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_mean_variance_axis1():
X, _ = make_classification(5, 4, random_state=0)
# Sparsify the array a little bit
X[0, 0] = 0
X[2, 1] = 0
X[4, 3] = 0
X_lil = sp.lil_matrix(X)
X_lil[1, 0] = 0
X[1, 0] = 0
assert_raises(TypeError, mean_variance_axis, X_lil, axis=1)
X_csr = sp.csr_matrix(X_lil)
X_csc = sp.csc_matrix(X_lil)
expected_dtypes = [(np.float32, np.float32), (np.float64, np.float64),
(np.int32, np.float64), (np.int64, np.float64)]
for input_dtype, output_dtype in expected_dtypes:
X_test = X.astype(input_dtype)
for X_sparse in (X_csr, X_csc):
X_sparse = X_sparse.astype(input_dtype)
X_means, X_vars = mean_variance_axis(X_sparse, axis=0)
assert_equal(X_means.dtype, output_dtype)
assert_equal(X_vars.dtype, output_dtype)
assert_array_almost_equal(X_means, np.mean(X_test, axis=0))
assert_array_almost_equal(X_vars, np.var(X_test, axis=0))
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 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 check_min_samples_leaf(name):
X, y = hastie_X, hastie_y
# Test if leaves contain more than leaf_count training examples
ForestEstimator = FOREST_ESTIMATORS[name]
# test boundary value
assert_raises(ValueError, ForestEstimator(min_samples_leaf=-1).fit, X, y)
assert_raises(ValueError, ForestEstimator(min_samples_leaf=0).fit, X, y)
est = ForestEstimator(min_samples_leaf=5, n_estimators=1, random_state=0)
est.fit(X, y)
out = est.estimators_[0].tree_.apply(X)
node_counts = bincount(out)
# drop inner nodes
leaf_count = node_counts[node_counts != 0]
assert_greater(np.min(leaf_count), 4, "Failed with {0}".format(name))
est = ForestEstimator(min_samples_leaf=0.25,
n_estimators=1,
random_state=0)
est.fit(X, y)
out = est.estimators_[0].tree_.apply(X)
node_counts = np.bincount(out)
# drop inner nodes
leaf_count = node_counts[node_counts != 0]
assert_greater(np.min(leaf_count),
len(X) * 0.25 - 1, "Failed with {0}".format(name))
def test_csc_row_median():
# Test csc_row_median actually calculates the median.
# Test that it gives the same output when X is dense.
rng = np.random.RandomState(0)
X = rng.rand(100, 50)
dense_median = np.median(X, axis=0)
csc = sp.csc_matrix(X)
sparse_median = csc_median_axis_0(csc)
assert_array_equal(sparse_median, dense_median)
# Test that it gives the same output when X is sparse
X = rng.rand(51, 100)
X[X < 0.7] = 0.0
ind = rng.randint(0, 50, 10)
X[ind] = -X[ind]
csc = sp.csc_matrix(X)
dense_median = np.median(X, axis=0)
sparse_median = csc_median_axis_0(csc)
assert_array_equal(sparse_median, dense_median)
# Test for toy data.
X = [[0, -2], [-1, -1], [1, 0], [2, 1]]
csc = sp.csc_matrix(X)
assert_array_equal(csc_median_axis_0(csc), np.array([0.5, -0.5]))
X = [[0, -2], [-1, -5], [1, -3]]
csc = sp.csc_matrix(X)
assert_array_equal(csc_median_axis_0(csc), np.array([0., -3]))
# Test that it raises an Error for non-csc matrices.
assert_raises(TypeError, csc_median_axis_0, sp.csr_matrix(X))
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_inplace_row_scale():
rng = np.random.RandomState(0)
X = sp.rand(100, 200, 0.05)
Xr = X.tocsr()
Xc = X.tocsc()
XA = X.toarray()
scale = rng.rand(100)
XA *= scale.reshape(-1, 1)
inplace_row_scale(Xc, scale)
inplace_row_scale(Xr, scale)
assert_array_almost_equal(Xr.toarray(), Xc.toarray())
assert_array_almost_equal(XA, Xc.toarray())
assert_array_almost_equal(XA, Xr.toarray())
assert_raises(TypeError, inplace_column_scale, X.tolil(), scale)
X = X.astype(np.float32)
scale = scale.astype(np.float32)
Xr = X.tocsr()
Xc = X.tocsc()
XA = X.toarray()
XA *= scale.reshape(-1, 1)
inplace_row_scale(Xc, scale)
inplace_row_scale(Xr, scale)
assert_array_almost_equal(Xr.toarray(), Xc.toarray())
assert_array_almost_equal(XA, Xc.toarray())
assert_array_almost_equal(XA, Xr.toarray())
assert_raises(TypeError, inplace_column_scale, X.tolil(), scale)
def test_warm_start_smaller_n_estimators():
# Test if warm start with smaller n_estimators raises error
X, y = datasets.make_hastie_10_2(n_samples=100, random_state=1)
for Cls in [GradientBoostingRegressor, GradientBoostingClassifier]:
est = Cls(n_estimators=100, max_depth=1, warm_start=True)
est.fit(X, y)
est.set_params(n_estimators=99)
assert_raises(ValueError, est.fit, X, y)
def check_warm_start_smaller_n_estimators(name):
