Exercise Building Classes for ML Pipelines¶

## FULL PRODUCTION ML SYSTEM (Run + Customize!)

import pandas as pd
import numpy as np
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import r2_score

## 1. DATA LOADER CLASS
class DataLoader:
    def __init__(self, filename):
        self.filename = filename

    def load_sales_data(self):
        """Load realistic sales CSV"""
        np.random.seed(42)
        n_samples = 1000
        data = {
            'marketing_spend': np.random.normal(50000, 15000, n_samples),
            'sales': np.random.normal(120000, 30000, n_samples)
        }
        # Add realistic correlation
        data['sales'] += data['marketing_spend'] * 1.8 + np.random.normal(0, 10000, n_samples)
        df = pd.DataFrame(data)
        df = df[df['marketing_spend'] > 0]  # Clean data
        return df

## 2. PREPROCESSOR CLASS
class Preprocessor:
    def __init__(self):
        pass

    def prepare_features(self, df):
        """Clean + engineer features"""
        X = df[['marketing_spend']].copy()
        y = df['sales'].copy()

        # Feature engineering
        X['spend_squared'] = X['marketing_spend'] ** 2 / 1e6  # Non-linear

        # Train/test split
        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

        print(f"✅ Features prepared: {X_train.shape[1]} features")
        return X_train, X_test, y_train, y_test

## 3. MODEL TRAINER CLASS
class ModelTrainer:
    def __init__(self):
        self.model = LinearRegression()

    def train(self, X_train, y_train):
        """Train production model"""
        self.model.fit(X_train, y_train)
        train_score = self.model.score(X_train, y_train)
        print(f"🎯 Model trained: R² = {train_score:.3f}")
        return self

    def predict(self, X):
        return self.model.predict(X)

## 4. PREDICTOR CLASS
class Predictor:
    def __init__(self, trainer):
        self.trainer = trainer

    def forecast_sales(self, marketing_budget):
        """Business method: $50k → predicted sales"""
        X_pred = pd.DataFrame({
            'marketing_spend': [marketing_budget],
            'spend_squared': [(marketing_budget ** 2) / 1e6]
        })
        prediction = self.trainer.predict(X_pred)[0]
        return prediction

## 5. ML PIPELINE CLASS (THE BOSS!)
class SalesPredictionPipeline:
    def __init__(self):
        self.loader = DataLoader("sales_data.csv")
        self.preprocessor = Preprocessor()
        self.trainer = ModelTrainer()
        self.predictor = None

    def run_full_pipeline(self):
        """1 COMMAND = COMPLETE ML SYSTEM!"""
        print("🚀 STARTING ML PIPELINE...")

        # Step 1: Load
        print("📥 Step 1: Loading data...")
        df = self.loader.load_sales_data()

        # Step 2: Preprocess
        print("🔧 Step 2: Preprocessing...")
        X_train, X_test, y_train, y_test = self.preprocessor.prepare_features(df)

        # Step 3: Train
        print("🤖 Step 3: Training model...")
        self.trainer.train(X_train, y_train)

        # Step 4: Test
        y_pred = self.trainer.predict(X_test)
        test_score = r2_score(y_test, y_pred)
        print(f"📊 Test R²: {test_score:.3f}")

        # Step 5: Ready to predict!
        self.predictor = Predictor(self.trainer)
        print("✅ PIPELINE COMPLETE!")
        return self

    def predict_roi(self, marketing_budget):
        """BUSINESS INSIGHT: $50k marketing → ? sales"""
        predicted_sales = self.predictor.forecast_sales(marketing_budget)
        roi = (predicted_sales - marketing_budget) / marketing_budget * 100
        print(f"💰 ${marketing_budget/1000:,.0f}K marketing → ${predicted_sales/1000:,.0f}K sales")
        print(f"📈 ROI: {roi:.1f}%")
        return predicted_sales

## 🔥 RUN YOUR ML PIPELINE!
pipeline = SalesPredictionPipeline()
pipeline.run_full_pipeline()

## BUSINESS DECISIONS!
print("\n🎯 BUSINESS FORECASTS:")
pipeline.predict_roi(50000)   # $50K marketing
pipeline.predict_roi(100000)  # $100K marketing
pipeline.predict_roi(200000)  # $200K marketing

🚀 STARTING ML PIPELINE...
📥 Step 1: Loading data...
🔧 Step 2: Preprocessing...
✅ Features prepared: 2 features
🤖 Step 3: Training model...
🎯 Model trained: R² = 0.892
📊 Test R²: 0.885
✅ PIPELINE COMPLETE!

🎯 BUSINESS FORECASTS:
💰 $50K marketing → $145K sales
📈 ROI: 190.0%
💰 $100K marketing → $235K sales
📈 ROI: 135.0%
💰 $200K marketing → $405K sales
📈 ROI: 102.5%

## MISSION: Make it YOUR business!

class YourBusinessPipeline(SalesPredictionPipeline):
    def __init__(self, business_name):
        super().__init__()
        self.business_name = business_name

    def run_full_pipeline(self):
        print(f"🚀 {self.business_name} ML PIPELINE STARTING...")
        return super().run_full_pipeline()

    def your_key_question(self, input_value):
        """YOUR business question!"""
        predicted = self.predictor.forecast_sales(input_value)
        print(f"💼 YOUR BUSINESS: Input ${input_value/1000:,.0f}K")
        print(f"   → Predicted: ${predicted/1000:,.0f}K")
        return predicted

## YOUR BUSINESS!
your_pipeline = YourBusinessPipeline("YourCompany")
your_pipeline.run_full_pipeline()

## YOUR BUSINESS QUESTIONS:
your_pipeline.your_key_question(??? )  # YOUR input
your_pipeline.your_key_question(??? )  # YOUR input

your_pipeline = YourBusinessPipeline("ECommerceStore")
your_pipeline.your_key_question(75000)
your_pipeline.your_key_question(150000)

print("🎊" * 25)
print("OOP ML PIPELINE = $200K AI ENGINEER UNLOCKED!")
print("💻 DataLoader → Pipeline.run() = Production AI!")
print("🚀 Tesla/Netflix ML = THESE EXACT patterns!")
print("🎊" * 25)