test: fact transformation function for payment test passes, other fact functions are equivalent, no tests written

3 files changed, 229 insertions, 412 deletions

diff --git a/src/dataframes.py b/src/dataframes.py
index ab53063..41f39b8 100644
--- a/src/dataframes.py
+++ b/src/dataframes.py
@@ -2,7 +2,7 @@ import pandas as pd
 from bs4 import BeautifulSoup
 import requests
 
-# Table names:
+#Table names:
 # fact_sales_order
 # fact_purchase_orders
 # fact_payment
@@ -16,214 +16,133 @@ import requests
 # dim_counterparty
 
 
+#no test, same as fact_payment
 def create_fact_sales_order(dict_of_df):
     df_sales = dict_of_df["sales_order"]
     df_sales.index.name = "sales_record_id"
-    df_sales["created_date"] = pd.to_datetime(df_sales["created_at"]).dt.date
-    df_sales["created_time"] = pd.to_datetime(df_sales["created_at"]).dt.time
-    df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"]).dt.date
-    df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time
-    fact_sales_order = df_sales.loc[
-        :,
-        [
-            "sales_record_id",
-            "sales_order_id",
-            "created_date",
-            "created_time",
-            "last_updated_date",
-            "last_updated_time",
-            "sales_staff_id",
-            "counterparty_id",
-            "units_sold",
-            "unit_price",
-            "currency_id",
-            "design_id",
-            "agreed_payment_date",
-            "agreed_delivery_date",
-            "agreed_delivery_location_id",
-        ],
-    ]
-    return fact_sales_order
-
-
-# fact_purchase_order from purchase_order
-
-
+    df_sales["created_date"] = pd.to_datetime(df_sales["created_at"],format='%Y-%m-%d')
+    df_sales["created_time"] = pd.to_datetime(df_sales["created_at"],format='%H-%M-%S')
+    df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"],format='%Y-%m-%d')
+    df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"],format='%H-%M-%S')
+    df_sales['agreed_delivery_date'] = pd.to_datetime(df_sales['agreed_delivery_date'],format="%Y-%m-%d")
+    df_sales['agreed_payment_date'] = pd.to_datetime(df_sales['agreed_payment_date'],format="%Y-%m-%d")
+    df_sales.drop(labels=['created_at','last_updated'],axis=1,inplace=True)
+    df_sales.reset_index(inplace=True)
+    return df_sales
+
+#no test, same as fact_payment
 def create_fact_purchase_orders(dict_of_df):
-    df_po = dict_of_df["purchase_order"]
-    df_po.index.name = "purchase_record_id"
-    df_po["created_date"] = df_po["created_at"].date()
-    df_po["created_time"] = df_po["created_at"].dt.time
-    df_po["last_updated_date"] = df_po["last_updated_at"].date()
-    df_po["last_updated_time"] = df_po["last_updated_at"].dt.time
-    df_po["agreed_delivery_date"] = pd.to_datetime(
-        df_po["agreed_delivery_date"], format="%Y-%m-%d"
-    )
-    df_po["agreed_payment_date"] = pd.to_datetime(
-        df_po["agreed_payment_date"], format="%Y-%m-%d"
-    )
-    df_po.drop(labels=["created_at", "last_updated_at"], axis=1, inplace=True)
+    df_po = dict_of_df['purchase_order']
+    df_po.index.name = 'purchase_record_id'
+    df_po['created_date'] = pd.to_datetime(df_po['created_at'],format='%Y-%m-%d')
+    df_po['created_time'] = pd.to_datetime(df_po['created_at'],format='%H-%M-%S')
+    df_po['last_updated_date'] = pd.to_datetime(df_po['last_updated'],format='%Y-%m-%d')
+    df_po['last_updated_time'] = pd.to_datetime(df_po['last_updated'],format='%H-%M-%S')
+    df_po['agreed_delivery_date'] = pd.to_datetime(df_po['agreed_delivery_date'],format="%Y-%m-%d")
+    df_po['agreed_payment_date'] = pd.to_datetime(df_po['agreed_payment_date'],format="%Y-%m-%d")
+    df_po.drop(labels=['created_at','last_updated'],axis=1,inplace=True)
+    df_po.reset_index(inplace=True)
     return df_po
 
