# Example: Complete Machine Learning Workflow Implementation
# Implementing a simple ML project from start to finish

#!/usr/bin/env python3
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.preprocessing import StandardScaler
import warnings
warnings.filterwarnings('ignore')

class MLWorkflowExample:
    def __init__(self):
        self.data = None
        self.X_train = None
        self.X_test = None
        self.y_train = None
        self.y_test = None
        self.model = None
        self.scaler = StandardScaler()
        
    def generate_sample_data(self, n_samples=1000):
        """Generate sample data for demonstration"""
        np.random.seed(42)
        
        # Generate synthetic housing data
        square_feet = np.random.normal(2000, 500, n_samples)
        bedrooms = np.random.randint(1, 6, n_samples)
        bathrooms = np.random.randint(1, 4, n_samples)
        age = np.random.randint(0, 50, n_samples)
        
        # Generate target variable (house price) with some noise
        base_price = 200000
        price_per_sqft = 100
        price_per_bedroom = 25000
        price_per_bathroom = 15000
        price_per_age = -1000
        
        prices = (base_price + 
                 square_feet * price_per_sqft + 
                 bedrooms * price_per_bedroom + 
                 bathrooms * price_per_bathroom + 
                 age * price_per_age + 
                 np.random.normal(0, 10000, n_samples))
        
        # Create DataFrame
        self.data = pd.DataFrame({
            'square_feet': square_feet,
            'bedrooms': bedrooms,
            'bathrooms': bathrooms,
            'age': age,
            'price': prices
        })
        
        print(f"Generated {n_samples} sample housing records")
        return self.data
    
    def explore_data(self):
        """Perform exploratory data analysis"""
        print("=== Data Exploration ===")
        print(f"Dataset shape: {self.data.shape}")
        print("\nFirst few rows:")
        print(self.data.head())
        
        print("\nData types:")
        print(self.data.dtypes)
        
        print("\nBasic statistics:")
        print(self.data.describe())
        
        print("\nMissing values:")
        print(self.data.isnull().sum())
        
        # Create visualizations
        self._create_visualizations()
        
    def _create_visualizations(self):
        """Create exploratory data visualizations"""
        fig, axes = plt.subplots(2, 2, figsize=(15, 10))
        fig.suptitle('Housing Data Analysis', fontsize=16)
        
        # Price distribution
        axes[0, 0].hist(self.data['price'], bins=30, alpha=0.7, color='skyblue')
        axes[0, 0].set_title('House Price Distribution')
        axes[0, 0].set_xlabel('Price ($)')
        axes[0, 0].set_ylabel('Frequency')
        
        # Square feet vs Price
        axes[0, 1].scatter(self.data['square_feet'], self.data['price'], alpha=0.6)
        axes[0, 1].set_title('Square Feet vs Price')
        axes[0, 1].set_xlabel('Square Feet')
        axes[0, 1].set_ylabel('Price ($)')
        
        # Bedrooms distribution
        axes[1, 0].hist(self.data['bedrooms'], bins=range(1, 7), alpha=0.7, color='lightgreen')
        axes[1, 0].set_title('Bedrooms Distribution')
        axes[1, 0].set_xlabel('Number of Bedrooms')
        axes[1, 0].set_ylabel('Frequency')
        
        # Correlation heatmap
        correlation_matrix = self.data.corr()
        sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', ax=axes[1, 1])
        axes[1, 1].set_title('Feature Correlation Matrix')
        
        plt.tight_layout()
        plt.show()
        
        # Print correlations with price
        print("\nCorrelations with Price:")
        price_correlations = self.data.corr()['price'].sort_values(ascending=False)
        print(price_correlations)
    
    def prepare_data(self):
        """Prepare data for machine learning"""
        print("\n=== Data Preparation ===")
        
        # Separate features and target
        X = self.data.drop('price', axis=1)
        y = self.data['price']
        
        # Split data into training and testing sets
        self.X_train, self.X_test, self.y_train, self.y_test = train_test_split(
            X, y, test_size=0.2, random_state=42
        )
        
        print(f"Training set size: {self.X_train.shape[0]} samples")
        print(f"Testing set size: {self.X_test.shape[0]} samples")
        print(f"Number of features: {self.X_train.shape[1]}")
        
