").all(axis=None) - -class TestCreateDimLocation: + +class TestCreateDimLocation: def test_returns_correct_columns_lo(self): - dict_df = {'address':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], - columns=['created_at','last_updated','address_id','postal_code'])} + dict_df = { + "address": pd.DataFrame( + data=[["some_time", "some_other_time", 1, "SE18 9QO"]], + columns=["created_at", "last_updated", "address_id", "postal_code"], + ) + } result = create_dim_location(dict_df) - assert list(result.columns) == ['location_id','postal_code'] - + assert list(result.columns) == ["location_id", "postal_code"] + + class TestCreateDimTransaction: - def test_returns_correct_columns_tr(self): - dict_df = {'transaction':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], - columns=['created_at','last_updated','transaction_id','some_other_id'])} + def test_returns_correct_columns_tr(self): + dict_df = { + "transaction": pd.DataFrame( + data=[["some_time", "some_other_time", 1, "SE18 9QO"]], + columns=[ + "created_at", + "last_updated", + "transaction_id", + "some_other_id", + ], + ) + } result = create_dim_transaction(dict_df) - assert list(result.columns) == ['transaction_id','some_other_id'] + assert list(result.columns) == ["transaction_id", "some_other_id"] + class TestCreateFactPayment: def test_returns_correct_columns_payment(self): - dict_df = {'payment':pd.DataFrame(data=[[dt.strptime('2022-11-03 14:20:49.962846','%Y-%m-%d %H:%M:%S.%f'), - dt.strptime('2022-12-14 16:20:49.962194','%Y-%m-%d %H:%M:%S.%f'),1,'SE18 9QO','2020-07-16']], - columns=['created_at','last_updated','payment_id','some_other_id','payment_date'])} - expected_cols = ['payment_record_id','created_date','created_time','last_updated_date', - 'last_updated_time','payment_date','payment_id','some_other_id'] + dict_df = { + "payment": pd.DataFrame( + data=[ + [ + dt.strptime( + "2022-11-03 14:20:49.962846", "%Y-%m-%d %H:%M:%S.%f" + ), + dt.strptime( + "2022-12-14 16:20:49.962194", "%Y-%m-%d %H:%M:%S.%f" + ), + 1, + "SE18 9QO", + "2020-07-16", + ] + ], + columns=[ + "created_at", + "last_updated", + "payment_id", + "some_other_id", + "payment_date", + ], + ) + } + expected_cols = [ + "payment_record_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "payment_date", + "payment_id", + "some_other_id", + ] result = create_fact_payment(dict_df) - assert isinstance(result,pd.DataFrame) + assert isinstance(result, pd.DataFrame) for col in list(result.columns): assert col in expected_cols for col in expected_cols: - if '_date' or '_time' in col: - assert result[col].dtype == 'O' - - \ No newline at end of file + if "_date" or "_time" in col: + assert result[col].dtype == "O" -- cgit v1.2.3 From f8988db9372802053db60e311960f5da4defba02 Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Tue, 27 Aug 2024 11:44:00 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in a05a371 according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/98 --- src/dataframes.py | 50 ++++++++++++++++++++++++++++++++++++++++++++++++ tests/test_dataframes.py | 13 +++++++++++++ 2 files changed, 63 insertions(+) diff --git a/src/dataframes.py b/src/dataframes.py index f122368..36361d2 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -20,6 +20,7 @@ import requests def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" +<<<<<<< HEAD df_sales["created_date"] = df_sales["created_at"].astype("datetime64[ns]").dt.date df_sales["created_time"] = ( df_sales["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time @@ -29,6 +30,15 @@ def create_fact_sales_order(dict_of_df): ) df_sales["last_updated_time"] = ( df_sales["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time +======= + df_sales["created_date"] = pd.to_datetime(df_sales["created_at"], format="%Y-%m-%d") + df_sales["created_time"] = pd.to_datetime(df_sales["created_at"], format="%H-%M-%S") + df_sales["last_updated_date"] = pd.to_datetime( + df_sales["last_updated"], format="%Y-%m-%d" + ) + df_sales["last_updated_time"] = pd.to_datetime( + df_sales["last_updated"], format="%H-%M-%S" +>>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) ) df_sales["agreed_delivery_date"] = pd.to_datetime( df_sales["agreed_delivery_date"], format="%Y-%m-%d" @@ -36,7 +46,11 @@ def create_fact_sales_order(dict_of_df): df_sales["agreed_payment_date"] = pd.to_datetime( df_sales["agreed_payment_date"], format="%Y-%m-%d" ) +<<<<<<< HEAD df_sales = df_sales.drop(labels=["created_at", "last_updated"], axis=1) +======= + df_sales.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) +>>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) df_sales.reset_index(inplace=True) return df_sales @@ -47,6 +61,7 @@ def create_fact_sales_order(dict_of_df): def create_fact_purchase_orders(dict_of_df): df_po = dict_of_df["purchase_order"] df_po.index.name = "purchase_record_id" +<<<<<<< HEAD df_po["created_date"] = df_po["created_at"].astype("datetime64[ns]").dt.date df_po["created_time"] = ( df_po["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time @@ -54,6 +69,15 @@ def create_fact_purchase_orders(dict_of_df): df_po["last_updated_date"] = df_po["last_updated"].astype("datetime64[ns]").dt.date df_po["last_updated_time"] = ( df_po["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time +======= + df_po["created_date"] = pd.to_datetime(df_po["created_at"], format="%Y-%m-%d") + df_po["created_time"] = pd.to_datetime(df_po["created_at"], format="%H-%M-%S") + df_po["last_updated_date"] = pd.to_datetime( + df_po["last_updated"], format="%Y-%m-%d" + ) + df_po["last_updated_time"] = pd.to_datetime( + df_po["last_updated"], format="%H-%M-%S" +>>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) ) df_po["agreed_delivery_date"] = pd.to_datetime( df_po["agreed_delivery_date"], format="%Y-%m-%d" @@ -61,7 +85,11 @@ def create_fact_purchase_orders(dict_of_df): df_po["agreed_payment_date"] = pd.to_datetime( df_po["agreed_payment_date"], format="%Y-%m-%d" ) +<<<<<<< HEAD df_po = df_po.drop(labels=["created_at", "last_updated"], axis=1) +======= + df_po.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) +>>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) df_po.reset_index(inplace=True) return df_po @@ -72,6 +100,7 @@ def create_fact_purchase_orders(dict_of_df): def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" +<<<<<<< HEAD df_payment["created_date"] = ( df_payment["created_at"].astype("datetime64[ns]").dt.date ) @@ -83,11 +112,28 @@ def create_fact_payment(dict_of_df): ) df_payment["last_updated_time"] = ( df_payment["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time +======= + df_payment["created_date"] = pd.to_datetime( + df_payment["created_at"], format="%Y-%m-%d" + ) + df_payment["created_time"] = pd.to_datetime( + df_payment["created_at"], format="%H-%M-%S" + ) + df_payment["last_updated_date"] = pd.to_datetime( + df_payment["last_updated"], format="%Y-%m-%d" + ) + df_payment["last_updated_time"] = pd.to_datetime( + df_payment["last_updated"], format="%H-%M-%S" +>>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) ) df_payment["payment_date"] = pd.to_datetime( df_payment["payment_date"], format="%Y-%m-%d" ) +<<<<<<< HEAD df_payment = df_payment.drop(labels=["created_at", "last_updated"], axis=1) +======= + df_payment.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) +>>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) df_payment.reset_index(inplace=True) return df_payment @@ -143,7 +189,11 @@ def create_dim_date(dict_of_df): list_of_date_columns = [] for df in fact_dfs: date_col_names = [ +<<<<<<< HEAD col_name for col_name in list(df.columns) if "_date" in col_name +======= + col_name for col_name in list(df.columns) if "date" in col_name +>>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) ] for col in date_col_names: list_of_date_columns.append(df[col]) diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index c9ff43f..cc133fe 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -252,6 +252,7 @@ class TestCreateFactPayment: "payment": pd.DataFrame( data=[ [ +<<<<<<< HEAD dt.strptime( "2022-11-03 14:20:49.962846", "%Y-%m-%d %H:%M:%S.