# Test if warm start second fit with smaller n_estimators raises error.
X, y = hastie_X, hastie_y
ForestEstimator = FOREST_ESTIMATORS[name]
clf = ForestEstimator(n_estimators=5, max_depth=1, warm_start=True)
clf.fit(X, y)
clf.set_params(n_estimators=4)
assert_raises(ValueError, clf.fit, X, y)
def test_get_params():
test = T(K(), K())
assert_true('a__d' in test.get_params(deep=True))
assert_true('a__d' not in test.get_params(deep=False))
test.set_params(a__d=2)
assert_true(test.a.d == 2)
assert_raises(ValueError, test.set_params, a__a=2)
def check_1d_input(name, X, X_2d, y):
ForestEstimator = FOREST_ESTIMATORS[name]
assert_raises(ValueError,
ForestEstimator(n_estimators=1, random_state=0).fit, X, y)
est = ForestEstimator(random_state=0)
est.fit(X_2d, y)
if name in FOREST_CLASSIFIERS or name in FOREST_REGRESSORS:
assert_raises(ValueError, est.predict, X)
def test_compute_class_weight_not_present():
# Raise error when y does not contain all class labels
classes = np.arange(4)
y = np.asarray([0, 0, 0, 1, 1, 2])
assert_raises(ValueError, compute_class_weight, "auto", classes, y)
assert_raises(ValueError, compute_class_weight, "balanced", classes, y)
# Raise error when y has items not in classes
classes = np.arange(2)
assert_raises(ValueError, compute_class_weight, "auto", classes, y)
assert_raises(ValueError, compute_class_weight, "balanced", classes, y)
assert_raises(ValueError, compute_class_weight, {0: 1., 1: 2.}, classes, y)
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_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_make_rng():
# Check the check_random_state utility function behavior
assert_true(check_random_state(None) is np.random.mtrand._rand)
assert_true(check_random_state(np.random) is np.random.mtrand._rand)
rng_42 = np.random.RandomState(42)
assert_true(check_random_state(42).randint(100) == rng_42.randint(100))
rng_42 = np.random.RandomState(42)
assert_true(check_random_state(rng_42) is rng_42)
rng_42 = np.random.RandomState(42)
assert_true(check_random_state(43).randint(100) != rng_42.randint(100))
assert_raises(ValueError, check_random_state, "some invalid seed")
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_count_nonzero():
X = np.array([[0, 3, 0], [2, -1, 0], [0, 0, 0], [9, 8, 7], [4, 0, 5]],
dtype=np.float64)
X_csr = sp.csr_matrix(X)
X_csc = sp.csc_matrix(X)
X_nonzero = X != 0
sample_weight = [.5, .2, .3, .1, .1]
X_nonzero_weighted = X_nonzero * np.array(sample_weight)[:, None]
for axis in [0, 1, -1, -2, None]:
assert_array_almost_equal(count_nonzero(X_csr, axis=axis),
X_nonzero.sum(axis=axis))
assert_array_almost_equal(
count_nonzero(X_csr, axis=axis, sample_weight=sample_weight),
X_nonzero_weighted.sum(axis=axis))
assert_raises(TypeError, count_nonzero, X_csc)
assert_raises(ValueError, count_nonzero, X_csr, axis=2)
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_inplace_swap_column():
X = np.array([[0, 3, 0], [2, 4, 0], [0, 0, 0], [9, 8, 7], [4, 0, 5]],
dtype=np.float64)
X_csr = sp.csr_matrix(X)
X_csc = sp.csc_matrix(X)
swap = linalg.get_blas_funcs(('swap', ), (X, ))
swap = swap[0]
X[:, 0], X[:, -1] = swap(X[:, 0], X[:, -1])
inplace_swap_column(X_csr, 0, -1)
inplace_swap_column(X_csc, 0, -1)
assert_array_equal(X_csr.toarray(), X_csc.toarray())
assert_array_equal(X, X_csc.toarray())
assert_array_equal(X, X_csr.toarray())
X[:, 0], X[:, 1] = swap(X[:, 0], X[:, 1])
inplace_swap_column(X_csr, 0, 1)
inplace_swap_column(X_csc, 0, 1)
assert_array_equal(X_csr.toarray(), X_csc.toarray())
assert_array_equal(X, X_csc.toarray())
assert_array_equal(X, X_csr.toarray())
assert_raises(TypeError, inplace_swap_column, X_csr.tolil())
X = np.array([[0, 3, 0], [2, 4, 0], [0, 0, 0], [9, 8, 7], [4, 0, 5]],
dtype=np.float32)
X_csr = sp.csr_matrix(X)
X_csc = sp.csc_matrix(X)
swap = linalg.get_blas_funcs(('swap', ), (X, ))
swap = swap[0]
X[:, 0], X[:, -1] = swap(X[:, 0], X[:, -1])
inplace_swap_column(X_csr, 0, -1)
inplace_swap_column(X_csc, 0, -1)
assert_array_equal(X_csr.toarray(), X_csc.toarray())
