%autosave 10

from sklearn.ensemble import GradientBoostingClassifier
from sklearn.datasets import make_hastie_10_2

X, y = make_hastie_10_2(n_samples=10000)
est = GradientBoostingClassifier(n_estimators=200, max_depth=3)
est.fit(X, y)

pred = est.predict(X)
est.predict_proba(X)[0]  # class probabilities

for pred in est.staged_predict(X):
    plt.plot(X[:, 0], pred, color='r', alpha=0.1)

# X_test/Y_test, held back data

test_score = np.empty(len(est.estimators_))
for i, pred in enumerate(est.staged_predict(X_test)):
    test_score[i] = est.loss_(y_test, pred)
plt.plot(np.arange(n_estimators) + 1, test_score, label='Test')
plt.plot(np.arange(n_estimators) + 1, est.train_score_, label='Train')