%f" ), @@ -261,6 +262,13 @@ class TestCreateFactPayment: 1, "SE18 9QO", "2020-07-16", +======= + dt(2020, 5, 17, 6, 15, 20), + dt(2020, 5, 20, 8, 19, 30), + 1, + "SE18 9QO", + "2020-7-16", +>>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) ] ], columns=[ @@ -287,5 +295,10 @@ class TestCreateFactPayment: for col in list(result.columns): assert col in expected_cols for col in expected_cols: +<<<<<<< HEAD if "_date" or "_time" in col: assert result[col].dtype == "O" +======= + if "date" in col: + assert result[col].dtype == "datetime64[ns]" +>>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) -- cgit v1.2.3 From 102575af5e1ac3f12b3f7e1c459a3a06bc5ec80a Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 17:24:47 +0100 Subject: amend to inner join --- src/dataframes.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 36361d2..4b32b36 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -161,7 +161,7 @@ def create_dim_location(dict_of_df): def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df["address"].add_prefix( + df_prefixed_address = dict_of_df["address"].drop(labels=["created_at", "last_updated"], axis=1).add_prefix( "counterparty_legal_", axis=1 ) df_cp = pd.merge( @@ -169,10 +169,10 @@ def create_dim_counterparty(dict_of_df): df_prefixed_address, left_on="legal_address_id", right_on="counterparty_legal_address_id", - how="outer", + how="inner", ) df_cp.drop( - columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True + columns=["legal_address_id", "counterparty_legal_address_id", ], inplace=True ) return df_cp -- cgit v1.2.3 From 0915d4fe4e151d6b593467129b51a1322398fc04 Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 17:27:21 +0100 Subject: add json.loads --- src/load_lambda.py | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/src/load_lambda.py b/src/load_lambda.py index 9e15af3..7339ab9 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -64,7 +64,7 @@ def retrieve_secrets(client=None, secret_name=None): logger.error(f"Secret {secret_name} does not contain a SecretString") raise ValueError(f"Secret {secret_name} does not contain a SecretString") - return json.loads(get_secret_value_response["SecretString"]) + return get_secret_value_response["SecretString"] # connect to database, slightly different way of doing it, to allow manipulation through pandas @@ -72,10 +72,10 @@ def retrieve_secrets(client=None, secret_name=None): def connect_to_db_and_return_engine(sm_secret=None): if sm_secret is None: - sm_secret = retrieve_secrets() + sm_secret = json.loads(retrieve_secrets()) try: - secrets = json.loads(sm_secret) + secrets = sm_secret host = secrets["host"] port = secrets["port"] user = secrets["user"] @@ -171,13 +171,14 @@ def upload_dfs_to_database(): ] for file_name, df in dict_of_dfs.items(): + print(df) if file_name in immutable_df_dict: table_name = file_name.split(".")[0] + print(table_name, "<<<<<") try: df.to_sql( table_name, con=db_engine, - schema="project_team_2", if_exists="append", index=False, ) -- cgit v1.2.3 From 08c971f0e56d0896aa09200c26b5cfa53ff29ca1 Mon Sep 17 00:00:00 2001 From: Ellie Date: Tue, 27 Aug 2024 17:27:40 +0100 Subject: add json.loads to retrieve secrets --- tests/test_load_lambda.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 829b908..02cf2c0 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -79,14 +79,14 @@ class TestRetrieveSecrets: mock_sm_client.create_secret(Name=secret_name, SecretString=json.dumps(secret)) - result = retrieve_secrets(mock_sm_client, secret_name) + result = json.loads(retrieve_secrets(mock_sm_client, secret_name)) assert isinstance(result, dict) def test_retrieve_secrets_returns_correct_keys_and_values(self, mock_sm_client): secret_name = "test_secret" - result = retrieve_secrets(mock_sm_client, secret_name) + result = json.loads(retrieve_secrets(mock_sm_client, secret_name)) assert result["user"] == "test_user_id" assert result["password"] == "test_password" -- cgit v1.2.3 From 95935534931b5ff6e617ba74c86cb7a6718128e4 Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Wed, 28 Aug 2024 08:24:21 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 08c971f according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/102 --- src/dataframes.py | 182 ++++++++++++++++++++++++---------------------- tests/test_dataframes.py | 43 ++++++----- tests/test_load_lambda.py | 2 - 3 files changed, 123 insertions(+), 104 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index 4b32b36..43facd6 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -20,8 +20,11 @@ import requests def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" -<<<<<<< HEAD - df_sales["created_date"] = df_sales["created_at"].astype("datetime64[ns]").dt.date + + +<< << << < HEAD + df_sales["created_date"] = df_sales["created_at"].astype( + "datetime64[ns]").dt.date df_sales["created_time"] = ( df_sales["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time ) @@ -30,27 +33,29 @@ def create_fact_sales_order(dict_of_df): ) df_sales["last_updated_time"] = ( df_sales["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time -======= - df_sales["created_date"] = pd.to_datetime(df_sales["created_at"], format="%Y-%m-%d") - df_sales["created_time"] = pd.to_datetime(df_sales["created_at"], format="%H-%M-%S") - df_sales["last_updated_date"] = pd.to_datetime( +== == == = + df_sales["created_date"]=pd.to_datetime( + df_sales["created_at"], format="%Y-%m-%d") + df_sales["created_time"]=pd.to_datetime( + df_sales["created_at"], format="%H-%M-%S") + df_sales["last_updated_date"]=pd.to_datetime( df_sales["last_updated"], format="%Y-%m-%d" ) - df_sales["last_updated_time"] = pd.to_datetime( + df_sales["last_updated_time"]=pd.to_datetime( df_sales["last_updated"], format="%H-%M-%S" ->>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) +>> >>>> > 5db3f61(style: format code with Autopep8, Black and Ruff Formatter) ) - df_sales["agreed_delivery_date"] = pd.to_datetime( + df_sales["agreed_delivery_date"]=pd.to_datetime( df_sales["agreed_delivery_date"], format="%Y-%m-%d" ) - df_sales["agreed_payment_date"] = pd.to_datetime( + df_sales["agreed_payment_date"]=pd.to_datetime( df_sales["agreed_payment_date"], format="%Y-%m-%d" ) -<<<<<<< HEAD - df_sales = df_sales.drop(labels=["created_at", "last_updated"], axis=1) -======= +<< << << < HEAD + df_sales=df_sales.drop(labels=["created_at", "last_updated"], axis=1) +== == == = df_sales.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) ->>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) +>> >>>> > 5db3f61(style: format code with Autopep8, Black and Ruff Formatter) df_sales.reset_index(inplace=True) return df_sales @@ -59,37 +64,40 @@ def create_fact_sales_order(dict_of_df): def create_fact_purchase_orders(dict_of_df): - df_po = dict_of_df["purchase_order"] - df_po.index.name = "purchase_record_id" -<<<<<<< HEAD - df_po["created_date"] = df_po["created_at"].astype("datetime64[ns]").dt.date - df_po["created_time"] = ( + df_po=dict_of_df["purchase_order"] + df_po.index.name="purchase_record_id" +<< << << < HEAD + df_po["created_date"]=df_po["created_at"].astype("datetime64[ns]").dt.date + df_po["created_time"]=( df_po["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time ) - df_po["last_updated_date"] = df_po["last_updated"].astype("datetime64[ns]").dt.date - df_po["last_updated_time"] = ( + df_po["last_updated_date"]=df_po["last_updated"].astype( + "datetime64[ns]").dt.date + df_po["last_updated_time"]=( df_po["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time -======= - df_po["created_date"] = pd.to_datetime(df_po["created_at"], format="%Y-%m-%d") - df_po["created_time"] = pd.to_datetime(df_po["created_at"], format="%H-%M-%S") - df_po["last_updated_date"] = pd.to_datetime( +== == == = + df_po["created_date"]=pd.to_datetime( + df_po["created_at"], format="%Y-%m-%d") + df_po["created_time"]=pd.to_datetime( + df_po["created_at"], format="%H-%M-%S") + df_po["last_updated_date"]=pd.to_datetime( df_po["last_updated"], format="%Y-%m-%d" ) - df_po["last_updated_time"] = pd.to_datetime( + df_po["last_updated_time"]=pd.to_datetime( df_po["last_updated"], format="%H-%M-%S" ->>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) +>> >>>> > 5db3f61(style: format code with Autopep8, Black and Ruff Formatter) ) - df_po["agreed_delivery_date"] = pd.to_datetime( + df_po["agreed_delivery_date"]=pd.to_datetime( df_po["agreed_delivery_date"], format="%Y-%m-%d" ) - df_po["agreed_payment_date"] = pd.to_datetime( + df_po["agreed_payment_date"]=pd.to_datetime( df_po["agreed_payment_date"], format="%Y-%m-%d" ) -<<<<<<< HEAD - df_po = df_po.drop(labels=["created_at", "last_updated"], axis=1) -======= +<< << << < HEAD + df_po=df_po.drop(labels=["created_at", "last_updated"], axis=1) +== == == = df_po.