-
+#test passed
 def create_fact_payment(dict_of_df):
     df_payment = dict_of_df["payment"]
     df_payment.index.name = "payment_record_id"
-    df_payment["created_date"] = df_payment["created_at"].date()
-    df_payment["created_time"] = df_payment["created_at"].time
-    df_payment["last_updated_date"] = df_payment["last_updated"].date()
-    df_payment["last_updated_time"] = df_payment["last_updated"].time
-    df_payment["payment_date"] = pd.to_datetime(
-        df_payment["payment_date"], format="%Y-%m-%d"
-    )
-    fact_payment = df_payment.loc[
-        :,
-        [
-            "payment_record_id",
-            "payment_id",
-            "created_date",
-            "created_time",
-            "last_updated_date",
-            "last_updated_time",
-            "transaction_id",
-            "counterparty_id",
-            "payment_amount",
-            "currency_id",
-            "payment_type_id",
-            "paid",
-            "payment_date",
-        ],
-    ]
-    return fact_payment
-
-
-# test passed
-
-
+    df_payment["created_date"] = pd.to_datetime(df_payment["created_at"],format='%Y-%m-%d')
+    df_payment["created_time"] = pd.to_datetime(df_payment["created_at"],format='%H-%M-%S')
+    df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"],format='%Y-%m-%d')
+    df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"],format='%H-%M-%S')
+    df_payment['payment_date'] = pd.to_datetime(df_payment['payment_date'],format="%Y-%m-%d")
+    df_payment.drop(labels=['created_at','last_updated'],axis=1,inplace=True)
+    df_payment.reset_index(inplace=True)
+    return df_payment
+
+#test passed
 def create_dim_transaction(dict_of_df):
-    df_transaction = dict_of_df["transaction"].drop(
-        labels=["created_at", "last_updated"], axis=1
-    )
+    df_transaction = dict_of_df["transaction"].drop(labels=['created_at', 'last_updated'], axis=1)
     return df_transaction
 
-
-# test passed
+#test passed
 def create_dim_location(dict_of_df):
-    df_loc = (
-        dict_of_df["address"]
-        .drop(labels=["created_at", "last_updated"], axis=1)
-        .rename(columns={"address_id": "location_id"})
-    )
+    df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'})
     return df_loc
 
 
 def create_dim_counterparty(dict_of_df):
-    df_prefixed_address = dict_of_df["address"].add_prefix(
-        "counterparty_legal_", axis=1
-    )
-    df_cp = pd.merge(
-        dict_of_df["counterparty"],
-        df_prefixed_address,
-        left_on="legal_address_id",
-        right_on="counterparty_legal_address_id",
-        how="outer",
-    )
-    df_cp.drop(
-        columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True
-    )
+    df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) 
+    df_cp = pd.merge(dict_of_df['counterparty'], 
+            df_prefixed_address, 
+            left_on="legal_address_id", 
+            right_on="counterparty_legal_address_id", 
+            how="outer")
+    df_cp.drop(columns=["legal_address_id","counterparty_legal_address_id"],inplace=True)
     return df_cp
 
