INNER CODE UNIT · Python

transform_data

balapriyac/data-science-tutorials · build-with-python/etl-pipeline/main.py:37

def transform_data(df):
    """Transform: Clean and enrich the data"""
    print("Transforming data...")
    
    # Start with a copy to avoid modifying original
    df_clean = df.copy()
    
    # Remove records with missing emails (data quality)
    initial_count = len(df_clean)
    df_clean = df_clean.dropna(subset=['customer_email'])
    removed_count = initial_count - len(df_clean)
    print(f"Removed {removed_count} records with missing emails")
    
    # Calculate derived fields
    df_clean['total_amount'] = df_clean['price'] * df_clean['quantity']
    
    # Extract date components for better analysis
    df_clean['transaction_date'] = pd.to_datetime(df_clean['transaction_date'])

View source record →