import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.ensemble import RandomForestRegressor
import joblib

# Load the dataset
url = "https://raw.githubusercontent.com/manishkr1754/CarDekho_Used_Car_Price_Prediction/main/notebooks/data/cardekho_dataset.csv"
df = pd.read_csv(url)

# Preprocessing
num_features = ['vehicle_age', 'km_driven', 'mileage', 'engine', 'max_power', 'seats']
cat_features = ['brand', 'model', 'seller_type', 'fuel_type', 'transmission_type']

# Define the target variable
X = df[num_features + cat_features]
y = df['selling_price']

# Preprocessing pipeline
numeric_transformer = StandardScaler()
onehot_transformer = OneHotEncoder(handle_unknown='ignore')

preprocessor = ColumnTransformer(
    transformers=[
        ('num', numeric_transformer, num_features),
        ('cat', onehot_transformer, cat_features)
    ])

# Create and train the model
model = Pipeline(steps=[
    ('preprocessor', preprocessor),
    ('regressor', RandomForestRegressor(n_estimators=100, random_state=42))
])

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
model.fit(X_train, y_train)

# Save the model
joblib.dump(model, 'random_forest_model.pkl')