-
-# test passed
-
-
+#test passed
 def create_dim_date(dict_of_df):
-    fact_dfs = [
-        create_fact_payment(dict_of_df),
-        create_fact_purchase_orders(dict_of_df),
-        create_fact_sales_order(dict_of_df),
-    ]
-    date_col_names = [
-        col_name for col_name in list(fact_dfs[0].columns) if "date" in col_name
-    ]
+    fact_dfs = [create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df)]
     list_of_date_columns = []
     for df in fact_dfs:
+        date_col_names = [col_name for col_name in list(df.columns) if 'date' in col_name]
         for col in date_col_names:
             list_of_date_columns.append(df[col])
-    sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]")
-    df_date = pd.DataFrame(data=sr_date, columns=["date_id"])
+    sr_date = pd.array(pd.concat(list_of_date_columns),dtype='datetime64[ns]')
+    df_date = pd.DataFrame(data=sr_date,columns=['date_id'])
     df_date.drop_duplicates(inplace=True)
-    df_date["year"] = df_date["date_id"].dt.year
-    df_date["month"] = df_date["date_id"].dt.month
-    df_date["day"] = df_date["date_id"].dt.day
-    df_date["day_of_week"] = df_date["date_id"].dt.dayofweek
-    df_date["day_name"] = df_date["date_id"].dt.day_name()
-    df_date["month_name"] = df_date["date_id"].dt.month_name()
-    df_date["quarter"] = df_date["date_id"].dt.quarter
+    df_date['year'] = df_date['date_id'].dt.year
+    df_date['month'] = df_date['date_id'].dt.month
+    df_date['day'] = df_date['date_id'].dt.day
+    df_date['day_of_week'] = df_date['date_id'].dt.dayofweek
+    df_date['day_name'] = df_date['date_id'].dt.day_name()
+    df_date['month_name'] = df_date['date_id'].dt.month_name()
+    df_date['quarter'] = df_date['date_id'].dt.quarter 
     return df_date
 
-
-# tests passed
+#tests passed
 def scrape_currency_names():
-    response = requests.get("https://www.xe.com/currency/").content
-    soup = BeautifulSoup(response, "html.parser")
-    currency = [
-        item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"})
-    ]
+    response = requests.get('https://www.xe.com/currency/').content
+    soup = BeautifulSoup(response,'html.parser')
+    currency = [item.text for item in soup.findAll('a', attrs={'class' : "sc-299dec64-6 fZPTSw"})]
     sr = pd.Series(currency)
-    df_cur = sr.str.split(pat=" - ", expand=True).rename(
-        {0: "currency_code", 1: "currency_name"}, axis=1
-    )
+    df_cur = sr.str.split(pat=" - ",expand=True).rename({0:'currency_code',1:'currency_name'},axis=1)
     return df_cur
 
+#tests passed
+def create_dim_currency(dict_of_df,names=scrape_currency_names()):
+    df_cur = dict_of_df['currency'].drop(labels=['created_at', 'last_updated'], axis=1)
+    dim_cur = pd.merge(df_cur,names,left_on='currency_code',right_on='currency_code',how='inner')
+    return dim_cur
+
+#tests passed
+def create_dim_payment_type(dict_of_df):
+    df_payment_type = dict_of_df["payment_type"]
+    dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]]
+    return dim_payment_type
+
+#tests passed
+def create_dim_design(dict_of_df):
+    df_design = dict_of_df["design"]
+    dim_design = df_design.loc[:, ["design_id", "design_name", "file_name", "file_location"]]
+    return dim_design
+#tests passed
+def create_dim_staff(dict_of_df):
+    staff_department = pd.merge(dict_of_df["staff"], dict_of_df["department"], on='department_id', how="left")
+    dim_staff = staff_department.loc[:, ['staff_id', 'first_name', 'last_name', 'department_name', 'location', 'email_address']]
+    return dim_staff
+
+
 
-# tests passed
 
 
-def create_dim_currency(dict_of_df, names=scrape_currency_names()):
-    df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1)
-    dim_cur = pd.merge(
-        df_cur, names, left_on="currency_code", right_on="currency_code", how="inner"
-    )
-    return dim_cur
 
 
-# tests passed
 
 
-def create_dim_payment_type(dict_of_df):
-    df_payment_type = dict_of_df["payment_type"]
-    dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]]
-    return dim_payment_type
 
 
-# tests passed
 
 
-def create_dim_design(dict_of_df):
-    df_design = dict_of_df["design"]
-    dim_design = df_design.loc[
-        :, ["design_id", "design_name", "file_name", "file_location"]
-    ]
-    return dim_design
 
