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') 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') 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') 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') 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') 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') 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') 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') 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 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(-) (limited to 'tests') 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 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(-) (limited to 'tests') 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