def test_oob_improvement_raise():
# Test if oob improvement has correct shape.
clf = GradientBoostingClassifier(n_estimators=100,
random_state=1,
subsample=1.0)
clf.fit(X, y)
assert_raises(AttributeError, lambda: clf.oob_improvement_)
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_verbose_output():
# Check verbose=1 does not cause error.
from sklearn.externals.six.moves import cStringIO as StringIO
import sys
old_stdout = sys.stdout
sys.stdout = StringIO()
clf = GradientBoostingClassifier(n_estimators=100,
random_state=1,
verbose=1,
subsample=0.8)
clf.fit(X, y)
verbose_output = sys.stdout
sys.stdout = old_stdout
# check output
verbose_output.seek(0)
header = verbose_output.readline().rstrip()
# with OOB
true_header = ' '.join(['%10s'] + ['%16s'] * 3) % (
'Iter', 'Train Loss', 'OOB Improve', 'Remaining Time')
assert_equal(true_header, header)
n_lines = sum(1 for l in verbose_output.readlines())
# one for 1-10 and then 9 for 20-100
assert_equal(10 + 9, n_lines)
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_plot_partial_dependence_input():
# Test partial dependence plot function input checks.
clf = GradientBoostingClassifier(n_estimators=10, random_state=1)
# not fitted yet
assert_raises(ValueError, plot_partial_dependence, clf, X, [0])
clf.fit(X, y)
assert_raises(ValueError, plot_partial_dependence, clf,
np.array(X)[:, :0], [0])
# first argument must be an instance of BaseGradientBoosting
assert_raises(ValueError, plot_partial_dependence, {}, X, [0])
# must be larger than -1
assert_raises(ValueError, plot_partial_dependence, clf, X, [-1])
# too large feature value
assert_raises(ValueError, plot_partial_dependence, clf, X, [100])
# str feature but no feature_names
assert_raises(ValueError, plot_partial_dependence, clf, X, ['foobar'])
# not valid features value
assert_raises(ValueError, plot_partial_dependence, clf, X, [{
'foo': 'bar'
}])
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_partial_dependecy_input():
# Test input validation of partial dependence.
clf = GradientBoostingClassifier(n_estimators=10, random_state=1)
clf.fit(X, y)
assert_raises(ValueError, partial_dependence, clf, [0], grid=None, X=None)
assert_raises(ValueError, partial_dependence, clf, [0], grid=[0, 1], X=X)
# first argument must be an instance of BaseGradientBoosting
assert_raises(ValueError, partial_dependence, {}, [0], X=X)
# Gradient boosting estimator must be fit
assert_raises(ValueError,
partial_dependence,
GradientBoostingClassifier(), [0],
X=X)
assert_raises(ValueError, partial_dependence, clf, [-1], X=X)
assert_raises(ValueError, partial_dependence, clf, [100], X=X)
# wrong ndim for grid
grid = np.random.rand(10, 2, 1)
assert_raises(ValueError, partial_dependence, clf, [0], grid=grid)
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 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_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_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 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_oob_improvement():
# Test if oob improvement has correct shape and regression test.
clf = GradientBoostingClassifier(n_estimators=100,
random_state=1,
subsample=0.5)
clf.fit(X, y)
assert_equal(clf.oob_improvement_.shape[0], 100)
# hard-coded regression test - change if modification in OOB computation
assert_array_almost_equal(clf.oob_improvement_[:5],
np.array([0.19, 0.15, 0.12, -0.12, -0.11]),
decimal=2)
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 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_partial_dependence_multiclass():
# Test partial dependence for multi-class classifier
clf = GradientBoostingClassifier(n_estimators=10, random_state=1)
clf.fit(iris.data, iris.target)
grid_resolution = 25
n_classes = clf.n_classes_
pdp, axes = partial_dependence(clf, [0],
X=iris.data,
grid_resolution=grid_resolution)
assert pdp.shape == (n_classes, grid_resolution)
assert len(axes) == 1
assert axes[0].shape[0] == grid_resolution
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_complete_classification():
# Test greedy trees with max_depth + 1 leafs.
from sklearn.tree._tree import TREE_LEAF
X, y = datasets.make_hastie_10_2(n_samples=100, random_state=1)
k = 4
est = GradientBoostingClassifier(n_estimators=20,
max_depth=None,
random_state=1,
max_leaf_nodes=k + 1)
est.fit(X, y)
tree = est.estimators_[0, 0].tree_
assert_equal(tree.max_depth, k)
assert_equal(tree.children_left[tree.children_left == TREE_LEAF].shape[0],
k + 1)
def test_max_feature_regression():