 
-# tests passed
 
 
-def create_dim_staff(dict_of_df):
-    staff_department = pd.merge(
-        dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left"
-    )
-    dim_staff = staff_department.loc[
-        :,
-        [
-            "staff_id",
-            "first_name",
-            "last_name",
-            "department_name",
-            "location",
-            "email_address",
-        ],
-    ]
-    return dim_staff
diff --git a/tests/test_dataframes.py b/tests/test_dataframes.py
new file mode 100644
index 0000000..8f32b1d
--- /dev/null
+++ b/tests/test_dataframes.py
@@ -0,0 +1,144 @@
+from src.dataframes import *
+import pandas as pd
+from unittest.mock import patch
+from datetime import datetime as dt
+
+class TestCreateDimDesign:
+    def test_dim_design_returns_dataframe(self):
+        d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], 
+                "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]}
+        test_df = {"design": pd.DataFrame(data=d)}
+        result = create_dim_design(test_df)
+        assert isinstance(result, pd.DataFrame)
+
+    def test_dim_design_returns_correct_columns_and_values(self):
+        d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], 
+                "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]}
+        test_df = {"design": pd.DataFrame(data=d)}
+        result = create_dim_design(test_df)
+        d2 = {"design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], "file_name": ["Hello", "Bye"], 
+            "file_location": ["Hello", "Bye"]}
+        expected_df = pd.DataFrame(data=d2)
+        expected_result = expected_df.copy()
+        assert result.equals(expected_result)
+
+class TestCreateDimStaff:
+    def test_dim_staff_returns_dataframe(self):
+        d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]}
+        d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]}
+        test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)}
+        result = create_dim_staff(test_df)
+        assert isinstance(result, pd.DataFrame)  
+
+    def test_dim_staff_returns_correct_columns_and_values(self):
+        d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]}
+        d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]}
+        test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)}
+        result = create_dim_staff(test_df)
+        expected_d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"]}
+        expected_df = pd.DataFrame(data=expected_d)
+        expected_result = expected_df.copy()
+        assert result.equals(expected_result)  
+
+class TestCreatePaymentType:
+    def test_create_dim_payment_type_returns_correct_columns_and_values(self):
+        d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]}
+        test_df = {"payment_type": pd.DataFrame(data=d)}
+        result = create_dim_payment_type(test_df)
+        expected_columns = ["payment_type_id", "payment_type_name"]
+        expected_d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]}
+        expected_df = pd.DataFrame(data=expected_d)
+        assert isinstance(result, pd.DataFrame)
+        assert list(result.columns) == expected_columns
+        assert result.equals(expected_df)
+
+class TestCreateDimCounterparty:
+    
+    def test_create_dim_counterparty_type_returns_correct_columns_and_object(self):
+        data_l = pd.DataFrame(data={"counterparty_id": ["Hello", "Bye"], 
+             "counterparty_legal_name": ["Hello", "Bye"], 
+             "commercial_contact": ["Hello", "Bye"], 
+             "legal_address_id": ["bond street", "regent street"]})
+        data_a = pd.DataFrame(data={"address_id":["bond street", "regent street"],
+                  "postcode":[98365,93753]})
+        test_df = {"address": data_a,"counterparty":data_l}
+        result = create_dim_counterparty(test_df)
+
+        expected_columns = ["counterparty_id", "counterparty_legal_name", 
+                            "commercial_contact", "counterparty_legal_postcode"]
+        print(data_l)
+        print(data_a)
+        assert isinstance(result, pd.DataFrame)
+        assert list(result.columns) == expected_columns
+
+class TestCreateDimCurrency:
+    
+    def test_dim_currency_returns_columns_and_values(self):
+        nones = [None,None,None]
+        d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"],"created_at":nones,"last_updated":nones}
+        test_df = {"currency": pd.DataFrame(data=d)}
