def test_zero_estimator_reg():
# Test if ZeroEstimator works for regression.
est = GradientBoostingRegressor(n_estimators=20,
max_depth=1,
random_state=1,
init=ZeroEstimator())
est.fit(boston.data, boston.target)
y_pred = est.predict(boston.data)
mse = mean_squared_error(boston.target, y_pred)
assert_almost_equal(mse, 33.0, decimal=0)
est = GradientBoostingRegressor(n_estimators=20,
max_depth=1,
random_state=1,
init='zero')
est.fit(boston.data, boston.target)
y_pred = est.predict(boston.data)
mse = mean_squared_error(boston.target, y_pred)
assert_almost_equal(mse, 33.0, decimal=0)
est = GradientBoostingRegressor(n_estimators=20,
max_depth=1,
random_state=1,
init='foobar')
assert_raises(ValueError, est.fit, boston.data, boston.target)
def test_plot_partial_dependence():
# Test partial dependence plot function.
clf = GradientBoostingRegressor(n_estimators=10, random_state=1)
clf.fit(boston.data, boston.target)
grid_resolution = 25
fig, axs = plot_partial_dependence(clf,
boston.data, [0, 1, (0, 1)],
grid_resolution=grid_resolution,
feature_names=boston.feature_names)
assert len(axs) == 3
assert all(ax.has_data for ax in axs)
# check with str features and array feature names
fig, axs = plot_partial_dependence(clf,
boston.data,
['CRIM', 'ZN', ('CRIM', 'ZN')],
grid_resolution=grid_resolution,
feature_names=boston.feature_names)
assert len(axs) == 3
assert all(ax.has_data for ax in axs)
# check with list feature_names
feature_names = boston.feature_names.tolist()
fig, axs = plot_partial_dependence(clf,
boston.data,
['CRIM', 'ZN', ('CRIM', 'ZN')],
grid_resolution=grid_resolution,
feature_names=feature_names)
assert len(axs) == 3
assert all(ax.has_data for ax in axs)
def check_boston(presort, loss, subsample):
# Check consistency on dataset boston house prices with least squares
# and least absolute deviation.
ones = np.ones(len(boston.target))
last_y_pred = None
for sample_weight in None, ones, 2 * ones:
clf = GradientBoostingRegressor(n_estimators=100,
loss=loss,
max_depth=4,
subsample=subsample,
min_samples_split=2,
random_state=1,
presort=presort)
assert_raises(ValueError, clf.predict, boston.data)
clf.fit(boston.data, boston.target, sample_weight=sample_weight)
leaves = clf.apply(boston.data)
assert_equal(leaves.shape, (506, 100))
y_pred = clf.predict(boston.data)
mse = mean_squared_error(boston.target, y_pred)
assert_less(mse, 6.0)
if last_y_pred is not None:
assert_array_almost_equal(last_y_pred, y_pred)
last_y_pred = y_pred
def test_non_uniform_weights_toy_edge_case_reg():
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 ('huber', 'ls', 'lad', 'quantile'):
gb = GradientBoostingRegressor(learning_rate=1.0,
n_estimators=2,
loss=loss)
gb.fit(X, y, sample_weight=sample_weight)
assert_greater(gb.predict([[1, 0]])[0], 0.5)
def test_partial_dependence_regressor():
# Test partial dependence for regressor
clf = GradientBoostingRegressor(n_estimators=10, random_state=1)
clf.fit(boston.data, boston.target)
grid_resolution = 25
pdp, axes = partial_dependence(clf, [0],
X=boston.data,
grid_resolution=grid_resolution)
assert pdp.shape == (1, grid_resolution)
assert axes[0].shape[0] == grid_resolution
def test_complete_regression():
