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_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_check_inputs():
# Test input checks (shape and type of X and y).
clf = GradientBoostingClassifier(n_estimators=100, random_state=1)
assert_raises(ValueError, clf.fit, X, y + [0, 1])
clf = GradientBoostingClassifier(n_estimators=100, random_state=1)
assert_raises(ValueError,
clf.fit,
X,
y,
sample_weight=([1] * len(y)) + [0, 1])
def test_loss_function():
assert_raises(ValueError, GradientBoostingClassifier(loss='ls').fit, X, y)
assert_raises(ValueError, GradientBoostingClassifier(loss='lad').fit, X, y)
assert_raises(ValueError,
GradientBoostingClassifier(loss='quantile').fit, X, y)
assert_raises(ValueError,
GradientBoostingClassifier(loss='huber').fit, X, y)
assert_raises(ValueError,
GradientBoostingRegressor(loss='deviance').fit, X, y)
assert_raises(ValueError,
GradientBoostingRegressor(loss='exponential').fit, X, y)
def test_check_inputs_predict():
# X has wrong shape
clf = GradientBoostingClassifier(n_estimators=100, random_state=1)
clf.fit(X, y)
x = np.array([1.0, 2.0])[:, np.newaxis]
assert_raises(ValueError, clf.predict, x)
x = np.array([[]])
assert_raises(ValueError, clf.predict, x)
x = np.array([1.0, 2.0, 3.0])[:, np.newaxis]
assert_raises(ValueError, clf.predict, x)
clf = GradientBoostingRegressor(n_estimators=100, random_state=1)
clf.fit(X, rng.rand(len(X)))
x = np.array([1.0, 2.0])[:, np.newaxis]
assert_raises(ValueError, clf.predict, x)
x = np.array([[]])
assert_raises(ValueError, clf.predict, x)
x = np.array([1.0, 2.0, 3.0])[:, np.newaxis]
assert_raises(ValueError, clf.predict, x)
def test_friedman_mse_in_graphviz():
clf = DecisionTreeRegressor(criterion="friedman_mse", random_state=0)
clf.fit(X, y)
dot_data = StringIO()
export_graphviz(clf, out_file=dot_data)
clf = GradientBoostingClassifier(n_estimators=2, random_state=0)
clf.fit(X, y)
for estimator in clf.estimators_:
export_graphviz(estimator[0], out_file=dot_data)
for finding in finditer("\[.*?samples.*?\]", dot_data.getvalue()):
assert_in("friedman_mse", finding.group())
def test_warm_start_wo_nestimators_change():
# Test if warm_start does nothing if n_estimators is not changed.
# Regression test for #3513.
clf = GradientBoostingClassifier(n_estimators=10, warm_start=True)
clf.fit([[0, 1], [2, 3]], [0, 1])
assert_equal(clf.estimators_.shape[0], 10)
clf.fit([[0, 1], [2, 3]], [0, 1])
assert_equal(clf.estimators_.shape[0], 10)
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_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 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)