def test_ridge_individual_penalties():
# Tests the ridge object using individual penalties
rng = np.random.RandomState(42)
n_samples, n_features, n_targets = 20, 10, 5
X = rng.randn(n_samples, n_features)
y = rng.randn(n_samples, n_targets)
penalties = np.arange(n_targets)
coef_cholesky = np.array([
Ridge(alpha=alpha, solver="cholesky").fit(X, target).coef_
for alpha, target in zip(penalties, y.T)
])
coefs_indiv_pen = [
Ridge(alpha=penalties, solver=solver, tol=1e-8).fit(X, y).coef_
for solver in ['svd', 'sparse_cg', 'lsqr', 'cholesky', 'sag', 'saga']
]
for coef_indiv_pen in coefs_indiv_pen:
assert_array_almost_equal(coef_cholesky, coef_indiv_pen)
# Test error is raised when number of targets and penalties do not match.
ridge = Ridge(alpha=penalties[:-1])
assert_raises(ValueError, ridge.fit, X, y)
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 = np.bincount(out)
# drop inner nodes
leaf_count = node_counts[node_counts != 0]
assert 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 np.min(leaf_count) > len(X) * 0.25 - 1, (
"Failed with {0}".format(name))
def test_bagging_regressor_with_missing_inputs():
# Check that BaggingRegressor can accept X with missing/infinite data
X = np.array([
[1, 3, 5],
[2, None, 6],
[2, np.nan, 6],
[2, np.inf, 6],
[2, np.NINF, 6],
])
y_values = [
np.array([2, 3, 3, 3, 3]),
np.array([
[2, 1, 9],
[3, 6, 8],
[3, 6, 8],
[3, 6, 8],
[3, 6, 8],
])
]
for y in y_values:
regressor = DecisionTreeRegressor()
pipeline = make_pipeline(FunctionTransformer(replace), regressor)
pipeline.fit(X, y).predict(X)
bagging_regressor = BaggingRegressor(pipeline)
y_hat = bagging_regressor.fit(X, y).predict(X)
assert y.shape == y_hat.shape
# Verify that exceptions can be raised by wrapper regressor
regressor = DecisionTreeRegressor()
pipeline = make_pipeline(regressor)
assert_raises(ValueError, pipeline.fit, X, y)
bagging_regressor = BaggingRegressor(pipeline)
assert_raises(ValueError, bagging_regressor.fit, X, y)
def test_checksubparams_n_subsamples_if_less_samples_than_features():
random_state = np.random.RandomState(0)
n_samples, n_features = 10, 20
X = random_state.normal(size=(n_samples, n_features))
y = random_state.normal(size=n_samples)
theil_sen = TheilSenRegressor(n_subsamples=9, random_state=0)
assert_raises(ValueError, theil_sen.fit, X, y)
def test_check_symmetric():
arr_sym = np.array([[0, 1], [1, 2]])
arr_bad = np.ones(2)
arr_asym = np.array([[0, 2], [0, 2]])
test_arrays = {
'dense': arr_asym,
'dok': sp.dok_matrix(arr_asym),
'csr': sp.csr_matrix(arr_asym),
'csc': sp.csc_matrix(arr_asym),
'coo': sp.coo_matrix(arr_asym),
'lil': sp.lil_matrix(arr_asym),
'bsr': sp.bsr_matrix(arr_asym)
}
# check error for bad inputs
assert_raises(ValueError, check_symmetric, arr_bad)
# check that asymmetric arrays are properly symmetrized
for arr_format, arr in test_arrays.items():
# Check for warnings and errors
assert_warns(UserWarning, check_symmetric, arr)
assert_raises(ValueError, check_symmetric, arr, raise_exception=True)
output = check_symmetric(arr, raise_warning=False)
if sp.issparse(output):
assert output.format == arr_format
assert_array_equal(output.toarray(), arr_sym)
else:
assert_array_equal(output, arr_sym)
def test_set_params():
# test nested estimator parameter setting
clf = Pipeline([("svc", SVC())])
# non-existing parameter in svc
assert_raises(ValueError, clf.set_params, svc__stupid_param=True)
# non-existing parameter of pipeline
assert_raises(ValueError, clf.set_params, svm__stupid_param=True)
def test_warm_start_smaller_n_estimators():
