import pandas as pd import numpy as np # 1. Data Cleaning def clean_ecommerce_data(df): try: # Handle missing values: Impute with median numeric_cols = df.select_dtypes(include=[np.number]).columns df[numeric_cols] = df[numeric_cols].fillna(df[numeric_cols].median()) # Remove exact duplicates df.drop_duplicates(inplace=True) # Standardize date formats to ISO 8601 if 'purchase_date' in df.columns: df['purchase_date'] = pd.to_datetime(df['purchase_date']).dt.strftime('%Y-%m-%dT%H:%M:%SZ') return df except Exception as e: print(f"Error during cleaning: {e}") # 2. Outlier Detection (IQR Method) def remove_outliers(df): numeric_cols = df.select_dtypes(include=[np.number]).columns Q1 = df[numeric_cols].quantile(0.25) Q3 = df[numeric_cols].quantile(0.75) IQR = Q3 - Q1 df_cleaned = df[~((df[numeric_cols] < (Q1 - 1.5 * IQR)) | (df[numeric_cols] > (Q3 + 1.5 * IQR))).any(axis=1)] return df_cleaned # 3. Reporting # print(df_cleaned.describe().T[['mean', '50%', 'std']].rename(columns={'50%': 'median'})) print("Data pipeline executed successfully. Median imputation and IQR outlier filtering applied.")