def test_mem_layout():
# Test with different memory layouts of X and y
X_ = np.asfortranarray(X)
clf = GradientBoostingClassifier(n_estimators=100, random_state=1)
clf.fit(X_, y)
assert_array_equal(clf.predict(T), true_result)
assert_equal(100, len(clf.estimators_))
X_ = np.ascontiguousarray(X)
clf = GradientBoostingClassifier(n_estimators=100, random_state=1)
clf.fit(X_, y)
assert_array_equal(clf.predict(T), true_result)
assert_equal(100, len(clf.estimators_))
y_ = np.asarray(y, dtype=np.int32)
y_ = np.ascontiguousarray(y_)
clf = GradientBoostingClassifier(n_estimators=100, random_state=1)
clf.fit(X, y_)
assert_array_equal(clf.predict(T), true_result)
assert_equal(100, len(clf.estimators_))
y_ = np.asarray(y, dtype=np.int32)
y_ = np.asfortranarray(y_)
clf = GradientBoostingClassifier(n_estimators=100, random_state=1)
clf.fit(X, y_)
assert_array_equal(clf.predict(T), true_result)
assert_equal(100, len(clf.estimators_))
def test_degenerate_targets():
# Check if we can fit even though all targets are equal.
clf = GradientBoostingClassifier(n_estimators=100, random_state=1)
# classifier should raise exception
assert_raises(ValueError, clf.fit, X, np.ones(len(X)))
clf = GradientBoostingRegressor(n_estimators=100, random_state=1)
clf.fit(X, np.ones(len(X)))
clf.predict([rng.rand(2)])
assert_array_equal(np.ones((1, ), dtype=np.float64),
clf.predict([rng.rand(2)]))
def test_staged_predict_proba():
# Test whether staged predict proba eventually gives
# the same prediction.
X, y = datasets.make_hastie_10_2(n_samples=1200, random_state=1)
X_train, y_train = X[:200], y[:200]
X_test, y_test = X[200:], y[200:]
clf = GradientBoostingClassifier(n_estimators=20)
# test raise NotFittedError if not fitted
assert_raises(
NotFittedError,
lambda X: np.fromiter(clf.staged_predict_proba(X), dtype=np.float64),
X_test)
clf.fit(X_train, y_train)
# test if prediction for last stage equals ``predict``
for y_pred in clf.staged_predict(X_test):
assert_equal(y_test.shape, y_pred.shape)
assert_array_equal(clf.predict(X_test), y_pred)
# test if prediction for last stage equals ``predict_proba``
for staged_proba in clf.staged_predict_proba(X_test):
assert_equal(y_test.shape[0], staged_proba.shape[0])
assert_equal(2, staged_proba.shape[1])
assert_array_equal(clf.predict_proba(X_test), staged_proba)
def test_symbol_labels():
# Test with non-integer class labels.
clf = GradientBoostingClassifier(n_estimators=100, random_state=1)
symbol_y = tosequence(map(str, y))
clf.fit(X, symbol_y)
assert_array_equal(clf.predict(T), tosequence(map(str, true_result)))
assert_equal(100, len(clf.estimators_))
def test_serialization():
# Check model serialization.
clf = GradientBoostingClassifier(n_estimators=100, random_state=1)
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
assert_equal(100, len(clf.estimators_))
try:
import cPickle as pickle
except ImportError:
import pickle
serialized_clf = pickle.dumps(clf, protocol=pickle.HIGHEST_PROTOCOL)
clf = None
clf = pickle.loads(serialized_clf)
assert_array_equal(clf.predict(T), true_result)
assert_equal(100, len(clf.estimators_))
def test_non_uniform_weights_toy_edge_case_clf():
X = [[1, 0], [1, 0], [1, 0], [0, 1]]
y = [0, 0, 1, 0]
# ignore the first 2 training samples by setting their weight to 0
sample_weight = [0, 0, 1, 1]
for loss in ('deviance', 'exponential'):
gb = GradientBoostingClassifier(n_estimators=5)
gb.fit(X, y, sample_weight=sample_weight)
assert_array_equal(gb.predict([[1, 0]]), [1])
def test_float_class_labels():
# Test with float class labels.
clf = GradientBoostingClassifier(n_estimators=100, random_state=1)
float_y = np.asarray(y, dtype=np.float32)
clf.fit(X, float_y)
assert_array_equal(clf.predict(T), np.asarray(true_result,
dtype=np.float32))
assert_equal(100, len(clf.estimators_))
def test_shape_y():
# Test with float class labels.
clf = GradientBoostingClassifier(n_estimators=100, random_state=1)
y_ = np.asarray(y, dtype=np.int32)
y_ = y_[:, np.newaxis]
# This will raise a DataConversionWarning that we want to
# "always" raise, elsewhere the warnings gets ignored in the
# later tests, and the tests that check for this warning fail
assert_warns(DataConversionWarning, clf.fit, X, y_)
assert_array_equal(clf.predict(T), true_result)
assert_equal(100, len(clf.estimators_))
def test_probability_log():
# Predict probabilities.
clf = GradientBoostingClassifier(n_estimators=100, random_state=1)
assert_raises(ValueError, clf.predict_proba, T)
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
# check if probabilities are in [0, 1].
y_proba = clf.predict_proba(T)
assert_true(np.all(y_proba >= 0.0))
assert_true(np.all(y_proba <= 1.0))
# derive predictions from probabilities
y_pred = clf.classes_.take(y_proba.argmax(axis=1), axis=0)
assert_array_equal(y_pred, true_result)
def check_classification_toy(presort, loss):
# Check classification on a toy dataset.
clf = GradientBoostingClassifier(loss=loss,
n_estimators=10,
random_state=1,
presort=presort)
assert_raises(ValueError, clf.predict, T)
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
assert_equal(10, len(clf.estimators_))
deviance_decrease = (clf.train_score_[:-1] - clf.train_score_[1:])
assert_true(np.any(deviance_decrease >= 0.0))
leaves = clf.apply(X)
assert_equal(leaves.shape, (6, 10, 1))
def test_probability_exponential():
# Predict probabilities.
clf = GradientBoostingClassifier(loss='exponential',
n_estimators=100,
random_state=1)
assert_raises(ValueError, clf.predict_proba, T)
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
# check if probabilities are in [0, 1].
y_proba = clf.predict_proba(T)
assert_true(np.all(y_proba >= 0.0))
assert_true(np.all(y_proba <= 1.0))
score = clf.decision_function(T).ravel()
assert_array_almost_equal(y_proba[:, 1], 1.0 / (1.0 + np.exp(-2 * score)))
# derive predictions from probabilities
y_pred = clf.classes_.take(y_proba.argmax(axis=1), axis=0)
assert_array_equal(y_pred, true_result)