# Test to make sure random state is set properly.
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=5,
max_depth=2,
learning_rate=.1,
max_features=2,
random_state=1)
gbrt.fit(X_train, y_train)
deviance = gbrt.loss_(y_test, gbrt.decision_function(X_test))
assert_true(deviance < 0.5, "GB failed with deviance %.4f" % deviance)
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_partial_dependence_classifier():
# Test partial dependence for classifier
clf = GradientBoostingClassifier(n_estimators=10, random_state=1)
clf.fit(X, y)
pdp, axes = partial_dependence(clf, [0], X=X, grid_resolution=5)
# only 4 grid points instead of 5 because only 4 unique X[:,0] vals
assert pdp.shape == (1, 4)
assert axes[0].shape[0] == 4
# now with our own grid
X_ = np.asarray(X)
grid = np.unique(X_[:, 0])
pdp_2, axes = partial_dependence(clf, [0], grid=grid)
assert axes is None
assert_array_equal(pdp, pdp_2)
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 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)
def test_plot_partial_dependence_multiclass():
# Test partial dependence plot function on multi-class input.
clf = GradientBoostingClassifier(n_estimators=10, random_state=1)
clf.fit(iris.data, iris.target)
grid_resolution = 25
fig, axs = plot_partial_dependence(clf,
iris.data, [0, 1],
label=0,
grid_resolution=grid_resolution)
assert len(axs) == 2
assert all(ax.has_data for ax in axs)
# now with symbol labels
target = iris.target_names[iris.target]
clf = GradientBoostingClassifier(n_estimators=10, random_state=1)
clf.fit(iris.data, target)
grid_resolution = 25
fig, axs = plot_partial_dependence(clf,
iris.data, [0, 1],
label='setosa',
grid_resolution=grid_resolution)
assert len(axs) == 2
assert all(ax.has_data for ax in axs)
# label not in gbrt.classes_
assert_raises(ValueError,
plot_partial_dependence,
clf,
iris.data, [0, 1],
label='foobar',
grid_resolution=grid_resolution)
# label not provided
assert_raises(ValueError,
plot_partial_dependence,
clf,
iris.data, [0, 1],
grid_resolution=grid_resolution)
def test_more_verbose_output():
# Check verbose=2 does not cause error.
from sklearn.externals.six.moves import cStringIO as StringIO
import sys
old_stdout = sys.stdout
sys.stdout = StringIO()
clf = GradientBoostingClassifier(n_estimators=100,
random_state=1,
verbose=2)
clf.fit(X, y)
verbose_output = sys.stdout
sys.stdout = old_stdout
# check output
verbose_output.seek(0)
header = verbose_output.readline().rstrip()
# no OOB
true_header = ' '.join(['%10s'] + ['%16s'] * 2) % ('Iter', 'Train Loss',
'Remaining Time')
assert_equal(true_header, header)
n_lines = sum(1 for l in verbose_output.readlines())
# 100 lines for n_estimators==100
assert_equal(100, n_lines)
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)
def test_max_feature_auto():
# Test if max features is set properly for floats and str.
X, y = datasets.make_hastie_10_2(n_samples=12000, random_state=1)
_, n_features = X.shape
X_train = X[:2000]
y_train = y[:2000]
gbrt = GradientBoostingClassifier(n_estimators=1, max_features='auto')
gbrt.fit(X_train, y_train)
assert_equal(gbrt.max_features_, int(np.sqrt(n_features)))
gbrt = GradientBoostingRegressor(n_estimators=1, max_features='auto')
gbrt.fit(X_train, y_train)
assert_equal(gbrt.max_features_, n_features)
gbrt = GradientBoostingRegressor(n_estimators=1, max_features=0.3)
gbrt.fit(X_train, y_train)
assert_equal(gbrt.max_features_, int(n_features * 0.3))
gbrt = GradientBoostingRegressor(n_estimators=1, max_features='sqrt')
gbrt.fit(X_train, y_train)
assert_equal(gbrt.max_features_, int(np.sqrt(n_features)))
gbrt = GradientBoostingRegressor(n_estimators=1, max_features='log2')
gbrt.fit(X_train, y_train)
assert_equal(gbrt.max_features_, int(np.log2(n_features)))
gbrt = GradientBoostingRegressor(n_estimators=1,
max_features=0.01 / X.shape[1])
gbrt.fit(X_train, y_train)
assert_equal(gbrt.max_features_, 1)