assert_array_equal(X, X_csc.toarray())
assert_array_equal(X, X_csr.toarray())
X[:, 0], X[:, 1] = swap(X[:, 0], X[:, 1])
inplace_swap_column(X_csr, 0, 1)
inplace_swap_column(X_csc, 0, 1)
assert_array_equal(X_csr.toarray(), X_csc.toarray())
assert_array_equal(X, X_csc.toarray())
assert_array_equal(X, X_csr.toarray())
assert_raises(TypeError, inplace_swap_column, X_csr.tolil())
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_column_or_1d():
EXAMPLES = [
("binary", ["spam", "egg", "spam"]),
("binary", [0, 1, 0, 1]),
("continuous", np.arange(10) / 20.),
("multiclass", [1, 2, 3]),
("multiclass", [0, 1, 2, 2, 0]),
("multiclass", [[1], [2], [3]]),
("multilabel-indicator", [[0, 1, 0], [0, 0, 1]]),
("multiclass-multioutput", [[1, 2, 3]]),
("multiclass-multioutput", [[1, 1], [2, 2], [3, 1]]),
("multiclass-multioutput", [[5, 1], [4, 2], [3, 1]]),
("multiclass-multioutput", [[1, 2, 3]]),
("continuous-multioutput", np.arange(30).reshape((-1, 3))),
]
for y_type, y in EXAMPLES:
if y_type in ["binary", 'multiclass', "continuous"]:
assert_array_equal(column_or_1d(y), np.ravel(y))
else:
assert_raises(ValueError, column_or_1d, y)
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 check_min_samples_split(name):
X, y = hastie_X, hastie_y
ForestEstimator = FOREST_ESTIMATORS[name]
# test boundary value
assert_raises(ValueError, ForestEstimator(min_samples_split=-1).fit, X, y)
assert_raises(ValueError, ForestEstimator(min_samples_split=0).fit, X, y)
assert_raises(ValueError, ForestEstimator(min_samples_split=1.1).fit, X, y)
est = ForestEstimator(min_samples_split=10, n_estimators=1, random_state=0)
est.fit(X, y)
node_idx = est.estimators_[0].tree_.children_left != -1
node_samples = est.estimators_[0].tree_.n_node_samples[node_idx]
assert_greater(np.min(node_samples),
len(X) * 0.5 - 1, "Failed with {0}".format(name))
est = ForestEstimator(min_samples_split=0.5,
n_estimators=1,
random_state=0)
est.fit(X, y)
node_idx = est.estimators_[0].tree_.children_left != -1
node_samples = est.estimators_[0].tree_.n_node_samples[node_idx]
assert_greater(np.min(node_samples),
len(X) * 0.5 - 1, "Failed with {0}".format(name))
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_min_max_axis_errors():
X = np.array([[0, 3, 0], [2, -1, 0], [0, 0, 0], [9, 8, 7], [4, 0, 5]],
dtype=np.float64)
X_csr = sp.csr_matrix(X)
X_csc = sp.csc_matrix(X)
assert_raises(TypeError, min_max_axis, X_csr.tolil(), axis=0)
assert_raises(ValueError, min_max_axis, X_csr, axis=2)
assert_raises(ValueError, min_max_axis, X_csc, axis=-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)
def check_edge_case_of_sample_int(sample_without_replacement):
# n_population < n_sample
assert_raises(ValueError, sample_without_replacement, 0, 1)
assert_raises(ValueError, sample_without_replacement, 1, 2)
# n_population == n_samples
assert_equal(sample_without_replacement(0, 0).shape, (0, ))
assert_equal(sample_without_replacement(1, 1).shape, (1, ))
# n_population >= n_samples
assert_equal(sample_without_replacement(5, 0).shape, (0, ))
assert_equal(sample_without_replacement(5, 1).shape, (1, ))
# n_population < 0 or n_samples < 0
assert_raises(ValueError, sample_without_replacement, -1, 5)
assert_raises(ValueError, sample_without_replacement, 5, -1)
def test_clone_buggy():
# Check that clone raises an error on buggy estimators.
buggy = Buggy()
buggy.a = 2
assert_raises(RuntimeError, clone, buggy)
no_estimator = NoEstimator()
assert_raises(TypeError, clone, no_estimator)
varg_est = VargEstimator()
assert_raises(RuntimeError, clone, varg_est)
def test_resample():
# Border case not worth mentioning in doctests
assert_true(resample() is None)
# Check that invalid arguments yield ValueError
assert_raises(ValueError, resample, [0], [0, 1])
assert_raises(ValueError,
resample, [0, 1], [0, 1],
replace=False,
n_samples=3)
assert_raises(ValueError, resample, [0, 1], [0, 1], meaning_of_life=42)
# Issue:6581, n_samples can be more when replace is True (default).
assert_equal(len(resample([1, 2], n_samples=5)), 5)
