""" Dataset: E-commerce Sales Data Target Variable: Total_Revenue Algorithm Preference: Random Forest Regressor """ import pandas as pd import numpy as np from sklearn.model_selection import train_test_split from sklearn.ensemble import RandomForestRegressor from sklearn.pipeline import Pipeline from sklearn.preprocessing import StandardScaler from sklearn.metrics import mean_squared_error, r2_score class EcommerceRevenuePipeline: """End-to-end ML pipeline for predicting E-commerce revenue.""" def __init__(self, filepath): self.filepath = filepath self.model = Pipeline([ ('scaler', StandardScaler()), ('rf', RandomForestRegressor(n_estimators=100, random_state=42)) ]) def load_and_clean(self): try: df = pd.read_csv(self.filepath) # Handle missing values robustly df.fillna(df.median(numeric_only=True), inplace=True) return df except FileNotFoundError: print("Error: Dataset file not found. Please check the path.") def feature_engineering(self, df): # Derived feature 1: Average order value df['Avg_Order_Value'] = df['Total_Revenue'] / df['Total_Orders'] # Derived feature 2: Customer tenure in months df['Tenure_Months'] = (pd.to_datetime('today') - pd.to_datetime(df['Signup_Date'])).dt.days / 30 return df def train_evaluate(self, df): X = df.drop(['Total_Revenue', 'Signup_Date'], axis=1) y = df['Total_Revenue'] X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) self.model.fit(X_train, y_train) predictions = self.model.predict(X_test) print(f"RMSE: {np.sqrt(mean_squared_error(y_test, predictions)):.2f}") print(f "R2 Score: {r2_score(y_test, predictions):.2f}")