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 (limited to '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 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(-) (limited to 'tests/test_load_lambda.py') 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 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(-) (limited to 'tests/test_load_lambda.py') 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(-) (limited to 'tests/test_load_lambda.py') 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(-) (limited to 'tests/test_load_lambda.py') 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 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(-) (limited to 'tests/test_load_lambda.py') 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(-) (limited to 'tests/test_load_lambda.py') 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(-) (limited to 'tests/test_load_lambda.py') 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 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(-) (limited to 'tests/test_load_lambda.py') 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(-) (limited to 'tests/test_load_lambda.py') 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 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(-) (limited to 'tests/test_load_lambda.py') 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 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(-) (limited to 'tests/test_load_lambda.py') 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(-) (limited to 'tests/test_load_lambda.py') 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(+) (limited to 'tests/test_load_lambda.py') 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(-) (limited to 'tests/test_load_lambda.py') 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 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(-) (limited to 'tests/test_load_lambda.py') 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 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(+) (limited to 'tests/test_load_lambda.py') 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 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(-) (limited to 'tests/test_load_lambda.py') 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(-) (limited to 'tests/test_load_lambda.py') 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