Merge pull request #97 from ajschofield/test/test_transform_lambda

PR: mergeing test_transform_lambda to dev

4 files changed, 270 insertions, 150 deletions

diff --git a/src/dataframes.py b/src/dataframes.py
index 684f102..ab53063 100644
--- a/src/dataframes.py
+++ b/src/dataframes.py
@@ -1,11 +1,5 @@
 import pandas as pd
 from bs4 import BeautifulSoup
-from src.transform_lambda import read_from_s3_subfolder_to_df, tables
-from src.extract_lambda import extract_bucket
-import json
-import boto3
-import re
-from datetime import datetime as dt
 import requests
 
 # Table names:
@@ -22,10 +16,6 @@ import requests
 # dim_counterparty
 
 
-def create_dim_transaction(dict_of_df):
-    pass
-
-
 def create_fact_sales_order(dict_of_df):
     df_sales = dict_of_df["sales_order"]
     df_sales.index.name = "sales_record_id"
@@ -33,8 +23,6 @@ def create_fact_sales_order(dict_of_df):
     df_sales["created_time"] = pd.to_datetime(df_sales["created_at"]).dt.time
     df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"]).dt.date
     df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time
-    pd.merge(dict_of_df["staff"], df_sales["sales_staff_id"], on="staff_id", how="left")
-    # df_sales.rename(columns={"staff_id": "sales_staff_id"})
     fact_sales_order = df_sales.loc[
         :,
         [
@@ -81,10 +69,13 @@ def create_fact_purchase_orders(dict_of_df):
 def create_fact_payment(dict_of_df):
     df_payment = dict_of_df["payment"]
     df_payment.index.name = "payment_record_id"
-    df_payment["created_date"] = pd.to_datetime(df_payment["created_at"]).dt.date
-    df_payment["created_time"] = pd.to_datetime(df_payment["created_at"]).dt.time
-    df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"]).dt.date
-    df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"]).dt.time
+    df_payment["created_date"] = df_payment["created_at"].date()
+    df_payment["created_time"] = df_payment["created_at"].time
+    df_payment["last_updated_date"] = df_payment["last_updated"].date()
+    df_payment["last_updated_time"] = df_payment["last_updated"].time
+    df_payment["payment_date"] = pd.to_datetime(
+        df_payment["payment_date"], format="%Y-%m-%d"
+    )
     fact_payment = df_payment.loc[
         :,
         [
@@ -106,22 +97,26 @@ def create_fact_payment(dict_of_df):
     return fact_payment
 
 
-# dim_location from address --> drops 2 columns
+# test passed
+
+
+def create_dim_transaction(dict_of_df):
+    df_transaction = dict_of_df["transaction"].drop(
+        labels=["created_at", "last_updated"], axis=1
+    )
+    return df_transaction
 
 
+# test passed
 def create_dim_location(dict_of_df):
     df_loc = (
         dict_of_df["address"]
         .drop(labels=["created_at", "last_updated"], axis=1)
         .rename(columns={"address_id": "location_id"})
-        .set_index("location_id")
     )
     return df_loc
 
 
-# dim_counterparty from address and counterparty
-
-
 def create_dim_counterparty(dict_of_df):
     df_prefixed_address = dict_of_df["address"].add_prefix(
         "counterparty_legal_", axis=1
@@ -130,33 +125,45 @@ def create_dim_counterparty(dict_of_df):
         dict_of_df["counterparty"],
         df_prefixed_address,
         left_on="legal_address_id",
-        right_on="address_id",
+        right_on="counterparty_legal_address_id",
         how="outer",
-    ).set_index("counterparty_id")
+    )
+    df_cp.drop(
+        columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True
+    )
     return df_cp
 