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) ->>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) +>> >>>> > 5db3f61(style: format code with Autopep8, Black and Ruff Formatter) df_po.reset_index(inplace=True) return df_po @@ -98,42 +106,44 @@ def create_fact_purchase_orders(dict_of_df): def create_fact_payment(dict_of_df): - df_payment = dict_of_df["payment"] - df_payment.index.name = "payment_record_id" -<<<<<<< HEAD - df_payment["created_date"] = ( + df_payment=dict_of_df["payment"] + df_payment.index.name="payment_record_id" +<< << << < HEAD + df_payment["created_date"]=( df_payment["created_at"].astype("datetime64[ns]").dt.date ) - df_payment["created_time"] = ( + df_payment["created_time"]=( df_payment["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time ) - df_payment["last_updated_date"] = ( + df_payment["last_updated_date"]=( df_payment["last_updated"].astype("datetime64[ns]").dt.date ) - df_payment["last_updated_time"] = ( - df_payment["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time -======= - df_payment["created_date"] = pd.to_datetime( + df_payment["last_updated_time"]=( + df_payment["last_updated"].astype( + "datetime64[ns]").dt.floor("s").dt.time +== == == = + df_payment["created_date"]=pd.to_datetime( df_payment["created_at"], format="%Y-%m-%d" ) - df_payment["created_time"] = pd.to_datetime( + df_payment["created_time"]=pd.to_datetime( df_payment["created_at"], format="%H-%M-%S" ) - df_payment["last_updated_date"] = pd.to_datetime( + df_payment["last_updated_date"]=pd.to_datetime( df_payment["last_updated"], format="%Y-%m-%d" ) - df_payment["last_updated_time"] = pd.to_datetime( + df_payment["last_updated_time"]=pd.to_datetime( df_payment["last_updated"], format="%H-%M-%S" ->>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) +>> >>>> > 5db3f61(style: format code with Autopep8, Black and Ruff Formatter) ) - df_payment["payment_date"] = pd.to_datetime( + df_payment["payment_date"]=pd.to_datetime( df_payment["payment_date"], format="%Y-%m-%d" ) -<<<<<<< HEAD - df_payment = df_payment.drop(labels=["created_at", "last_updated"], axis=1) -======= - df_payment.drop(labels=["created_at", "last_updated"], axis=1, inplace=True) ->>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) +<< << << < HEAD + df_payment=df_payment.drop(labels=["created_at", "last_updated"], axis=1) +== == == = + df_payment.drop( + labels=["created_at", "last_updated"], axis=1, inplace=True) +>> >>>> > 5db3f61(style: format code with Autopep8, Black and Ruff Formatter) df_payment.reset_index(inplace=True) return df_payment @@ -142,7 +152,7 @@ def create_fact_payment(dict_of_df): def create_dim_transaction(dict_of_df): - df_transaction = dict_of_df["transaction"].drop( + df_transaction=dict_of_df["transaction"].drop( labels=["created_at", "last_updated"], axis=1 ) return df_transaction @@ -152,7 +162,7 @@ def create_dim_transaction(dict_of_df): def create_dim_location(dict_of_df): - df_loc = ( + df_loc=( dict_of_df["address"] .drop(labels=["created_at", "last_updated"], axis=1) .rename(columns={"address_id": "location_id"}) @@ -161,10 +171,10 @@ def create_dim_location(dict_of_df): def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df["address"].drop(labels=["created_at", "last_updated"], axis=1).add_prefix( + df_prefixed_address=dict_of_df["address"].drop(labels=["created_at", "last_updated"], axis=1).add_prefix( "counterparty_legal_", axis=1 ) - df_cp = pd.merge( + df_cp=pd.merge( dict_of_df["counterparty"], df_prefixed_address, left_on="legal_address_id", @@ -181,32 +191,32 @@ def create_dim_counterparty(dict_of_df): def create_dim_date(dict_of_df): - fact_dfs = [ + fact_dfs=[ create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df), ] - list_of_date_columns = [] + list_of_date_columns=[] for df in fact_dfs: - date_col_names = [ -<<<<<<< HEAD + date_col_names=[ +<< << << < HEAD col_name for col_name in list(df.columns) if "_date" in col_name -======= +== == == = col_name for col_name in list(df.columns) if "date" in col_name ->>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) +>> >>>> > 5db3f61(style: format code with Autopep8, Black and Ruff Formatter) ] for col in date_col_names: list_of_date_columns.append(df[col]) - sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") - df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) + sr_date=pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") + df_date=pd.DataFrame(data=sr_date, columns=["date_id"]) df_date.drop_duplicates(inplace=True) - df_date["year"] = df_date["date_id"].dt.year - df_date["month"] = df_date["date_id"].dt.month - df_date["day"] = df_date["date_id"].dt.day - df_date["day_of_week"] = df_date["date_id"].dt.dayofweek - df_date["day_name"] = df_date["date_id"].dt.day_name() - df_date["month_name"] = df_date["date_id"].dt.month_name() - df_date["quarter"] = df_date["date_id"].dt.quarter + df_date["year"]=df_date["date_id"].dt.year + df_date["month"]=df_date["date_id"].dt.month + df_date["day"]=df_date["date_id"].dt.day + df_date["day_of_week"]=df_date["date_id"].dt.dayofweek + df_date["day_name"]=df_date["date_id"].dt.day_name() + df_date["month_name"]=df_date["date_id"].dt.month_name() + df_date["quarter"]=df_date["date_id"].dt.quarter return df_date @@ -214,13 +224,13 @@ def create_dim_date(dict_of_df): def scrape_currency_names(): - response = requests.get("https://www.xe.com/currency/").content - soup = BeautifulSoup(response, "html.parser") - currency = [ + response=requests.get("https://www.xe.com/currency/").content + soup=BeautifulSoup(response, "html.parser") + currency=[ item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) ] - sr = pd.Series(currency) - df_cur = sr.str.split(pat=" - ", expand=True).rename( + sr=pd.Series(currency) + df_cur=sr.str.split(pat=" - ", expand=True).rename( {0: "currency_code", 1: "currency_name"}, axis=1 ) return df_cur @@ -230,8 +240,9 @@ def scrape_currency_names(): def create_dim_currency(dict_of_df, names=scrape_currency_names()): - df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) - dim_cur = pd.merge( + df_cur=dict_of_df["currency"].drop( + labels=["created_at", "last_updated"], axis=1) + dim_cur=pd.merge( df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" ) return dim_cur @@ -241,8 +252,9 @@ def create_dim_currency(dict_of_df, names=scrape_currency_names()): def create_dim_payment_type(dict_of_df): - df_payment_type = dict_of_df["payment_type"] - dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + df_payment_type=dict_of_df["payment_type"] + dim_payment_type=df_payment_type.loc[:, [ + "payment_type_id", "payment_type_name"]] return dim_payment_type @@ -250,8 +262,8 @@ def create_dim_payment_type(dict_of_df): def create_dim_design(dict_of_df): - df_design = dict_of_df["design"] - dim_design = df_design.loc[ + df_design=dict_of_df["design"] + dim_design=df_design.loc[ :, ["design_id", "design_name", "file_name", "file_location"] ] return dim_design @@ -261,10 +273,10 @@ def create_dim_design(dict_of_df): def create_dim_staff(dict_of_df): - staff_department = pd.merge( + staff_department=pd.merge( dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" ) - dim_staff = staff_department.loc[ + dim_staff=staff_department.loc[ :, [ "staff_id", diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index cc133fe..785a3fd 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -54,7 +54,8 @@ class TestCreateDimStaff: "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"], } - test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} + test_df = {"staff": pd.DataFrame( + data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) assert isinstance(result, pd.DataFrame) @@ -71,7 +72,8 @@ class TestCreateDimStaff: "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"], } - test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} + test_df = {"staff": pd.DataFrame( + data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) expected_d = { "staff_id": ["Hello", "Bye"], @@ -88,7 +90,8 @@ class TestCreateDimStaff: class TestCreatePaymentType: def test_create_dim_payment_type_returns_correct_columns_and_values(self): - d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} + d = {"payment_type_id": ["Hello", "Bye"], + "payment_type_name": ["Hello", "Bye"]} test_df = {"payment_type": pd.DataFrame(data=d)} result = create_dim_payment_type(test_df) expected_columns = ["payment_type_id", "payment_type_name"] @@ -180,11 +183,13 @@ class TestCreateDimDate: index=[0], ) df_two = pd.DataFrame( - data={"updated_date": dt(2020, 5, 17), "created_date": dt(2021, 9, 13)}, + data={"updated_date": dt(2020, 5, 17), + "created_date": dt(2021, 9, 13)}, index=[0], ) df_three = pd.DataFrame( - data={"updated_date": dt(2022, 5, 17), "created_date": dt(2023, 5, 13)}, + data={"updated_date": dt(2022, 5, 17), + "created_date": dt(2023, 5, 13)}, index=[0], ) expected_df = pd.DataFrame( @@ -214,7 +219,8 @@ class TestCreateDimDate: mock_fso.return_value = df_three result = create_dim_date({"dum": 0}) result.reset_index(inplace=True, drop=True) - assert result.eq(expected_df, axis="columns").all(axis=None) + assert result.eq( + expected_df, axis="columns").all(axis=None) class TestCreateDimLocation: @@ -222,7 +228,8 @@ class TestCreateDimLocation: dict_df = { "address": pd.DataFrame( data=[["some_time", "some_other_time", 1, "SE18 9QO"]], - columns=["created_at", "last_updated", "address_id", "postal_code"], + columns=["created_at", "last_updated", + "address_id", "postal_code"], ) } result = create_dim_location(dict_df) @@ -252,7 +259,7 @@ class TestCreateFactPayment: "payment": pd.DataFrame( data=[ [ -<<<<<<< HEAD + << << << < HEAD dt.strptime( "2022-11-03 14:20:49.962846", "%Y-%m-%d %H:%M:%S.%f" ), @@ -262,13 +269,13 @@ class TestCreateFactPayment: 1, "SE18 9QO", "2020-07-16", -======= + == == === dt(2020, 5, 17, 6, 15, 20), dt(2020, 5, 20, 8, 19, 30), 1, "SE18 9QO", "2020-7-16", ->>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) + >>>>>> > 5db3f61(style: format code with Autopep8, Black and Ruff Formatter) ] ], columns=[ @@ -295,10 +302,12 @@ class TestCreateFactPayment: for col in list(result.columns): assert col in expected_cols for col in expected_cols: -<<<<<<< HEAD - if "_date" or "_time" in col: - assert result[col].dtype == "O" -======= - if "date" in col: - assert result[col].dtype == "datetime64[ns]" ->>>>>>> 5db3f61 (style: format code with Autopep8, Black and Ruff Formatter) + + +<< << << < HEAD +if "_date" or "_time" in col: + assert result[col].dtype == "O" +== == == = +if "date" in col: + assert result[col].dtype == "datetime64[ns]" +>>>>>> > 5db3f61(style: format code with Autopep8, Black and Ruff Formatter) diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py index 02cf2c0..65106f7 100644 --- a/tests/test_load_lambda.py +++ b/tests/test_load_lambda.py @@ -62,8 +62,6 @@ class TestLambdaHandler: assert result == {"error"} - - class TestRetrieveSecrets: def test_retrieve_secrets_returns_dictionary(self, mock_sm_client): secret = { -- cgit v1.2.3 From 4bd3f408a185d16f9580294755621156ad850ab4 Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Wed, 28 Aug 2024 08:36:33 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in d0b0fa9 according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/102 --- src/dataframes.py | 118 +++++++++++++++++++++++------------------------ tests/test_dataframes.py | 2 - 2 files changed, 59 insertions(+), 61 deletions(-) diff --git a/src/dataframes.py b/src/dataframes.py index ab32fff..2a46bd6 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -20,9 +20,8 @@ import requests def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" - - df_sales["created_date"] = df_sales["created_at"].astype( - "datetime64[ns]").dt.date + + df_sales["created_date"] = df_sales["created_at"].astype("datetime64[ns]").dt.date df_sales["created_time"] = ( df_sales["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time ) @@ -32,13 +31,13 @@ def create_fact_sales_order(dict_of_df): df_sales["last_updated_time"] = ( df_sales["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time ) - df_sales["agreed_delivery_date"]=pd.to_datetime( + df_sales["agreed_delivery_date"] = pd.to_datetime( df_sales["agreed_delivery_date"], format="%Y-%m-%d" ) - df_sales["agreed_payment_date"]=pd.to_datetime( + df_sales["agreed_payment_date"] = pd.to_datetime( df_sales["agreed_payment_date"], format="%Y-%m-%d" ) - df_sales=df_sales.drop(labels=["created_at", "last_updated"], axis=1) + df_sales = df_sales.drop(labels=["created_at", "last_updated"], axis=1) df_sales.reset_index(inplace=True) return df_sales @@ -68,25 +67,23 @@ def create_fact_sales_order(dict_of_df): def create_fact_purchase_orders(dict_of_df): - df_po=dict_of_df["purchase_order"] - df_po.index.name="purchase_record_id" - df_po["created_date"]=df_po["created_at"].astype("datetime64[ns]").dt.date - df_po["created_time"]=( + df_po = dict_of_df["purchase_order"] + df_po.index.name = "purchase_record_id" + df_po["created_date"] = df_po["created_at"].astype("datetime64[ns]").dt.date + df_po["created_time"] = ( df_po["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time ) - df_po["last_updated_date"]=df_po["last_updated"].astype( - "datetime64[ns]").dt.date - df_po["last_updated_time"]=( + df_po["last_updated_date"] = df_po["last_updated"].astype("datetime64[ns]").dt.date + df_po["last_updated_time"] = ( df_po["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time - ) - df_po["agreed_delivery_date"]=pd.to_datetime( + df_po["agreed_delivery_date"] = pd.to_datetime( df_po["agreed_delivery_date"], format="%Y-%m-%d" ) - df_po["agreed_payment_date"]=pd.to_datetime( + df_po["agreed_payment_date"] = pd.to_datetime( df_po["agreed_payment_date"], format="%Y-%m-%d" ) - df_po=df_po.drop(labels=["created_at", "last_updated"], axis=1) + df_po = df_po.drop(labels=["created_at", "last_updated"], axis=1) df_po.reset_index(inplace=True) return df_po @@ -95,26 +92,25 @@ def create_fact_purchase_orders(dict_of_df): def create_fact_payment(dict_of_df): - df_payment=dict_of_df["payment"] - df_payment.index.name="payment_record_id" - df_payment["created_date"]=( + df_payment = dict_of_df["payment"] + df_payment.index.name = "payment_record_id" + df_payment["created_date"] = ( df_payment["created_at"].astype("datetime64[ns]").dt.date ) - df_payment["created_time"]=( + df_payment["created_time"] = ( df_payment["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time ) - df_payment["last_updated_date"]=( + df_payment["last_updated_date"] = ( df_payment["last_updated"].astype("datetime64[ns]").dt.date ) - df_payment["last_updated_time"]=( - df_payment["last_updated"].astype( - "datetime64[ns]").dt.floor("s").dt.time + df_payment["last_updated_time"] = ( + df_payment["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time ) - df_payment["payment_date"]=pd.to_datetime( + df_payment["payment_date"] = pd.to_datetime( df_payment["payment_date"], format="%Y-%m-%d" ) - df_payment=df_payment.drop(labels=["created_at", "last_updated"], axis=1) - + df_payment = df_payment.drop(labels=["created_at", "last_updated"], axis=1) + df_payment.reset_index(inplace=True) return