+        scraper_output = pd.DataFrame({"currency_code":["RUS","USD","PHP","GBP","EUR"],"currency_name":["Rubble","US Dollar","Peso","Pound","Euro"]})
+        result = create_dim_currency(test_df,names=scraper_output).sort_values(by="currency_code",axis=0)
+        expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]}
+        expected_df = pd.DataFrame(data=expected_d).sort_values(by="currency_code",axis=0)
+        assert isinstance(result, pd.DataFrame) 
+        assert result.equals(expected_df)  
+
+    def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self):
+        result = scrape_currency_names()
+        assert isinstance(result,pd.DataFrame)
+        assert list(result.columns) == ['currency_code', 'currency_name']
+
+class TestCreateDimDate:
+
+    def test_returns_required_columns(self):
+        df_one = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 5, 13),'not_dat':None},index=[0])
+        df_two = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 9, 13)},index=[0])
+        df_three = pd.DataFrame(data={'updated_date':dt(2022, 5, 17),'created_date':dt(2023, 5, 13)},index=[0])
+        expected_df = pd.DataFrame(data=
+                        [[dt(2020,5,17),2020,5,17,6,'Sunday','May',2],
+                        [dt(2021,5,13),2021,5,13,3,'Thursday','May',2],
+                        [dt(2021,9,13),2021,9,13,0,'Monday','September',3],
+                        [dt(2022,5,17),2022,5,17,1,'Tuesday','May',2],
+                        [dt(2023,5,13),2023,5,13,5,'Saturday','May',2]],
+                        columns=['date_id','year','month','day','day_of_week','day_name','month_name','quarter'])
+        with patch("src.dataframes.create_fact_payment") as mock_fp:
+            with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo:
+                with patch("src.dataframes.create_fact_sales_order") as mock_fso:
+                    mock_fp.return_value = df_one
+                    mock_fpo.return_value = df_two
+                    mock_fso.return_value = df_three
+                    result = create_dim_date({'dum':0})
+                    result.reset_index(inplace=True,drop=True)
+                    assert result.eq(expected_df, axis="columns").all(axis=None)
+        
+class TestCreateDimLocation:
+
+    def test_returns_correct_columns_lo(self):
+        dict_df = {'address':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']],
+                                          columns=['created_at','last_updated','address_id','postal_code'])}        
+        result = create_dim_location(dict_df)
+        assert list(result.columns) == ['location_id','postal_code']
+    
+class TestCreateDimTransaction:
+     def test_returns_correct_columns_tr(self):
+        dict_df = {'transaction':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']],
+                                          columns=['created_at','last_updated','transaction_id','some_other_id'])}        
+        result = create_dim_transaction(dict_df)
+        assert list(result.columns) == ['transaction_id','some_other_id']
+
+class TestCreateFactPayment:
+    def test_returns_correct_columns_payment(self):
+        dict_df = {'payment':pd.DataFrame(data=[[dt(2020,5,17,6,15,20),dt(2020,5,20,8,19,30),1,'SE18 9QO','2020-7-16']],
+                                          columns=['created_at','last_updated','payment_id','some_other_id','payment_date'])}        
+        expected_cols = ['payment_record_id','created_date','created_time','last_updated_date',
+                                        'last_updated_time','payment_date','payment_id','some_other_id']
+        result = create_fact_payment(dict_df)
+        assert isinstance(result,pd.DataFrame)
+        for col in list(result.columns):
+            assert col in expected_cols
+        for col in expected_cols:
+            if 'date' in col:
+                assert result[col].dtype == 'datetime64[ns]'
+            
+       
\ No newline at end of file
diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py
deleted file mode 100644
index a245379..0000000
--- a/tests/test_fact_sales_order.py
+++ /dev/null
@@ -1,246 +0,0 @@
-from src.dataframes import *
-import pandas as pd
-from unittest.mock import patch
-from datetime import datetime as dt
-
-
-class TestCreateDimDesign:
-    def test_dim_design_returns_dataframe(self):
-        d = {
-            "test": ["Hello", "Bye"],
-            "design_id": ["Hello", "Bye"],