        # Scale features
        self.X_train_scaled = self.scaler.fit_transform(self.X_train)
        self.X_test_scaled = self.scaler.transform(self.X_test)
        
        print("Features scaled using StandardScaler")
        
        return self.X_train_scaled, self.X_test_scaled, self.y_train, self.y_test
    
    def train_model(self):
        """Train a linear regression model"""
        print("\n=== Model Training ===")
        
        # Initialize and train the model
        self.model = LinearRegression()
        self.model.fit(self.X_train_scaled, self.y_train)
        
        print("Linear Regression model trained successfully")
        print(f"Model coefficients: {self.model.coef_}")
        print(f"Model intercept: {self.model.intercept_:.2f}")
        
        # Make predictions
        y_train_pred = self.model.predict(self.X_train_scaled)
        y_test_pred = self.model.predict(self.X_test_scaled)
        
        # Calculate metrics
        train_mse = mean_squared_error(self.y_train, y_train_pred)
        test_mse = mean_squared_error(self.y_test, y_test_pred)
        train_r2 = r2_score(self.y_train, y_train_pred)
        test_r2 = r2_score(self.y_test, y_test_pred)
        
        print("\nModel Performance:")
        print(f"Training MSE: {train_mse:,.2f}")
        print(f"Testing MSE: {test_mse:,.2f}")
        print(f"Training R²: {train_r2:.4f}")
        print(f"Testing R²: {test_r2:.4f}")
        
        return y_train_pred, y_test_pred
    
    def evaluate_model(self, y_train_pred, y_test_pred):
        """Evaluate model performance"""
        print("\n=== Model Evaluation ===")
        
        # Create evaluation visualizations
        fig, axes = plt.subplots(1, 2, figsize=(15, 5))
        
        # Training predictions vs actual
        axes[0].scatter(self.y_train, y_train_pred, alpha=0.6, color='blue')
        axes[0].plot([self.y_train.min(), self.y_train.max()], 
                     [self.y_train.min(), self.y_train.max()], 'r--', lw=2)
        axes[0].set_title('Training: Predicted vs Actual')
        axes[0].set_xlabel('Actual Price ($)')
        axes[0].set_ylabel('Predicted Price ($)')
        
        # Testing predictions vs actual
        axes[1].scatter(self.y_test, y_test_pred, alpha=0.6, color='green')
        axes[1].plot([self.y_test.min(), self.y_test.max()], 
                     [self.y_test.min(), self.y_test.max()], 'r--', lw=2)
        axes[1].set_title('Testing: Predicted vs Actual')
        axes[1].set_xlabel('Actual Price ($)')
        axes[1].set_ylabel('Predicted Price ($)')
        
        plt.tight_layout()
        plt.show()
        
        # Feature importance analysis
        feature_importance = pd.DataFrame({
            'feature': self.data.drop('price', axis=1).columns,
            'coefficient': self.model.coef_
        })
        feature_importance = feature_importance.sort_values('coefficient', key=abs, ascending=False)
        
        print("\nFeature Importance (by absolute coefficient value):")
        print(feature_importance)
        
        # Residual analysis
        residuals = self.y_test - y_test_pred
        
        plt.figure(figsize=(12, 4))
        
        plt.subplot(1, 2, 1)
        plt.scatter(y_test_pred, residuals, alpha=0.6)
        plt.axhline(y=0, color='r', linestyle='--')
        plt.title('Residual Plot')
        plt.xlabel('Predicted Price ($)')
        plt.ylabel('Residuals')
        
        plt.subplot(1, 2, 2)
        plt.hist(residuals, bins=30, alpha=0.7, color='orange')
        plt.title('Residual Distribution')
        plt.xlabel('Residuals')
        plt.ylabel('Frequency')
        
        plt.tight_layout()
        plt.show()
    
    def make_predictions(self, new_data):
        """Make predictions on new data"""
        print("\n=== Making Predictions ===")
        
        # Scale new data
        new_data_scaled = self.scaler.transform(new_data)
        
        # Make predictions
        predictions = self.model.predict(new_data_scaled)
        
        # Create results DataFrame
        results = pd.DataFrame({
            'square_feet': new_data['square_feet'],
            'bedrooms': new_data['bedrooms'],
            'bathrooms': new_data['bathrooms'],
            'age': new_data['age'],
            'predicted_price': predictions
        })
        
        print("Predictions for new data:")
        print(results)
        
        return predictions
    
    def run_complete_workflow(self):
        """Run the complete ML workflow"""
        print("=== Complete Machine Learning Workflow ===")
        print("This example demonstrates a typical ML project from start to finish\n")
        