df_payment @@ -123,7 +119,7 @@ def create_fact_payment(dict_of_df): def create_dim_transaction(dict_of_df): - df_transaction=dict_of_df["transaction"].drop( + df_transaction = dict_of_df["transaction"].drop( labels=["created_at", "last_updated"], axis=1 ) return df_transaction @@ -133,7 +129,7 @@ def create_dim_transaction(dict_of_df): def create_dim_location(dict_of_df): - df_loc=( + df_loc = ( dict_of_df["address"] .drop(labels=["created_at", "last_updated"], axis=1) .rename(columns={"address_id": "location_id"}) @@ -142,10 +138,12 @@ def create_dim_location(dict_of_df): def create_dim_counterparty(dict_of_df): - df_prefixed_address=dict_of_df["address"].drop(labels=["created_at", "last_updated"], axis=1).add_prefix( - "counterparty_legal_", axis=1 + df_prefixed_address = ( + dict_of_df["address"] + .drop(labels=["created_at", "last_updated"], axis=1) + .add_prefix("counterparty_legal_", axis=1) ) - df_cp=pd.merge( + df_cp = pd.merge( dict_of_df["counterparty"], df_prefixed_address, left_on="legal_address_id", @@ -153,7 +151,11 @@ def create_dim_counterparty(dict_of_df): how="inner", ) df_cp.drop( - columns=["legal_address_id", "counterparty_legal_address_id", ], inplace=True + columns=[ + "legal_address_id", + "counterparty_legal_address_id", + ], + inplace=True, ) return df_cp @@ -162,7 +164,7 @@ def create_dim_counterparty(dict_of_df): def create_dim_date(dict_of_df): - fact_dfs=[ + fact_dfs = [ create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df), @@ -174,16 +176,16 @@ def create_dim_date(dict_of_df): ] for col in date_col_names: list_of_date_columns.append(df[col]) - sr_date=pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") - df_date=pd.DataFrame(data=sr_date, columns=["date_id"]) + sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") + df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) df_date.drop_duplicates(inplace=True) - df_date["year"]=df_date["date_id"].dt.year - df_date["month"]=df_date["date_id"].dt.month - df_date["day"]=df_date["date_id"].dt.day - df_date["day_of_week"]=df_date["date_id"].dt.dayofweek - df_date["day_name"]=df_date["date_id"].dt.day_name() - df_date["month_name"]=df_date["date_id"].dt.month_name() - df_date["quarter"]=df_date["date_id"].dt.quarter + df_date["year"] = df_date["date_id"].dt.year + df_date["month"] = df_date["date_id"].dt.month + df_date["day"] = df_date["date_id"].dt.day + df_date["day_of_week"] = df_date["date_id"].dt.dayofweek + df_date["day_name"] = df_date["date_id"].dt.day_name() + df_date["month_name"] = df_date["date_id"].dt.month_name() + df_date["quarter"] = df_date["date_id"].dt.quarter return df_date @@ -191,13 +193,13 @@ def create_dim_date(dict_of_df): def scrape_currency_names(): - response=requests.get("https://www.xe.com/currency/").content - soup=BeautifulSoup(response, "html.parser") - currency=[ + response = requests.get("https://www.xe.com/currency/").content + soup = BeautifulSoup(response, "html.parser") + currency = [ item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) ] - sr=pd.Series(currency) - df_cur=sr.str.split(pat=" - ", expand=True).rename( + sr = pd.Series(currency) + df_cur = sr.str.split(pat=" - ", expand=True).rename( {0: "currency_code", 1: "currency_name"}, axis=1 ) return df_cur @@ -207,9 +209,8 @@ def scrape_currency_names(): def create_dim_currency(dict_of_df, names=scrape_currency_names()): - df_cur=dict_of_df["currency"].drop( - labels=["created_at", "last_updated"], axis=1) - dim_cur=pd.merge( + df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) + dim_cur = pd.merge( df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" ) return dim_cur @@ -219,9 +220,8 @@ def create_dim_currency(dict_of_df, names=scrape_currency_names()): def create_dim_payment_type(dict_of_df): - df_payment_type=dict_of_df["payment_type"] - dim_payment_type=df_payment_type.loc[:, [ - "payment_type_id", "payment_type_name"]] + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] return dim_payment_type @@ -229,8 +229,8 @@ def create_dim_payment_type(dict_of_df): def create_dim_design(dict_of_df): - df_design=dict_of_df["design"] - dim_design=df_design.loc[ + df_design = dict_of_df["design"] + dim_design = df_design.loc[ :, ["design_id", "design_name", "file_name", "file_location"] ] return dim_design @@ -240,10 +240,10 @@ def create_dim_design(dict_of_df): def create_dim_staff(dict_of_df): - staff_department=pd.merge( + staff_department = pd.merge( dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" ) - dim_staff=staff_department.loc[ + dim_staff = staff_department.loc[ :, [ "staff_id", diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py index ff282eb..ea7bad1 100644 --- a/tests/test_dataframes.py +++ b/tests/test_dataframes.py @@ -227,7 +227,6 @@ class TestCreateDimDate: expected_df, axis="columns").all(axis=None) - class TestCreateDimLocation: def test_returns_correct_columns_lo(self): dict_df = { @@ -302,6 +301,5 @@ class TestCreateFactPayment: for col in expected_cols: - if "_date" or "_time" in col: assert result[col].dtype == "O" -- cgit v1.2.3 From 03787e3aabc5bc516bb7bfcc3831a74681932c36 Mon Sep 17 00:00:00 2001 From: HastarTara Date: Wed, 28 Aug 2024 09:48:07 +0100 Subject: moved extract_l & dataframes into own directory in src --- src/dataframes.py | 228 ------------------------------- src/transform_lambda.py | 217 ----------------------------- src/transform_lambda/dataframes.py | 228 +++++++++++++++++++++++++++++++ src/transform_lambda/transform_lambda.py | 217 +++++++++++++++++++++++++++++ 4 files changed, 445 insertions(+), 445 deletions(-) delete mode 100644 src/dataframes.py delete mode 100644 src/transform_lambda.py create mode 100644 src/transform_lambda/dataframes.py create mode 100644 src/transform_lambda/transform_lambda.py diff --git a/src/dataframes.py b/src/dataframes.py deleted file mode 100644 index f122368..0000000 --- a/src/dataframes.py +++ /dev/null @@ -1,228 +0,0 @@ -import pandas as pd -from bs4 import BeautifulSoup -import requests - -# Table names: -# fact_sales_order -# fact_purchase_orders -# fact_payment -# dim_transaction -# dim_staff -# dim_payment_type -# dim_location -# dim_design -# dim_date -# dim_currency -# dim_counterparty - - -# no test, same as fact_payment -def create_fact_sales_order(dict_of_df): - df_sales = dict_of_df["sales_order"] - df_sales.index.name = "sales_record_id" - df_sales["created_date"] = df_sales["created_at"].astype("datetime64[ns]").dt.date - df_sales["created_time"] = ( - df_sales["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time - ) - df_sales["last_updated_date"] = ( - df_sales["last_updated"].astype("datetime64[ns]").dt.date - ) - df_sales["last_updated_time"] = ( - df_sales["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time - ) - df_sales["agreed_delivery_date"] = pd.to_datetime( - df_sales["agreed_delivery_date"], format="%Y-%m-%d" - ) - df_sales["agreed_payment_date"] = pd.to_datetime( - df_sales["agreed_payment_date"], format="%Y-%m-%d" - ) - df_sales = df_sales.drop(labels=["created_at", "last_updated"], axis=1) - df_sales.reset_index(inplace=True) - return df_sales - - -# no test, same as fact_payment - - -def create_fact_purchase_orders(dict_of_df): - df_po = dict_of_df["purchase_order"] - df_po.index.name = "purchase_record_id" - df_po["created_date"] = df_po["created_at"].astype("datetime64[ns]").dt.date - df_po["created_time"] = ( - df_po["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time - ) - df_po["last_updated_date"] = df_po["last_updated"].astype("datetime64[ns]").dt.date - df_po["last_updated_time"] = ( - df_po["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time - ) - df_po["agreed_delivery_date"] = pd.to_datetime( - df_po["agreed_delivery_date"], format="%Y-%m-%d" - ) - df_po["agreed_payment_date"] = pd.to_datetime( - df_po["agreed_payment_date"], format="%Y-%m-%d" - ) - df_po = df_po.drop(labels=["created_at", "last_updated"], axis=1) - df_po.reset_index(inplace=True) - return df_po - - -# test passed - - -def