passing tests create_dim_design and create_dim_staff

2 files changed, 90 insertions, 0 deletions

diff --git a/src/fact_sales_order.py b/src/fact_sales_order.py
new file mode 100644
index 0000000..870a030
--- /dev/null
+++ b/src/fact_sales_order.py
@@ -0,0 +1,50 @@
+import pandas as pd
+
+
+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
+
+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 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
+
+# repeat ln 52 - 60 for each column
+# merge dataframes into one dataframe
+# remove duplicates
+
+
+
+
+
+# TO DO:
+# complete dim_date
+# fact_sales_order
diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py
new file mode 100644
index 0000000..13196d5
--- /dev/null
+++ b/tests/test_fact_sales_order.py
@@ -0,0 +1,40 @@
+from src.fact_sales_order import create_dim_design, create_dim_staff
+import pandas as pd
+
+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)     
+    
\ No newline at end of file