# Test if warm start'ed second fit with smaller n_estimators raises error.
X, y = make_hastie_10_2(n_samples=20, random_state=1)
clf = BaggingClassifier(n_estimators=5, warm_start=True)
clf.fit(X, y)
clf.set_params(n_estimators=4)
assert_raises(ValueError, clf.fit, X, y)
def test_bagging_classifier_with_missing_inputs():
# Check that BaggingClassifier can accept X with missing/infinite data
X = np.array([
[1, 3, 5],
[2, None, 6],
[2, np.nan, 6],
[2, np.inf, 6],
[2, np.NINF, 6],
])
y = np.array([3, 6, 6, 6, 6])
classifier = DecisionTreeClassifier()
pipeline = make_pipeline(FunctionTransformer(replace), classifier)
pipeline.fit(X, y).predict(X)
bagging_classifier = BaggingClassifier(pipeline)
bagging_classifier.fit(X, y)
y_hat = bagging_classifier.predict(X)
assert y.shape == y_hat.shape
bagging_classifier.predict_log_proba(X)
bagging_classifier.predict_proba(X)
# Verify that exceptions can be raised by wrapper classifier
classifier = DecisionTreeClassifier()
pipeline = make_pipeline(classifier)
assert_raises(ValueError, pipeline.fit, X, y)
bagging_classifier = BaggingClassifier(pipeline)
assert_raises(ValueError, bagging_classifier.fit, X, y)
def test_constant_size_multioutput_regressor():
random_state = np.random.RandomState(seed=1)
X = random_state.randn(10, 10)
y = random_state.randn(10, 5)
est = DummyRegressor(strategy='constant', constant=[1, 2, 3, 4])
assert_raises(ValueError, est.fit, X, y)
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 X_means.dtype == output_dtype
assert 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_kernel_density_sampling(n_samples=100, n_features=3):
rng = np.random.RandomState(0)
X = rng.randn(n_samples, n_features)
bandwidth = 0.2
for kernel in ['gaussian', 'tophat']:
# draw a tophat sample
kde = KernelDensity(bandwidth, kernel=kernel).fit(X)
samp = kde.sample(100)
assert X.shape == samp.shape
# check that samples are in the right range
nbrs = NearestNeighbors(n_neighbors=1).fit(X)
dist, ind = nbrs.kneighbors(X, return_distance=True)
if kernel == 'tophat':
assert np.all(dist < bandwidth)
elif kernel == 'gaussian':
# 5 standard deviations is safe for 100 samples, but there's a
# very small chance this test could fail.
assert np.all(dist < 5 * bandwidth)
# check unsupported kernels
for kernel in ['epanechnikov', 'exponential', 'linear', 'cosine']:
kde = KernelDensity(bandwidth, kernel=kernel).fit(X)
assert_raises(NotImplementedError, kde.sample, 100)
# non-regression test: used to return a scalar
X = rng.randn(4, 1)
kde = KernelDensity(kernel="gaussian").fit(X)
assert kde.sample().shape == (1, 1)
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_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_calibration_curve():
"""Check calibration_curve function"""
y_true = np.array([0, 0, 0, 1, 1, 1])
y_pred = np.array([0., 0.1, 0.2, 0.8, 0.9, 1.])
prob_true, prob_pred = calibration_curve(y_true, y_pred, n_bins=2)
prob_true_unnormalized, prob_pred_unnormalized = \
calibration_curve(y_true, y_pred * 2, n_bins=2, normalize=True)
assert len(prob_true) == len(prob_pred)
assert len(prob_true) == 2
assert_almost_equal(prob_true, [0, 1])
assert_almost_equal(prob_pred, [0.1, 0.9])
assert_almost_equal(prob_true, prob_true_unnormalized)
assert_almost_equal(prob_pred, prob_pred_unnormalized)
# probabilities outside [0, 1] should not be accepted when normalize
# is set to False
assert_raises(ValueError, calibration_curve, [1.1], [-0.1],
normalize=False)
# test that quantiles work as expected
y_true2 = np.array([0, 0, 0, 0, 1, 1])
y_pred2 = np.array([0., 0.1, 0.2, 0.5, 0.9, 1.])
prob_true_quantile, prob_pred_quantile = calibration_curve(
y_true2, y_pred2, n_bins=2, strategy='quantile')
assert len(prob_true_quantile) == len(prob_pred_quantile)
assert len(prob_true_quantile) == 2
assert_almost_equal(prob_true_quantile, [0, 2 / 3])
assert_almost_equal(prob_pred_quantile, [0.1, 0.8])
# Check that error is raised when invalid strategy is selected
assert_raises(ValueError, calibration_curve, y_true2, y_pred2,
strategy='percentile')
def test_check_outlier_corruption():
# should raise AssertionError
decision = np.array([0., 1., 1.5, 2.])
assert_raises(AssertionError, check_outlier_corruption, 1, 2, decision)
# should pass
decision = np.array([0., 1., 1., 2.])