create_fact_payment(dict_of_df): - df_payment = dict_of_df["payment"] - df_payment.index.name = "payment_record_id" - df_payment["created_date"] = ( - df_payment["created_at"].astype("datetime64[ns]").dt.date - ) - df_payment["created_time"] = ( - df_payment["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time - ) - df_payment["last_updated_date"] = ( - df_payment["last_updated"].astype("datetime64[ns]").dt.date - ) - df_payment["last_updated_time"] = ( - df_payment["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time - ) - df_payment["payment_date"] = pd.to_datetime( - df_payment["payment_date"], format="%Y-%m-%d" - ) - df_payment = df_payment.drop(labels=["created_at", "last_updated"], axis=1) - df_payment.reset_index(inplace=True) - return df_payment - - -# test passed - - -def create_dim_transaction(dict_of_df): - df_transaction = dict_of_df["transaction"].drop( - labels=["created_at", "last_updated"], axis=1 - ) - return df_transaction - - -# test passed - - -def create_dim_location(dict_of_df): - df_loc = ( - dict_of_df["address"] - .drop(labels=["created_at", "last_updated"], axis=1) - .rename(columns={"address_id": "location_id"}) - ) - return df_loc - - -def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df["address"].add_prefix( - "counterparty_legal_", axis=1 - ) - df_cp = pd.merge( - dict_of_df["counterparty"], - df_prefixed_address, - left_on="legal_address_id", - right_on="counterparty_legal_address_id", - how="outer", - ) - df_cp.drop( - columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True - ) - return df_cp - - -# test passed - - -def create_dim_date(dict_of_df): - fact_dfs = [ - create_fact_payment(dict_of_df), - create_fact_purchase_orders(dict_of_df), - create_fact_sales_order(dict_of_df), - ] - list_of_date_columns = [] - for df in fact_dfs: - date_col_names = [ - col_name for col_name in list(df.columns) if "_date" in col_name - ] - for col in date_col_names: - list_of_date_columns.append(df[col]) - sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") - df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) - df_date.drop_duplicates(inplace=True) - df_date["year"] = df_date["date_id"].dt.year - df_date["month"] = df_date["date_id"].dt.month - df_date["day"] = df_date["date_id"].dt.day - df_date["day_of_week"] = df_date["date_id"].dt.dayofweek - df_date["day_name"] = df_date["date_id"].dt.day_name() - df_date["month_name"] = df_date["date_id"].dt.month_name() - df_date["quarter"] = df_date["date_id"].dt.quarter - return df_date - - -# tests passed - - -def scrape_currency_names(): - response = requests.get("https://www.xe.com/currency/").content - soup = BeautifulSoup(response, "html.parser") - currency = [ - item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) - ] - sr = pd.Series(currency) - df_cur = sr.str.split(pat=" - ", expand=True).rename( - {0: "currency_code", 1: "currency_name"}, axis=1 - ) - return df_cur - - -# tests passed - - -def create_dim_currency(dict_of_df, names=scrape_currency_names()): - df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) - dim_cur = pd.merge( - df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" - ) - return dim_cur - - -# tests passed - - -def create_dim_payment_type(dict_of_df): - df_payment_type = dict_of_df["payment_type"] - dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] - return dim_payment_type - - -# tests passed - - -def create_dim_design(dict_of_df): - df_design = dict_of_df["design"] - dim_design = df_design.loc[ - :, ["design_id", "design_name", "file_name", "file_location"] - ] - return dim_design - - -# tests passed - - -def create_dim_staff(dict_of_df): - staff_department = pd.merge( - dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" - ) - dim_staff = staff_department.loc[ - :, - [ - "staff_id", - "first_name", - "last_name", - "department_name", - "location", - "email_address", - ], - ] - return dim_staff diff --git a/src/transform_lambda.py b/src/transform_lambda.py deleted file mode 100644 index 93b2284..0000000 --- a/src/transform_lambda.py +++ /dev/null @@ -1,217 +0,0 @@ -import json -import boto3 -import re -import logging -import pandas as pd -import pyarrow as pa -import pyarrow.parquet as pq -from dataframes import * -from botocore.exceptions import ClientError -from pg8000.native import Connection, InterfaceError -from datetime import datetime - - -class DBConnectionException(Exception): - """Wraps pg8000.native Error or DatabaseError.""" - - def __init__(self, e): - """Initialise with provided error message.""" - self.message = str(e) - super().__init__(self.message) - - -logger = logging.getLogger(__name__) - -logging.basicConfig( - format="{asctime} - {levelname} - {message}", - style="{", - datefmt="%Y-%m-%d %H:%M", - level=logging.DEBUG, -) - -logging.getLogger("botocore").setLevel(logging.WARNING) - -TABLES = [ - "sales_order", - "transaction", - "payment", - "counterparty", - "address", - "staff", - "purchase_order", - "department", - "currency", - "design", - "payment_type", -] - - -def lambda_handler(event, context): - db = None - - try: - db = connect_to_database() - bucket = bucket_name("transform") - - existing_s3_files = list_existing_s3_files(bucket) - - dict_of_df = read_from_s3_subfolder_to_df( - TABLES, bucket_name("extract"), client=boto3.client("s3") - ) - - immutable_df_dict = { - "dim_counterparty": create_dim_counterparty(dict_of_df), - "dim_date": create_dim_date(dict_of_df), - "dim_location": create_dim_location(dict_of_df), - "dim_staff": create_dim_staff(dict_of_df), - "dim_design": create_dim_design(dict_of_df), - } - - mutable_df_dict = { - "fact_sales_order": create_fact_sales_order(dict_of_df), - "fact_purchase_order": create_fact_purchase_orders(dict_of_df), - "fact_payment": create_fact_payment(dict_of_df), - "dim_currency": create_dim_currency(dict_of_df), - } - - status = process_to_parquet_and_upload_to_s3( - existing_s3_files, immutable_df_dict, mutable_df_dict, bucket - ) - - if not status["uploaded"]: - logger.info("No dataframes written to the bucket.") - return { - "statusCode": 204, - "body": json.dumps("No files where uploaded."), - } - - return { - "statusCode": 200, - "body": json.dumps( - f"""Parquet files processed for {', '.join(status['uploaded'])} and uploaded successfully.{ - 'The following tables were not uploaded: '+', '.join([status['not_uploaded']]) if status['not_uploaded'] else ''}""" - ), - } - - except Exception as e: - logger.error(f"Error: {e}", exc_info=True) - return {"statusCode": 500, "body": json.dumps("Internal server error.")} - finally: - if db: - db.close() - - -def process_to_parquet_and_upload_to_s3( - existing_s3_files, - immutable_df_dict, - mutable_df_dict, - bucket, - client=boto3.client("s3"), -): - status = {"uploaded": [], "not_uploaded": []} - - for table_name, df in immutable_df_dict.items(): - if table_name in existing_s3_files: - status["not_uploaded"].append(table_name) - else: - parquet_file = df.to_parquet( - f"{table_name}.parquet", engine="pyarrow" - ) # or fastparquet - # changed parquet_file variable to the file name - client.upload_file(f"{table_name}.parquet", bucket, f"{table_name}.parquet") - status["uploaded"].append(table_name) - - for table_name, df in mutable_df_dict.items(): - s3_key = datetime.strftime( - datetime.today(), f"{table_name}/%Y/%m/%d/{table_name}_%H:%M:%S.parquet" - ) - parquet_file = df.to_parquet( - f"{table_name}.parquet", engine="pyarrow" - ) # or fastparquet - client.upload_file(f"{table_name}.parquet", bucket, s3_key) - status["uploaded"].append(table_name) - - return status - - -def retrieve_secrets(): - secret_name = "bentley-secrets" - region_name = "eu-west-2" - - # Create a Secrets Manager client - session = boto3.session.Session() - client = session.client(service_name="secretsmanager", region_name=region_name) - - try: - get_secret_value_response = client.get_secret_value(SecretId=secret_name) - except ClientError as e: - logger.error(f"Failed to retrieve secret {secret_name}: {str(e)}") - raise