-            "design_name": ["Hello", "Bye"],
-            "file_name": ["Hello", "Bye"],
-            "file_location": ["Hello", "Bye"],
-            "Hello": ["Hello", "Bye"],
-        }
-        test_df = {"design": pd.DataFrame(data=d)}
-        result = create_dim_design(test_df)
-        assert isinstance(result, pd.DataFrame)
-
-    def test_dim_design_returns_correct_columns_and_values(self):
-        d = {
-            "test": ["Hello", "Bye"],
-            "design_id": ["Hello", "Bye"],
-            "design_name": ["Hello", "Bye"],
-            "file_name": ["Hello", "Bye"],
-            "file_location": ["Hello", "Bye"],
-            "Hello": ["Hello", "Bye"],
-        }
-        test_df = {"design": pd.DataFrame(data=d)}
-        result = create_dim_design(test_df)
-        d2 = {
-            "design_id": ["Hello", "Bye"],
-            "design_name": ["Hello", "Bye"],
-            "file_name": ["Hello", "Bye"],
-            "file_location": ["Hello", "Bye"],
-        }
-        expected_df = pd.DataFrame(data=d2)
-        expected_result = expected_df.copy()
-        assert result.equals(expected_result)
-
-
-class TestCreateDimStaff:
-    def test_dim_staff_returns_dataframe(self):
-        d = {
-            "staff_id": ["Hello", "Bye"],
-            "first_name": ["Hello", "Bye"],
-            "last_name": ["Hello", "Bye"],
-            "department_id": ["Hello", "Bye"],
-        }
-        d2 = {
-            "department_name": ["Hello", "Bye"],
-            "location": ["Hello", "Bye"],
-            "email_address": ["Hello", "Bye"],
-            "department_id": ["Hello", "Bye"],
-        }
-        test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)}
-        result = create_dim_staff(test_df)
-        assert isinstance(result, pd.DataFrame)
-
-    def test_dim_staff_returns_correct_columns_and_values(self):
-        d = {
-            "staff_id": ["Hello", "Bye"],
-            "first_name": ["Hello", "Bye"],
-            "last_name": ["Hello", "Bye"],
-            "department_id": ["Hello", "Bye"],
-        }
-        d2 = {
-            "department_name": ["Hello", "Bye"],
-            "location": ["Hello", "Bye"],
-            "email_address": ["Hello", "Bye"],
-            "department_id": ["Hello", "Bye"],
-        }
-        test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)}
-        result = create_dim_staff(test_df)
-        expected_d = {
-            "staff_id": ["Hello", "Bye"],
-            "first_name": ["Hello", "Bye"],
-            "last_name": ["Hello", "Bye"],
-            "department_name": ["Hello", "Bye"],
-            "location": ["Hello", "Bye"],
-            "email_address": ["Hello", "Bye"],
-        }
-        expected_df = pd.DataFrame(data=expected_d)
-        expected_result = expected_df.copy()
-        assert result.equals(expected_result)
-
-
-class TestCreatePaymentType:
-    def test_create_dim_payment_type_returns_correct_columns_and_values(self):
-        d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]}
-        test_df = {"payment_type": pd.DataFrame(data=d)}
-        result = create_dim_payment_type(test_df)
-        expected_columns = ["payment_type_id", "payment_type_name"]
-        expected_d = {
-            "payment_type_id": ["Hello", "Bye"],
-            "payment_type_name": ["Hello", "Bye"],
-        }
-        expected_df = pd.DataFrame(data=expected_d)
-        assert isinstance(result, pd.DataFrame)
-        assert list(result.columns) == expected_columns
-        assert result.equals(expected_df)
-
-
-class TestCreateDimCounterparty:
-    def test_create_dim_counterparty_type_returns_correct_columns_and_object(self):
-        data_l = pd.DataFrame(
-            data={
-                "counterparty_id": ["Hello", "Bye"],
-                "counterparty_legal_name": ["Hello", "Bye"],
-                "commercial_contact": ["Hello", "Bye"],
-                "legal_address_id": ["bond street", "regent street"],
-            }
-        )
-        data_a = pd.DataFrame(
-            data={
-                "address_id": ["bond street", "regent street"],
-                "postcode": [98365, 93753],
-            }
-        )
-        test_df = {"address": data_a, "counterparty": data_l}
-        result = create_dim_counterparty(test_df)
-
-        expected_columns = [
-            "counterparty_id",
-            "counterparty_legal_name",
-            "commercial_contact",
-            "counterparty_legal_postcode",
