import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
import joblib

# Load Dataset
def load_data(file_path):
    df = pd.read_csv(file_path)
    # Drop unnecessary index column if present
    df = df.loc[:, ~df.columns.str.contains('^Unnamed')]
    return df

# Preprocessing
def preprocess_data(df):
    # Calculate Car Age
    df['Car_Age'] = 2024 - df['Year']
    df.drop(columns=['Year'], inplace=True)

    # Handle missing values
    df['Engine CC'] = df['Engine CC'].fillna(df['Engine CC'].median())
    df['Power'] = df['Power'].fillna(df['Power'].median())
    df['Seats'] = df['Seats'].fillna(df['Seats'].mode()[0])

    # Remove rows with missing target variable
    df = df.dropna(subset=['Mileage Km/L'])

    # Remove outliers in 'Kilometers Driven'
    q1, q3 = df['Kilometers_Driven'].quantile([0.25, 0.75])
    iqr = q3 - q1
    lower_bound = q1 - 1.5 * iqr
    upper_bound = q3 + 1.5 * iqr
    df = df[(df['Kilometers_Driven'] >= lower_bound) & (df['Kilometers_Driven'] <= upper_bound)]

    # Return processed dataframe
    return df

# Train Model
def train_model(df):
    # Features and target
    X = df.drop(columns=['Mileage Km/L', 'Name', 'Price'])
    y = df['Mileage Km/L']

    # Split data
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

    # ColumnTransformer for preprocessing
    categorical_cols = ['Fuel_Type', 'Transmission', 'Owner_Type', 'Location']
    numerical_cols = ['Kilometers_Driven', 'Engine CC', 'Power', 'Seats', 'Car_Age']

    preprocessor = ColumnTransformer(
        transformers=[
            ('num', StandardScaler(), numerical_cols),
            ('cat', OneHotEncoder(drop='first'), categorical_cols)
        ]
    )

    # Random Forest Regressor pipeline
    rf_pipeline = Pipeline([
        ('preprocessor', preprocessor),
        ('regressor', RandomForestRegressor(random_state=42))
    ])

    # Hyperparameter tuning
    param_grid = {
        'regressor__n_estimators': [50, 100, 200],
        'regressor__max_depth': [10, 20, None]
    }

    grid_search = GridSearchCV(rf_pipeline, param_grid, cv=5, scoring='neg_mean_squared_error')
    grid_search.fit(X_train, y_train)

    # Best model
    best_model = grid_search.best_estimator_

    # Test predictions
    y_pred = best_model.predict(X_test)

    # Evaluation
    print("Model Performance:")
    print(f"MAE: {mean_absolute_error(y_test, y_pred):.2f}")
    print(f"RMSE: {mean_squared_error(y_test, y_pred, squared=False):.2f}")
    print(f"R^2: {r2_score(y_test, y_pred):.2f}")

    # Save the model
    joblib.dump(best_model, 'model.pkl')
    print("Model saved as 'model.pkl'")

# Main Function
def main():
    file_path = 'data.csv'  # Update with your dataset file path
    df = load_data(file_path)
    print("Dataset loaded.")

    df = preprocess_data(df)
    print("Data preprocessing complete.")
    print("Model is training...")

    train_model(df)
    print("Model is trained.")

if __name__ == "__main__":
    main()