import pandas as pd
import numpy as np
import pickle
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.datasets import fetch_california_housing

# Load California Housing Dataset
data = fetch_california_housing()
df = pd.DataFrame(data.data, columns=data.feature_names)
df['PRICE'] = data.target

# Prepare Data
X = df.drop(columns=['PRICE'])
y = df['PRICE']
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)

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

print("✅ Model trained and saved as 'house_price_model.pkl'")