-        ]
-        print(data_l)
-        print(data_a)
-        assert isinstance(result, pd.DataFrame)
-        assert list(result.columns) == expected_columns
-
-
-class TestCreateDimCurrency:
-    def test_dim_currency_returns_columns_and_values(self):
-        nones = [None, None, None]
-        d = {
-            "currency_id": [1, 2, 3],
-            "currency_code": ["USD", "EUR", "GBP"],
-            "created_at": nones,
-            "last_updated": nones,
-        }
-        test_df = {"currency": pd.DataFrame(data=d)}
-        scraper_output = pd.DataFrame(
-            {
-                "currency_code": ["RUS", "USD", "PHP", "GBP", "EUR"],
-                "currency_name": ["Rubble", "US Dollar", "Peso", "Pound", "Euro"],
-            }
-        )
-        result = create_dim_currency(test_df, names=scraper_output).sort_values(
-            by="currency_code", axis=0
-        )
-        expected_d = {
-            "currency_id": [1, 2, 3],
-            "currency_code": ["USD", "EUR", "GBP"],
-            "currency_name": ["US Dollar", "Euro", "Pound"],
-        }
-        expected_df = pd.DataFrame(data=expected_d).sort_values(
-            by="currency_code", axis=0
-        )
-        assert isinstance(result, pd.DataFrame)
-        assert result.equals(expected_df)
-
-    def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self):
-        result = scrape_currency_names()
-        assert isinstance(result, pd.DataFrame)
-        assert list(result.columns) == ["currency_code", "currency_name"]
-
-
-class TestCreateDimDate:
-    def test_returns_required_columns(self):
-        df_one = pd.DataFrame(
-            data={
-                "updated_date": dt(2020, 5, 17),
-                "created_date": dt(2021, 5, 13),
-                "not_dat": None,
-            },
-            index=[0],
-        )
-        df_two = pd.DataFrame(
-            data={"updated_date": dt(2020, 5, 17), "created_date": dt(2021, 9, 13)},
-            index=[0],
-        )
-        df_three = pd.DataFrame(
-            data={"updated_date": dt(2022, 5, 17), "created_date": dt(2023, 5, 13)},
-            index=[0],
-        )
-        expected_df = pd.DataFrame(
-            data=[
-                [dt(2020, 5, 17), 2020, 5, 17, 6, "Sunday", "May", 2],
-                [dt(2021, 5, 13), 2021, 5, 13, 3, "Thursday", "May", 2],
-                [dt(2021, 9, 13), 2021, 9, 13, 0, "Monday", "September", 3],
-                [dt(2022, 5, 17), 2022, 5, 17, 1, "Tuesday", "May", 2],
-                [dt(2023, 5, 13), 2023, 5, 13, 5, "Saturday", "May", 2],
-            ],
-            columns=[
-                "date_id",
-                "year",
-                "month",
-                "day",
-                "day_of_week",
-                "day_name",
-                "month_name",
-                "quarter",
-            ],
-        )
-        with patch("src.dataframes.create_fact_payment") as mock_fp:
-            with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo:
-                with patch("src.dataframes.create_fact_sales_order") as mock_fso:
-                    mock_fp.return_value = df_one
-                    mock_fpo.return_value = df_two
-                    mock_fso.return_value = df_three
-                    result = create_dim_date({"dum": 0})
-                    result.reset_index(inplace=True, drop=True)
-                    assert result.eq(expected_df, axis="columns").all(axis=None)
-
-
-class TestCreateDimLocation:
-    def test_returns_correct_columns_lo(self):
-        dict_df = {
-            "address": pd.DataFrame(
-                data=[["some_time", "some_other_time", 1, "SE18 9QO"]],
-                columns=["created_at", "last_updated", "address_id", "postal_code"],
-            )
-        }
-        result = create_dim_location(dict_df)
-        assert list(result.columns) == ["location_id", "postal_code"]
-
-
-class TestCreateDimTransaction:
-    def test_returns_correct_columns_tr(self):
-        dict_df = {
-            "transaction": pd.DataFrame(
-                data=[["some_time", "some_other_time", 1, "SE18 9QO"]],
-                columns=[
-                    "created_at",
-                    "last_updated",
-                    "transaction_id",
-                    "some_other_id",
-                ],
-            )
-        }
-        result = create_dim_transaction(dict_df)
-        assert list(result.columns) == ["transaction_id", "some_other_id"]