e - except KeyError: - logger.error(f"Secret {secret_name} does not contain a SecretString") - raise ValueError(f"Secret {secret_name} does not contain a SecretString") - - return get_secret_value_response["SecretString"] - - -def connect_to_database() -> Connection: - try: - secrets = json.loads(retrieve_secrets()) - host = secrets["host"] - port = secrets["port"] - user = secrets["user"] - password = secrets["password"] - database = secrets["database"] - - return Connection( - database=database, user=user, password=password, host=host, port=port - ) - except InterfaceError as i: - logger.error(f"Interface error: {i}") - raise DBConnectionException("Failed to connect to database") - - -def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client("s3")): - table_dfs = {} - for table in tables: - response = client.list_objects_v2(Bucket=bucket, Prefix=table) - list_of_keys = [ - "s3://" + bucket + "/" + object["Key"] for object in response["Contents"] - ] - list_of_df = [pd.read_csv(key) for key in list_of_keys] - table_dfs[table] = pd.concat(list_of_df) - return table_dfs - - -def bucket_name(bucket_prefix, client=boto3.client("s3")): - response = client.list_buckets() - bucket_filter = [ - bucket["Name"] - for bucket in response["Buckets"] - if bucket_prefix in bucket["Name"] - ] - - return bucket_filter[0] - - -def list_existing_s3_files(bucket_name, client=boto3.client("s3")): - logging.info("Listing existing S3 files") - - try: - response = client.list_objects_v2(Bucket=bucket_name) - - if "Contents" in response: - existing_files = [obj["Key"] for obj in response["Contents"]] - else: - logger.error("The bucket is empty") - return [] # changed from None to [] so it is an iterable - - except ClientError as e: - logger.error(f"Error listing S3 objects: {e}") - raise e - - return existing_files - - -if __name__ == "__main__": - lambda_handler({}, "") diff --git a/src/transform_lambda/dataframes.py b/src/transform_lambda/dataframes.py new file mode 100644 index 0000000..f122368 --- /dev/null +++ b/src/transform_lambda/dataframes.py @@ -0,0 +1,228 @@ +import pandas as pd +from bs4 import BeautifulSoup +import requests + +# Table names: +# fact_sales_order +# fact_purchase_orders +# fact_payment +# dim_transaction +# dim_staff +# dim_payment_type +# dim_location +# dim_design +# dim_date +# dim_currency +# dim_counterparty + + +# no test, same as fact_payment +def create_fact_sales_order(dict_of_df): + df_sales = dict_of_df["sales_order"] + df_sales.index.name = "sales_record_id" + df_sales["created_date"] = df_sales["created_at"].astype("datetime64[ns]").dt.date + df_sales["created_time"] = ( + df_sales["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_sales["last_updated_date"] = ( + df_sales["last_updated"].astype("datetime64[ns]").dt.date + ) + df_sales["last_updated_time"] = ( + df_sales["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_sales["agreed_delivery_date"] = pd.to_datetime( + df_sales["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_sales["agreed_payment_date"] = pd.to_datetime( + df_sales["agreed_payment_date"], format="%Y-%m-%d" + ) + df_sales = df_sales.drop(labels=["created_at", "last_updated"], axis=1) + df_sales.reset_index(inplace=True) + return df_sales + + +# no test, same as fact_payment + + +def create_fact_purchase_orders(dict_of_df): + df_po = dict_of_df["purchase_order"] + df_po.index.name = "purchase_record_id" + df_po["created_date"] = df_po["created_at"].astype("datetime64[ns]").dt.date + df_po["created_time"] = ( + df_po["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_po["last_updated_date"] = df_po["last_updated"].astype("datetime64[ns]").dt.date + df_po["last_updated_time"] = ( + df_po["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_po["agreed_delivery_date"] = pd.to_datetime( + df_po["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_po["agreed_payment_date"] = pd.to_datetime( + df_po["agreed_payment_date"], format="%Y-%m-%d" + ) + df_po = df_po.drop(labels=["created_at", "last_updated"], axis=1) + df_po.reset_index(inplace=True) + return df_po + + +# test passed + + +def create_fact_payment(dict_of_df): + df_payment = dict_of_df["payment"] + df_payment.index.name = "payment_record_id" + df_payment["created_date"] = ( + df_payment["created_at"].astype("datetime64[ns]").dt.date + ) + df_payment["created_time"] = ( + df_payment["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_payment["last_updated_date"] = ( + df_payment["last_updated"].astype("datetime64[ns]").dt.date + ) + df_payment["last_updated_time"] = ( + df_payment["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_payment["payment_date"] = pd.to_datetime( + df_payment["payment_date"], format="%Y-%m-%d" + ) + df_payment = df_payment.drop(labels=["created_at", "last_updated"], axis=1) + df_payment.reset_index(inplace=True) + return df_payment + + +# test passed + + +def create_dim_transaction(dict_of_df): + df_transaction = dict_of_df["transaction"].drop( + labels=["created_at", "last_updated"], axis=1 + ) + return df_transaction + + +# test passed + + +def create_dim_location(dict_of_df): + df_loc = ( + dict_of_df["address"] + .drop(labels=["created_at", "last_updated"], axis=1) + .rename(columns={"address_id": "location_id"}) + ) + return df_loc + + +def create_dim_counterparty(dict_of_df): + df_prefixed_address = dict_of_df["address"].add_prefix( + "counterparty_legal_", axis=1 + ) + df_cp = pd.merge( + dict_of_df["counterparty"], + df_prefixed_address, + left_on="legal_address_id", + right_on="counterparty_legal_address_id", + how="outer", + ) + df_cp.drop( + columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True + ) + return df_cp + + +# test passed + + +def create_dim_date(dict_of_df): + fact_dfs = [ + create_fact_payment(dict_of_df), + create_fact_purchase_orders(dict_of_df), + create_fact_sales_order(dict_of_df), + ] + list_of_date_columns = [] + for df in fact_dfs: + date_col_names = [ + col_name for col_name in list(df.columns) if "_date" in col_name + ] + for col in date_col_names: + list_of_date_columns.append(df[col]) + sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") + df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) + df_date.drop_duplicates(inplace=True) + df_date["year"] = df_date["date_id"].dt.year + df_date["month"] = df_date["date_id"].dt.month + df_date["day"] = df_date["date_id"].dt.day + df_date["day_of_week"] = df_date["date_id"].dt.dayofweek + df_date["day_name"] = df_date["date_id"].dt.day_name() + df_date["month_name"] = df_date["date_id"].dt.month_name() + df_date["quarter"] = df_date["date_id"].dt.quarter + return df_date + + +# tests passed + + +def scrape_currency_names(): + response = requests.get("https://www.xe.com/currency/").content + soup = BeautifulSoup(response, "html.parser") + currency = [ + item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) + ] + sr = pd.Series(currency) + df_cur = sr.str.split(pat=" - ", expand=True).rename( + {0: "currency_code", 1: "currency_name"}, axis=1 + ) + return df_cur + + +# tests passed + + +def create_dim_currency(dict_of_df, names=scrape_currency_names()): + df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) + dim_cur = pd.merge( + df_cur, names, left_on="currency_code", right_on="currency_code", how="inner" + ) + return dim_cur + + +# tests passed + + +def create_dim_payment_type(dict_of_df): + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + return dim_payment_type + + +# tests passed + + +def create_dim_design(dict_of_df): + df_design = dict_of_df["design"] + dim_design = df_design.loc[ + :, ["design_id", "design_name", "file_name", "file_location"] + ] + return dim_design + + +# tests passed + + +def create_dim_staff(dict_of_df): + staff_department = pd.merge( + dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" + ) + dim_staff = staff_department.loc[ + :, + [ + "staff_id", + "first_name", + "last_name", + "department_name", + "location", + "email_address", + ], + ] + return dim_staff diff --git a/src/transform_lambda/transform_lambda.py b/src/transform_lambda/transform_lambda.py new file mode 100644 index 0000000..93b2284 --- /dev/null +++ b/src/transform_lambda/transform_lambda.py @@ -0,0 +1,217 @@ +import json +import boto3 +import re +import logging +import pandas as pd +import pyarrow as pa +import pyarrow.parquet as pq +from dataframes import * +from botocore.exceptions import ClientError +from pg8000.native import Connection, InterfaceError +from datetime import datetime + + +class DBConnectionException(Exception): + """Wraps pg8000.native Error or DatabaseError.""" + + def __init__(self, e): + """Initialise with provided error message.""" + self.message = str(e) + super().