update data_loader with the error message and add data_preprocessing.…

…py module for removing missing values

src/data_loader.py

@@ -31,6 +31,6 @@ def load_ecommerce_data(path=None, encoding="ISO-8859-1"):
 
     if data.empty:
         print(f"The file {path} is empty!")
-        raise EmptyDataError(f"No data found in {path}!")
+        raise ValueError("The loaded dataframe is empty.")
 
     return data

src/data_preprocessing.py

@@ -0,0 +1,22 @@
+import pandas as pd
+
+def remove_and_check_missing(df):
+    """
+    Remove rows with missing values in 'CustomerID' and 'Description' columns.
+    Then, check if there are any missing values left in the dataframe.
+    If there are, raise a MissingValueError.
+    """
+
+    # Remove rows with missing values in 'CustomerID' and 'Description'
+    df = df.dropna(subset=['CustomerID', 'Description'])
+
+    # Check if there are any missing values left
+    if df.isna().sum().sum() != 0:
+        missing_count = df.isna().sum().sum()
+        message = f"There are {missing_count} missing values left in the dataframe."
+        print(message)
+        raise ValueError(message)
+
+    return df
+
+