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



np.random.seed(42)

n_samples = 500

year = np.random.randint(2005, 2024, n_samples)
mileage = np.random.randint(0, 250000, n_samples)

color = np.random.choice(['white', 'black', 'red', 'blue'], n_samples)
transmission = np.random.choice(['manual', 'auto'], n_samples)
fuel = np.random.choice(['petrol', 'gas', 'hybrid'], n_samples)


price = (
    200 + (year - 2005) * 15
    - mileage * 0.0005
    + (transmission == 'auto') * 50
    + (fuel == 'hybrid') * 80
    + np.random.normal(0, 20, n_samples)
)

data = pd.DataFrame({
    "year": year,
    "mileage": mileage,
    "color": color,
    "transmission": transmission,
    "fuel": fuel,
    "price": price
})


data = pd.get_dummies(data, drop_first=True)


X = data.drop("price", axis=1)
y = data["price"]

X_train, X_test, y_train, y_test = train_test_split(
    X, y, train_size=400, random_state=42
)



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


y_pred = model.predict(X_test)

def predict_car_price(model, columns):
    print("Mashina ma'lumotlarini kiriting:")

    year = int(input("Yili: "))
    mileage = int(input("Yurgan km: "))
    color = input("Rangi (white/black/red/blue): ")
    transmission = input("Uzatma (manual/auto): ")
    fuel = input("Yoqilg'i (petrol/gas/hybrid): ")

    data = {
        "year": year,
        "mileage": mileage,
        "color": color,
        "transmission": transmission,
        "fuel": fuel
    }

    df = pd.DataFrame([data])
    df = pd.get_dummies(df)

    df = df.reindex(columns=columns, fill_value=0)

    price = model.predict(df)[0]
    print(f"\nTaxminiy narx: {price:.1f}")

predict_car_price(model, X.columns)



mae  = mean_absolute_error(y_test, y_pred)
mse  = mean_squared_error(y_test, y_pred)
rmse = np.sqrt(mse)
r2   = r2_score(y_test, y_pred)

print("=" * 50)
print("MODEL EVALUATION")
print("=" * 50)
print(f"MAE:  {mae:.2f}")
print(f"RMSE: {rmse:.2f}")
print(f"R²:   {r2:.3f}")


import matplotlib.pyplot as plt

plt.figure(figsize=(6,6))
plt.scatter(y_test, y_pred)
plt.xlabel("Haqiqiy narx")
plt.ylabel("Model aytgan narx")
plt.title("Haqiqiy vs Bashorat")

plt.plot([y_test.min(), y_test.max()],
         [y_test.min(), y_test.max()])

plt.show()


# saqlash
# import pickle

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

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