%matplotlib inline 

import matplotlib as mlp
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import sklearn
from sklearn import cross_validation
from sklearn import datasets
from sklearn import ensemble
from sklearn import grid_search
from sklearn import metrics
import time

plt.style.use('fivethirtyeight')

california_housing = datasets.california_housing.fetch_california_housing()
california_housing_data = california_housing['data']
california_housing_labels = california_housing['target']# 'target' variables
california_housing_feature_names = california_housing['feature_names']

X_train, X_test, y_train, y_test = cross_validation.train_test_split(california_housing_data,
                                                    california_housing_labels,
                                                    test_size=0.2,
                                                    random_state=0)

param_grid = {
              'learning_rate': [0.1, 0.05, 0.01],
              'max_depth': [4, 6],
              'min_samples_leaf': [3, 9, 15],
              'n_estimators': [1000, 2000, 3000],
              }

est = ensemble.GradientBoostingRegressor()

start_time = time.time()
gs_cv = grid_search.GridSearchCV(est, param_grid, n_jobs=4).fit(X_train, y_train)
end_time = time.time()

print('It took {} seconds'.format(end_time - start_time))
# best hyperparameter setting
gs_cv.best_params_

gs_cv.grid_scores_