 
-# dim_date from purchase_order
+# test passed
+
+
 def create_dim_date(dict_of_df):
-    sr_date = pd.concat(
-        [
-            dict_of_df["created_date"],
-            dict_of_df["last_updated_date"],
-            dict_of_df["agreed_delivery_date"],
-            dict_of_df["agreed_payment_date"],
-        ]
-    ).sort()
-    df_date = pd.DataFrame(sr_date, columns="date_id")
+    fact_dfs = [
+        create_fact_payment(dict_of_df),
+        create_fact_purchase_orders(dict_of_df),
+        create_fact_sales_order(dict_of_df),
+    ]
+    date_col_names = [
+        col_name for col_name in list(fact_dfs[0].columns) if "date" in col_name
+    ]
+    list_of_date_columns = []
+    for df in fact_dfs:
+        for col in date_col_names:
+            list_of_date_columns.append(df[col])
+    sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]")
+    df_date = pd.DataFrame(data=sr_date, columns=["date_id"])
+    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["day_name"] = df_date["date_id"].dt.day_name()
+    df_date["month_name"] = df_date["date_id"].dt.month_name()
     df_date["quarter"] = df_date["date_id"].dt.quarter
-    df_date.set_index("date_id")
+    return df_date
 
 
+# tests passed
 def scrape_currency_names():
     response = requests.get("https://www.xe.com/currency/").content
     soup = BeautifulSoup(response, "html.parser")
@@ -170,46 +177,27 @@ def scrape_currency_names():
     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"
-    ).set_index("currency_id")
+    )
     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
 
 
-def create_fact_payment(dict_of_df):
-    df_payment = dict_of_df["payment"]
-    df_payment.index.name = "payment_record_id"
-    df_payment["created_date"] = pd.to_datetime(df_payment["created_at"]).dt.date
-    df_payment["created_time"] = pd.to_datetime(df_payment["created_at"]).dt.time
-    df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"]).dt.date
-    df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"]).dt.time
-    fact_payment = df_payment.loc[
-        :,
-        [
-            "payment_record_id",
-            "payment_id",
-            "created_date",
-            "created_time",
-            "last_updated_date",
-            "last_updated_time",
-            "transaction_id",
-            "counterparty_id",
-            "payment_amount",
-            "currency_id",
-            "payment_type_id",
-            "paid",
-            "payment_date",
-        ],
-    ]
-    return fact_payment
+# tests passed
 
