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

# Load the data
df = pd.read_csv("Cleaned_Car_data.csv")

# Drop unnecessary columns
df.drop(["Unnamed: 0", "name"], axis=1, inplace=True)

# Feature Engineering
df['car_age'] = 2025 - df['year']
df.drop(['year'], axis=1, inplace=True)

# One-hot encoding
df = pd.get_dummies(df, columns=['company', 'fuel_type'], drop_first=True)

# Define X and y
X = df.drop("Price", axis=1)
y = df["Price"]

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

# Train model
model = LinearRegression()
model.fit(X_train, y_train)

# Evaluation
y_pred = model.predict(X_test)
print("R² Score:", r2_score(y_test, y_pred))

# Save model and columns
with open("car_price_model.pkl", "wb") as f:
    pickle.dump(model, f)

with open("model_columns.pkl", "wb") as f:
    pickle.dump(list(X.columns), f)

print("✅ Model trained and saved successfully.")