def check_classification_synthetic(presort, loss):
# Test GradientBoostingClassifier on synthetic dataset used by
# Hastie et al. in ESLII Example 12.7.
X, y = datasets.make_hastie_10_2(n_samples=12000, random_state=1)
X_train, X_test = X[:2000], X[2000:]
y_train, y_test = y[:2000], y[2000:]
gbrt = GradientBoostingClassifier(n_estimators=100,
min_samples_split=2,
max_depth=1,
loss=loss,
learning_rate=1.0,
random_state=0)
gbrt.fit(X_train, y_train)
error_rate = (1.0 - gbrt.score(X_test, y_test))
assert_less(error_rate, 0.09)
gbrt = GradientBoostingClassifier(n_estimators=200,
min_samples_split=2,
max_depth=1,
loss=loss,
learning_rate=1.0,
subsample=0.5,
random_state=0,
presort=presort)
gbrt.fit(X_train, y_train)
error_rate = (1.0 - gbrt.score(X_test, y_test))
assert_less(error_rate, 0.08)
def test_oob_multilcass_iris():
# Check OOB improvement on multi-class dataset.
clf = GradientBoostingClassifier(n_estimators=100,
loss='deviance',
random_state=1,
subsample=0.5)
clf.fit(iris.data, iris.target)
score = clf.score(iris.data, iris.target)
assert_greater(score, 0.9)
assert_equal(clf.oob_improvement_.shape[0], clf.n_estimators)
def check_iris(presort, subsample, sample_weight):
# Check consistency on dataset iris.
clf = GradientBoostingClassifier(n_estimators=100,
loss='deviance',
random_state=1,
subsample=subsample,
presort=presort)
clf.fit(iris.data, iris.target, sample_weight=sample_weight)
score = clf.score(iris.data, iris.target)
assert_greater(score, 0.9)
leaves = clf.apply(iris.data)
assert_equal(leaves.shape, (150, 100, 3))
def test_zero_estimator_clf():
# Test if ZeroEstimator works for classification.
X = iris.data
y = np.array(iris.target)
est = GradientBoostingClassifier(n_estimators=20,
max_depth=1,
random_state=1,
init=ZeroEstimator())
est.fit(X, y)
assert_greater(est.score(X, y), 0.96)
est = GradientBoostingClassifier(n_estimators=20,
max_depth=1,
random_state=1,
init='zero')
est.fit(X, y)
assert_greater(est.score(X, y), 0.96)
# binary clf
mask = y != 0
y[mask] = 1
y[~mask] = 0
est = GradientBoostingClassifier(n_estimators=20,
max_depth=1,
random_state=1,
init='zero')
est.fit(X, y)
assert_greater(est.score(X, y), 0.96)
est = GradientBoostingClassifier(n_estimators=20,
max_depth=1,
random_state=1,
init='foobar')
assert_raises(ValueError, est.fit, X, y)