 
 def create_dim_design(dict_of_df):
@@ -220,6 +208,9 @@ def create_dim_design(dict_of_df):
     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"
@@ -236,70 +227,3 @@ def create_dim_staff(dict_of_df):
         ],
     ]
     return dim_staff
-
-
-def create_dim_currency(dict_of_df):
-    df_currency = dict_of_df["currency"]
-    dim_currency = df_currency.loc[:, ["currency_id", "currency_code"]]
-    mappings = {"GBP": "Pound", "USD": "US Dollar", "EUR": "Euro"}
-    dim_currency["currency_name"] = dim_currency["currency_code"].map(mappings)
-    return dim_currency
-
-
-def create_dim_date(dict_of_df):
-    df_sales = dict_of_df["sales"]
-    df_sales = df_sales.loc[:, ["agreed_delivery_date"]]
-    df_sales["agreed_delivery_date"] = pd.to_datetime["agreed_delivery_date"]
-    df_sales["year"] = df_sales["agreed_delivery_date"].dt.year
-    df_sales["month"] = df_sales["agreed_delivery_date"].dt.month
-    df_sales["day"] = df_sales["agreed_delivery_date"].dt.day
-    df_sales["day_of_week"] = df_sales["agreed_delivery_date"].dt.dayofweek
-    df_sales["day_name"] = df_sales["agreed_delivery_date"].dt.day_name()
-    df_sales["month_name"] = df_sales["agreed_delivery_date"].dt.month_name()
-    df_sales["quarter"] = df_sales["agreed_delivery_date"].dt.quarter()
-    dim_date = [
-        "date_id",
-        "year",
-        "month",
-        "day",
-        "day_of_week",
-        "day_name",
-        "month_name",
-        "quarter",
-    ]  # series.dt.quarter()
-    return dim_date
-
-
-# TO DO:
-# complete dim_date from merged fact table
-# merge dataframes into one dataframe
-# remove duplicates
-# test dim_date and fact_sales_order
-
-
-def create_sales_star_schema(dict_of_df):
-    dim_design = create_dim_design(dict_of_df)
-    dim_staff = create_dim_staff(dict_of_df)
-    dim_currency = create_dim_currency(dict_of_df)
-    dim_date = create_dim_date(dict_of_df)
-
-    fact_sales_order = create_fact_sales_order(dict_of_df)
-
-    fact_sales_order = fact_sales_order.merge(dim_design, on="design_id", how="left")
-    fact_sales_order = fact_sales_order.merge(
-        dim_staff, left_on="sales_staff_id", right_on="staff_id", how="left"
-    )
-    fact_sales_order = fact_sales_order.merge(
-        dim_currency, on="currency_id", how="left"
-    )
-    fact_sales_order = fact_sales_order.merge(
-        dim_date, left_on="agreed_delivery_date", right_on="date_id", how="left"
-    )
-
-    return fact_sales_order
-
-
-def create_dim_payment_type(dict_of_df):
-    df_payment_type = dict_of_df["payment_type"]
-    dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]]
-    return dim_payment_type
diff --git a/src/transform_lambda.py b/src/transform_lambda.py
index defa15d..2cd9272 100644
--- a/src/transform_lambda.py
+++ b/src/transform_lambda.py
@@ -5,7 +5,7 @@ import logging
 import pandas as pd
 import pyarrow as pa
 import pyarrow.parquet as pq
-from src.dataframes import *
+from dataframes import *
 from botocore.exceptions import ClientError
 from pg8000.native import Connection, InterfaceError
 from datetime import datetime
@@ -207,5 +207,10 @@ def list_existing_s3_files(bucket_name, client=boto3.client("s3")):
 
     except ClientError as e:
         logger.error(f"Error listing S3 objects: {e}")
+        raise e
 
     return existing_files
+
+
+if __name__ == "__main__":
+    lambda_handler({}, "")
diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py
index 48426b4..a245379 100644
--- a/tests/test_fact_sales_order.py
+++ b/tests/test_fact_sales_order.py
@@ -1,10 +1,7 @@
+from src.dataframes import *
 import pandas as pd
-from fact_sales_order import create_dim_design, create_dim_staff, create_dim_currency
-from src.fact_sales_order import (
-    create_dim_design,
-    create_dim_staff,
-    create_dim_currency,
-)
+from unittest.mock import patch
+from datetime import datetime as dt
 
 
 class TestCreateDimDesign:
@@ -89,22 +86,161 @@ class TestCreateDimStaff:
         assert result.equals(expected_result)
 
 
-class TestCreateDimCurrency:
-    def test_dim_currency_returns_dataframe(self):
-        d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"]}
-        test_df = {"currency": pd.DataFrame(data=d)}
-        result = create_dim_currency(test_df)
+class TestCreatePaymentType:
+    def test_create_dim_payment_type_returns_correct_columns_and_values(self):
+        d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]}
+        test_df = {"payment_type": pd.DataFrame(data=d)}
+        result = create_dim_payment_type(test_df)
+        expected_columns = ["payment_type_id", "payment_type_name"]
+        expected_d = {
+            "payment_type_id": ["Hello", "Bye"],
+            "payment_type_name": ["Hello", "Bye"],
+        }
+        expected_df = pd.DataFrame(data=expected_d)
         assert isinstance(result, pd.DataFrame)
+        assert list(result.columns) == expected_columns
+        assert result.equals(expected_df)
+
 