        # Step 1: Generate data
        print("Step 1: Data Generation")
        self.generate_sample_data()
        
        # Step 2: Explore data
        print("\nStep 2: Data Exploration")
        self.explore_data()
        
        # Step 3: Prepare data
        print("\nStep 3: Data Preparation")
        self.prepare_data()
        
        # Step 4: Train model
        print("\nStep 4: Model Training")
        y_train_pred, y_test_pred = self.train_model()
        
        # Step 5: Evaluate model
        print("\nStep 5: Model Evaluation")
        self.evaluate_model(y_train_pred, y_test_pred)
        
        # Step 6: Make predictions
        print("\nStep 6: Making Predictions")
        new_houses = pd.DataFrame({
            'square_feet': [2500, 1800, 3200],
            'bedrooms': [3, 2, 4],
            'bathrooms': [2, 2, 3],
            'age': [5, 15, 2]
        })
        
        self.make_predictions(new_houses)
        
        print("\n=== Workflow Complete ===")
        print("This demonstrates the complete ML workflow:")
        print("1. Data Generation/Collection")
        print("2. Data Exploration & Analysis")
        print("3. Data Preparation & Preprocessing")
        print("4. Model Training")
        print("5. Model Evaluation")
        print("6. Making Predictions")
        print("\nNext steps would include:")
        print("- Model deployment to production")
        print("- Continuous monitoring and retraining")
        print("- Model versioning and management")

# Example: Simple Classification Problem
class SimpleClassificationExample:
    def __init__(self):
        self.model = None
        
    def generate_classification_data(self):
        """Generate sample data for classification"""
        from sklearn.datasets import make_classification
        from sklearn.model_selection import train_test_split
        
        # Generate synthetic classification data
        X, y = make_classification(
            n_samples=1000,
            n_features=20,
            n_informative=15,
            n_redundant=5,
            n_classes=2,
            random_state=42
        )
        
        # Split data
        X_train, X_test, y_train, y_test = train_test_split(
            X, y, test_size=0.2, random_state=42
        )
        
        return X_train, X_test, y_train, y_test
    
    def train_classification_model(self, X_train, y_train):
        """Train a simple classification model"""
        from sklearn.ensemble import RandomForestClassifier
        from sklearn.metrics import accuracy_score, classification_report
        
        # Train Random Forest classifier
        self.model = RandomForestClassifier(n_estimators=100, random_state=42)
        self.model.fit(X_train, y_train)
        
        return self.model
    
    def evaluate_classification_model(self, X_test, y_test):
        """Evaluate classification model performance"""
        from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
        
        # Make predictions
        y_pred = self.model.predict(X_test)
        
        # Calculate metrics
        accuracy = accuracy_score(y_test, y_pred)
        
        print(f"Classification Accuracy: {accuracy:.4f}")
        print("\nClassification Report:")
        print(classification_report(y_test, y_pred))
        
        # Confusion matrix
        cm = confusion_matrix(y_test, y_pred)
        print("\nConfusion Matrix:")
        print(cm)
        
        return accuracy

# Usage examples
if __name__ == "__main__":
    print("=== AI/ML Module 1: Practical Examples ===\n")
    
    # Example 1: Complete ML Workflow
    print("Example 1: Complete Machine Learning Workflow")
    print("=" * 50)
    ml_workflow = MLWorkflowExample()
    ml_workflow.run_complete_workflow()
    
    print("\n" + "=" * 50)
    
    # Example 2: Simple Classification
    print("Example 2: Simple Classification Problem")
    print("=" * 50)
    classification_example = SimpleClassificationExample()
    X_train, X_test, y_train, y_test = classification_example.generate_classification_data()
    model = classification_example.train_classification_model(X_train, y_train)
    accuracy = classification_example.evaluate_classification_model(X_test, y_test)
    
    print("\nBoth examples demonstrate:")
    print("- Data generation and exploration")
    print("- Data preprocessing and preparation")
    print("- Model training and evaluation")
    print("- Making predictions on new data")
    print("- Complete ML workflow implementation")