from sklearn.model_selection import KFold

n_splits = 5
kfold = KFold(n_splits=n_splits, random_state=42)

X = np.array(df.drop('MEDV', 1))
Y = np.array(df['MEDV'])

lgbm_fold = LGBMRegressor(random_state=42)
i = 1
total_error = 0

for train_index, test_index in kfold.split(X):
    x_train_fold, x_test_fold = X[train_index], X[test_index]
    y_train_fold, y_test_fold = Y[train_index], Y[test_index]
    lgbm_pred_fold = lgbm_fold.fit(x_train_fold, y_train_fold).predict(x_test_fold)
    error = mean_squared_error(lgbm_pred_fold, y_test_fold)
    print('Fold = {}, prediction score = {:.2f}'.format(i, error))
    total_error += error
    i += 1

print('---'*10)
print('Average Error : %s' % (total_error / n_splits))

'''
출력
Fold = 1, prediction score = 9.00
Fold = 2, prediction score = 15.73
Fold = 3, prediction score = 18.18
Fold = 4, prediction score = 43.95
Fold = 5, prediction score = 24.96
------------------------------
Average Error : 22.36329584390587
'''