+class TestCreateDimCounterparty:
+    def test_create_dim_counterparty_type_returns_correct_columns_and_object(self):
+        data_l = pd.DataFrame(
+            data={
+                "counterparty_id": ["Hello", "Bye"],
+                "counterparty_legal_name": ["Hello", "Bye"],
+                "commercial_contact": ["Hello", "Bye"],
+                "legal_address_id": ["bond street", "regent street"],
+            }
+        )
+        data_a = pd.DataFrame(
+            data={
+                "address_id": ["bond street", "regent street"],
+                "postcode": [98365, 93753],
+            }
+        )
+        test_df = {"address": data_a, "counterparty": data_l}
+        result = create_dim_counterparty(test_df)
+
+        expected_columns = [
+            "counterparty_id",
+            "counterparty_legal_name",
+            "commercial_contact",
+            "counterparty_legal_postcode",
+        ]
+        print(data_l)
+        print(data_a)
+        assert isinstance(result, pd.DataFrame)
+        assert list(result.columns) == expected_columns
+
+
+class TestCreateDimCurrency:
     def test_dim_currency_returns_columns_and_values(self):
-        d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"]}
+        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)}
-        result = create_dim_currency(test_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)
-        expected_result = expected_df.copy()
-        assert result.equals(expected_result)
+        expected_df = pd.DataFrame(data=expected_d).sort_values(
+            by="currency_code", axis=0
+        )
+        assert isinstance(result, pd.DataFrame)
+        assert result.equals(expected_df)
+
+    def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self):
+        result = scrape_currency_names()
+        assert isinstance(result, pd.DataFrame)
+        assert list(result.columns) == ["currency_code", "currency_name"]
+
+
+class TestCreateDimDate:
+    def test_returns_required_columns(self):
+        df_one = pd.DataFrame(
+            data={
+                "updated_date": dt(2020, 5, 17),
+                "created_date": dt(2021, 5, 13),
+                "not_dat": None,
+            },
+            index=[0],
+        )
+        df_two = pd.DataFrame(
+            data={"updated_date": dt(2020, 5, 17), "created_date": dt(2021, 9, 13)},
+            index=[0],
+        )
+        df_three = pd.DataFrame(
+            data={"updated_date": dt(2022, 5, 17), "created_date": dt(2023, 5, 13)},
+            index=[0],
+        )
+        expected_df = pd.DataFrame(
+            data=[
+                [dt(2020, 5, 17), 2020, 5, 17, 6, "Sunday", "May", 2],
+                [dt(2021, 5, 13), 2021, 5, 13, 3, "Thursday", "May", 2],
+                [dt(2021, 9, 13), 2021, 9, 13, 0, "Monday", "September", 3],
+                [dt(2022, 5, 17), 2022, 5, 17, 1, "Tuesday", "May", 2],
+                [dt(2023, 5, 13), 2023, 5, 13, 5, "Saturday", "May", 2],
+            ],
+            columns=[
+                "date_id",
+                "year",
+                "month",
+                "day",
+                "day_of_week",
+                "day_name",
+                "month_name",
+                "quarter",
+            ],
+        )
+        with patch("src.dataframes.create_fact_payment") as mock_fp:
+            with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo:
+                with patch("src.dataframes.create_fact_sales_order") as mock_fso:
+                    mock_fp.return_value = df_one
+                    mock_fpo.return_value = df_two
+                    mock_fso.return_value = df_three
+                    result = create_dim_date({"dum": 0})
+                    result.reset_index(inplace=True, drop=True)
+                    assert result.eq(expected_df, axis="columns").all(axis=None)
+
+
+class TestCreateDimLocation:
+    def test_returns_correct_columns_lo(self):
+        dict_df = {
+            "address": pd.DataFrame(
+                data=[["some_time", "some_other_time", 1, "SE18 9QO"]],
+                columns=["created_at", "last_updated", "address_id", "postal_code"],
+            )
+        }
+        result = create_dim_location(dict_df)
+        assert list(result.columns) == ["location_id", "postal_code"]
+
+
+class TestCreateDimTransaction:
+    def test_returns_correct_columns_tr(self):
+        dict_df = {
+            "transaction": pd.DataFrame(
+                data=[["some_time", "some_other_time", 1, "SE18 9QO"]],
+                columns=[
+                    "created_at",
+                    "last_updated",
+                    "transaction_id",
+                    "some_other_id",
+                ],
+            )
+        }
+        result = create_dim_transaction(dict_df)
+        assert list(result.columns) == ["transaction_id", "some_other_id"]
diff --git a/tests/test_transform_lambda.py b/tests/test_transform_lambda.py
index 37ca08f..5ed743e 100644
--- a/tests/test_transform_lambda.py
+++ b/tests/test_transform_lambda.py
@@ -1,11 +1,23 @@
-from src.transform_lambda import read_from_s3_subfolder_to_df
+from src.transform_lambda import (
+    read_from_s3_subfolder_to_df,
+    list_existing_s3_files,
+    bucket_name,
+)
 from moto import mock_aws
 import pytest
 import pandas as pd
 import os
 import boto3
+from botocore.exceptions import ClientError
 import numpy as np
 