# Test greedy trees with max_depth + 1 leafs.
from sklearn.tree._tree import TREE_LEAF
k = 4
est = GradientBoostingRegressor(n_estimators=20,
max_depth=None,
random_state=1,
max_leaf_nodes=k + 1)
est.fit(boston.data, boston.target)
tree = est.estimators_[-1, 0].tree_
assert_equal(tree.children_left[tree.children_left == TREE_LEAF].shape[0],
k + 1)
def test_quantile_loss():
# Check if quantile loss with alpha=0.5 equals lad.
clf_quantile = GradientBoostingRegressor(n_estimators=100,
loss='quantile',
max_depth=4,
alpha=0.5,
random_state=7)
clf_quantile.fit(boston.data, boston.target)
y_quantile = clf_quantile.predict(boston.data)
clf_lad = GradientBoostingRegressor(n_estimators=100,
loss='lad',
max_depth=4,
random_state=7)
clf_lad.fit(boston.data, boston.target)
y_lad = clf_lad.predict(boston.data)
assert_array_almost_equal(y_quantile, y_lad, decimal=4)
def test_staged_predict():
# Test whether staged decision function eventually gives
# the same prediction.
X, y = datasets.make_friedman1(n_samples=1200, random_state=1, noise=1.0)
X_train, y_train = X[:200], y[:200]
X_test = X[200:]
clf = GradientBoostingRegressor()
# test raise ValueError if not fitted
assert_raises(
ValueError,
lambda X: np.fromiter(clf.staged_predict(X), dtype=np.float64), X_test)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
# test if prediction for last stage equals ``predict``
for y in clf.staged_predict(X_test):
assert_equal(y.shape, y_pred.shape)
assert_array_equal(y_pred, y)
def test_feature_importances():
X = np.array(boston.data, dtype=np.float32)
y = np.array(boston.target, dtype=np.float32)
for presort in True, False:
clf = GradientBoostingRegressor(n_estimators=100,
max_depth=5,
min_samples_split=2,
random_state=1,
presort=presort)
clf.fit(X, y)
assert_true(hasattr(clf, 'feature_importances_'))
# XXX: Remove this test in 0.19 after transform support to estimators
# is removed.
X_new = assert_warns(DeprecationWarning,
clf.transform,
X,
threshold="mean")
assert_less(X_new.shape[1], X.shape[1])
feature_mask = (clf.feature_importances_ >
clf.feature_importances_.mean())
assert_array_almost_equal(X_new, X[:, feature_mask])
def test_regression_synthetic():
# Test on synthetic regression datasets used in Leo Breiman,
# `Bagging Predictors?. Machine Learning 24(2): 123-140 (1996).
random_state = check_random_state(1)
regression_params = {
'n_estimators': 100,
'max_depth': 4,
'min_samples_split': 2,
'learning_rate': 0.1,
'loss': 'ls'
}
# Friedman1
X, y = datasets.make_friedman1(n_samples=1200,
random_state=random_state,
noise=1.0)
X_train, y_train = X[:200], y[:200]
X_test, y_test = X[200:], y[200:]
for presort in True, False:
clf = GradientBoostingRegressor(presort=presort)
clf.fit(X_train, y_train)
mse = mean_squared_error(y_test, clf.predict(X_test))
assert_less(mse, 5.0)
# Friedman2
X, y = datasets.make_friedman2(n_samples=1200, random_state=random_state)
X_train, y_train = X[:200], y[:200]
X_test, y_test = X[200:], y[200:]
for presort in True, False:
regression_params['presort'] = presort
clf = GradientBoostingRegressor(**regression_params)
clf.fit(X_train, y_train)
mse = mean_squared_error(y_test, clf.predict(X_test))
assert_less(mse, 1700.0)
# Friedman3
X, y = datasets.make_friedman3(n_samples=1200, random_state=random_state)
X_train, y_train = X[:200], y[:200]
X_test, y_test = X[200:], y[200:]
for presort in True, False:
regression_params['presort'] = presort
clf = GradientBoostingRegressor(**regression_params)
clf.fit(X_train, y_train)
mse = mean_squared_error(y_test, clf.predict(X_test))
assert_less(mse, 0.015)