__init__(self.message) + + +logger = logging.getLogger(__name__) + +logging.basicConfig( + format="{asctime} - {levelname} - {message}", + style="{", + datefmt="%Y-%m-%d %H:%M", + level=logging.DEBUG, +) + +logging.getLogger("botocore").setLevel(logging.WARNING) + +TABLES = [ + "sales_order", + "transaction", + "payment", + "counterparty", + "address", + "staff", + "purchase_order", + "department", + "currency", + "design", + "payment_type", +] + + +def lambda_handler(event, context): + db = None + + try: + db = connect_to_database() + bucket = bucket_name("transform") + + existing_s3_files = list_existing_s3_files(bucket) + + dict_of_df = read_from_s3_subfolder_to_df( + TABLES, bucket_name("extract"), client=boto3.client("s3") + ) + + immutable_df_dict = { + "dim_counterparty": create_dim_counterparty(dict_of_df), + "dim_date": create_dim_date(dict_of_df), + "dim_location": create_dim_location(dict_of_df), + "dim_staff": create_dim_staff(dict_of_df), + "dim_design": create_dim_design(dict_of_df), + } + + mutable_df_dict = { + "fact_sales_order": create_fact_sales_order(dict_of_df), + "fact_purchase_order": create_fact_purchase_orders(dict_of_df), + "fact_payment": create_fact_payment(dict_of_df), + "dim_currency": create_dim_currency(dict_of_df), + } + + status = process_to_parquet_and_upload_to_s3( + existing_s3_files, immutable_df_dict, mutable_df_dict, bucket + ) + + if not status["uploaded"]: + logger.info("No dataframes written to the bucket.") + return { + "statusCode": 204, + "body": json.dumps("No files where uploaded."), + } + + return { + "statusCode": 200, + "body": json.dumps( + f"""Parquet files processed for {', '.join(status['uploaded'])} and uploaded successfully.{ + 'The following tables were not uploaded: '+', '.join([status['not_uploaded']]) if status['not_uploaded'] else ''}""" + ), + } + + except Exception as e: + logger.error(f"Error: {e}", exc_info=True) + return {"statusCode": 500, "body": json.dumps("Internal server error.")} + finally: + if db: + db.close() + + +def process_to_parquet_and_upload_to_s3( + existing_s3_files, + immutable_df_dict, + mutable_df_dict, + bucket, + client=boto3.client("s3"), +): + status = {"uploaded": [], "not_uploaded": []} + + for table_name, df in immutable_df_dict.items(): + if table_name in existing_s3_files: + status["not_uploaded"].append(table_name) + else: + parquet_file = df.to_parquet( + f"{table_name}.parquet", engine="pyarrow" + ) # or fastparquet + # changed parquet_file variable to the file name + client.upload_file(f"{table_name}.parquet", bucket, f"{table_name}.parquet") + status["uploaded"].append(table_name) + + for table_name, df in mutable_df_dict.items(): + s3_key = datetime.strftime( + datetime.today(), f"{table_name}/%Y/%m/%d/{table_name}_%H:%M:%S.parquet" + ) + parquet_file = df.to_parquet( + f"{table_name}.parquet", engine="pyarrow" + ) # or fastparquet + client.upload_file(f"{table_name}.parquet", bucket, s3_key) + status["uploaded"].append(table_name) + + return status + + +def retrieve_secrets(): + secret_name = "bentley-secrets" + region_name = "eu-west-2" + + # Create a Secrets Manager client + session = boto3.session.Session() + client = session.client(service_name="secretsmanager", region_name=region_name) + + try: + get_secret_value_response = client.get_secret_value(SecretId=secret_name) + except ClientError as e: + logger.error(f"Failed to retrieve secret {secret_name}: {str(e)}") + raise e + except KeyError: + logger.error(f"Secret {secret_name} does not contain a SecretString") + raise ValueError(f"Secret {secret_name} does not contain a SecretString") + + return get_secret_value_response["SecretString"] + + +def connect_to_database() -> Connection: + try: + secrets = json.loads(retrieve_secrets()) + host = secrets["host"] + port = secrets["port"] + user = secrets["user"] + password = secrets["password"] + database = secrets["database"] + + return Connection( + database=database, user=user, password=password, host=host, port=port + ) + except InterfaceError as i: + logger.error(f"Interface error: {i}") + raise DBConnectionException("Failed to connect to database") + + +def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client("s3")): + table_dfs = {} + for table in tables: + response = client.list_objects_v2(Bucket=bucket, Prefix=table) + list_of_keys = [ + "s3://" + bucket + "/" + object["Key"] for object in response["Contents"] + ] + list_of_df = [pd.read_csv(key) for key in list_of_keys] + table_dfs[table] = pd.concat(list_of_df) + return table_dfs + + +def bucket_name(bucket_prefix, client=boto3.client("s3")): + response = client.list_buckets() + bucket_filter = [ + bucket["Name"] + for bucket in response["Buckets"] + if bucket_prefix in bucket["Name"] + ] + + return bucket_filter[0] + + +def list_existing_s3_files(bucket_name, client=boto3.client("s3")): + logging.info("Listing existing S3 files") + + try: + response = client.list_objects_v2(Bucket=bucket_name) + + if "Contents" in response: + existing_files = [obj["Key"] for obj in response["Contents"]] + else: + logger.error("The bucket is empty") + return [] # changed from None to [] so it is an iterable + + except ClientError as e: + logger.error(f"Error listing S3 objects: {e}") + raise e + + return existing_files + + +if __name__ == "__main__": + lambda_handler({}, "") -- cgit v1.2.3 From 553c24060a9a4224efceec5d27c0e6083bca4b98 Mon Sep 17 00:00:00 2001 From: HastarTara Date: Wed, 28 Aug 2024 10:46:17 +0100 Subject: work on lambda handler dirctory config --- terraform/lambda.tf | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/terraform/lambda.tf b/terraform/lambda.tf index d33a6c9..6e5000a 100644 --- a/terraform/lambda.tf +++ b/terraform/lambda.tf @@ -87,6 +87,13 @@ data "archive_file" "transform_lambda_zip" { type = "zip" source_file = "${path.module}/../src/transform_lambda.py" output_path = "${path.module}/../transform_function.zip" + + +data "archive_file" "transform_lambda_zip" { + type = "zip" + source_dir = "../src/transform_lambda" + output_path = "../transform_lambda.zip" +} } resource "aws_s3_object" "transform_lambda_code" { bucket = aws_s3_bucket.lambda_code_bucket.bucket -- cgit v1.2.3 From 05e39b418ea6991e87adedc979c887ae4e72edc3 Mon Sep 17 00:00:00 2001 From: HastarTara Date: Wed, 28 Aug 2024 10:47:43 +0100 Subject: work on lambda handler dirctory config 2 --- terraform/lambda.tf | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/terraform/lambda.tf b/terraform/lambda.tf index 6e5000a..5f4a58e 100644 --- a/terraform/lambda.tf +++ b/terraform/lambda.tf @@ -83,18 +83,13 @@ resource "aws_lambda_function" "extract_lambda" { # Transform Lambda Function # ############################# -data "archive_file" "transform_lambda_zip" { - type = "zip" - source_file = "${path.module}/../src/transform_lambda.py" - output_path = "${path.module}/../transform_function.zip" - data "archive_file" "transform_lambda_zip" { type = "zip" - source_dir = "../src/transform_lambda" - output_path = "../transform_lambda.zip" -} + source_dir = "${path.module}../src/transform_lambda" + output_path = "${path.module}../transform_lambda.zip" } + resource "aws_s3_object" "transform_lambda_code" { bucket = aws_s3_bucket.lambda_code_bucket.bucket key = "${var.transform_lambda_name}/transform_function.zip" -- cgit v1.2.3