+# import caplog
+import logging
+
+
+logger = logging.getLogger()
+logger.setLevel(logging.INFO)
+
 
 @pytest.fixture(scope="class")
 def aws_credentials():
@@ -23,7 +35,7 @@ def s3_client(aws_credentials):
 
 
 class TestReadFromS3:
-    @pytest.mark.skip(reason="The test is broken!")
+    # @pytest.mark.skip(reason="The test is broken!")
     def test_returns_dictionary_with_correct_value_pair(self, s3_client):
         s3_client.create_bucket(
             Bucket="dummy_buc",
@@ -53,7 +65,7 @@ class TestReadFromS3:
         assert isinstance(result["Foods"], pd.DataFrame)
         assert result["Foods"].eq(expected_df, axis="columns").all(axis=None)
 
-    @pytest.mark.skip(reason="The test is broken!")
+    # @pytest.mark.skip(reason="The test is broken!")
     def test_returns_dictionary_of_dataframes_for_multiple_tables(self, s3_client):
         s3_client.upload_file(
             "tests/dummy_2.csv", "dummy_buc", "Cars/2024/08/21/Cars_14:03:56.csv"
@@ -84,3 +96,46 @@ class TestReadFromS3:
         assert list(result.keys()) == tables
         assert result["Foods"].eq(expected_foods_df, axis="columns").all(axis=None)
         assert result["Cars"].eq(expected_cars_df, axis="columns").all(axis=None)
+
+
+class TestListExistingFiles:
+    def test_functions_receives_error_if_no_bucket(self, s3_client, caplog):
+        caplog.set_level(logging.INFO)
+
+        with pytest.raises(ClientError):
+            list_existing_s3_files("rando_bucket", client=s3_client)
+
+        assert (
+            "Error listing S3 objects: An error occurred (NoSuchBucket) when calling the ListObjectsV2 operation: The specified bucket does not exist"
+            in caplog.text
+        )
+
+    def test_recieves_logger_error_if_no_files_listed(self, s3_client, caplog):
+        caplog.set_level(logging.INFO)
+
+        s3_client.create_bucket(
+            Bucket="mock_bucket",
+            CreateBucketConfiguration={"LocationConstraint": "eu-west-2"},
+        )
+        response = list_existing_s3_files("mock_bucket", client=s3_client)
+        assert "The bucket is empty" in caplog.text
+
+    def test_retrieves_existing_files(self, s3_client, caplog):
+        caplog.set_level(logging.INFO)
+
+        s3_client.upload_file("tests/dummy.txt", "mock_bucket", "dummy.txt")
+        result = list_existing_s3_files("mock_bucket", client=s3_client)
+        assert result == ["dummy.txt"]
+
+
+class TestBucketName:
+    def test_functions_retrieves_bucket(self, s3_client):
+        s3_client.create_bucket(
+            Bucket="mock_bucket",
+            CreateBucketConfiguration={"LocationConstraint": "eu-west-2"},
+        )
+
+        bucket = bucket_name("mock_bucket", s3_client)
+        assert bucket == "mock_bucket"
+
+    # def test_