# I'm getting a good 0.83 without much tunning of the parameters so it's a good out of the box technique.
mse = mean_squared_error(y_test, clf.predict(x_test))
r2 = r2_score(y_test, clf.predict(x_test))
print("MSE: %.4f" % mse)
print("R2: %.4f" % r2)
# Let's plot how does it behave the training and testing error
import matplotlib.pyplot as plt
# compute test set deviance
test_score = np.zeros((params['n_estimators'], ), dtype=np.float64)
for i, y_pred in enumerate(clf._staged_decision_function(x_test)):
test_score[i] = clf.loss_(y_test, y_pred)
plt.figure(figsize=(12, 6))
plt.subplot(1, 1, 1)
plt.title('Deviance')
plt.plot(np.arange(params['n_estimators']) + 1,
clf.train_score_,
'b-',
label='Training Set Deviance')
plt.plot(np.arange(params['n_estimators']) + 1,
test_score,
'r-',
label='Test Set Deviance')
plt.legend(loc='upper right')
plt.xlabel('Boosting Iterations')
