#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import joblib
import numpy as np

from catboost import CatBoostRegressor
from sklearn.datasets import fetch_california_housing
from sklearn.model_selection import train_test_split

# Set the random seed
random_seed = 0
np.random.seed(random_seed)

# Load the dataset
dataset = fetch_california_housing()
X, y = dataset.data, dataset.target

# Split the dataset into training and testing sets
X_train, _, y_train, _ = train_test_split(X, y, test_size=0.25, random_state=random_seed)

# Create and train model
model = CatBoostRegressor(iterations=100, learning_rate=0.1, depth=6, random_seed=random_seed, verbose=0)
model.fit(X_train, y_train)

# Save the trained model to disk
joblib.dump(model, 'catboost_regressor.joblib')