check_outlier_corruption(1, 2, decision)
def test_suppress_validation():
X = np.array([0, np.inf])
assert_raises(ValueError, assert_all_finite, X)
sklearn_lib.set_config(assume_finite=True)
assert_all_finite(X)
sklearn_lib.set_config(assume_finite=False)
assert_raises(ValueError, assert_all_finite, X)
def test_plot_partial_dependence_multiclass(pyplot):
# 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_random_projection_transformer_invalid_input():
for RandomProjection in all_RandomProjection:
assert_raises(ValueError,
RandomProjection(n_components='auto').fit, [[0, 1, 2]])
assert_raises(ValueError,
RandomProjection(n_components=-10).fit, data)
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_wrong_class_weight_label():
# ValueError due to wrong class_weight label.
X2 = np.array([[-1.0, -1.0], [-1.0, 0], [-.8, -1.0], [1.0, 1.0],
[1.0, 0.0]])
y2 = [1, 1, 1, -1, -1]
clf = PassiveAggressiveClassifier(class_weight={0: 0.5}, max_iter=100)
assert_raises(ValueError, clf.fit, X2, y2)
def test_pipeline_slice():
pipe = Pipeline([('transf1', Transf()), ('transf2', Transf()),
('clf', FitParamT())])
pipe2 = pipe[:-1]
assert isinstance(pipe2, Pipeline)
assert pipe2.steps == pipe.steps[:-1]
assert 2 == len(pipe2.named_steps)
assert_raises(ValueError, lambda: pipe[::-1])
def test_x_none_gram_none_raises_value_error():
# Test that lars_path with no X and Gram raises exception
Xy = np.dot(X.T, y)
assert_raises(ValueError,
linear_model.lars_path,
None,
y,
Gram=None,
Xy=Xy)
def test_input_size_jl_min_dim():
assert_raises(ValueError, johnson_lindenstrauss_min_dim,
3 * [100], 2 * [0.9])
assert_raises(ValueError, johnson_lindenstrauss_min_dim, 3 * [100],
2 * [0.9])
johnson_lindenstrauss_min_dim(np.random.randint(1, 10, size=(10, 10)),
np.full((10, 10), 0.5))
def test_get_params():
test = T(K(), K())
assert 'a__d' in test.get_params(deep=True)
assert 'a__d' not in test.get_params(deep=False)
test.set_params(a__d=2)
assert test.a.d == 2
assert_raises(ValueError, test.set_params, a__a=2)
def test_additive_chi2_sampler():
# test that AdditiveChi2Sampler approximates kernel on random data
# compute exact kernel
# abbreviations for easier formula
X_ = X[:, np.newaxis, :]
Y_ = Y[np.newaxis, :, :]
large_kernel = 2 * X_ * Y_ / (X_ + Y_)
# reduce to n_samples_x x n_samples_y by summing over features
kernel = (large_kernel.sum(axis=2))
# approximate kernel mapping
transform = AdditiveChi2Sampler(sample_steps=3)
X_trans = transform.fit_transform(X)
Y_trans = transform.transform(Y)
kernel_approx = np.dot(X_trans, Y_trans.T)
assert_array_almost_equal(kernel, kernel_approx, 1)
X_sp_trans = transform.fit_transform(csr_matrix(X))
Y_sp_trans = transform.transform(csr_matrix(Y))
assert_array_equal(X_trans, X_sp_trans.A)
assert_array_equal(Y_trans, Y_sp_trans.A)
# test error is raised on negative input
Y_neg = Y.copy()
Y_neg[0, 0] = -1
assert_raises(ValueError, transform.transform, Y_neg)
# test error on invalid sample_steps
transform = AdditiveChi2Sampler(sample_steps=4)
assert_raises(ValueError, transform.fit, X)
# test that the sample interval is set correctly
sample_steps_available = [1, 2, 3]
for sample_steps in sample_steps_available:
# test that the sample_interval is initialized correctly
transform = AdditiveChi2Sampler(sample_steps=sample_steps)
assert transform.sample_interval is None
# test that the sample_interval is changed in the fit method
transform.fit(X)
assert transform.sample_interval_ is not None
# test that the sample_interval is set correctly
sample_interval = 0.3
transform = AdditiveChi2Sampler(sample_steps=4,
sample_interval=sample_interval)
assert transform.sample_interval == sample_interval
transform.fit(X)
assert transform.sample_interval_ == sample_interval
def test_ovr_coef_exceptions():
# Not fitted exception!
ovr = OneVsRestClassifier(LinearSVC(random_state=0))
# lambda is needed because we don't want coef_ to be evaluated right away
assert_raises(ValueError, lambda x: ovr.coef_, None)
# Doesn't have coef_ exception!
ovr = OneVsRestClassifier(DecisionTreeClassifier())
ovr.fit(iris.data, iris.target)
assert_raises(AttributeError, lambda x: ovr.coef_, None)
def test_pipeline_index():
transf = Transf()
clf = FitParamT()
pipe = Pipeline([('transf', transf), ('clf', clf)])
assert pipe[0] == transf
assert pipe['transf'] == transf
assert pipe[-1] == clf
assert pipe['clf'] == clf
assert_raises(IndexError, lambda: pipe[3])
assert_raises(KeyError, lambda: pipe['foobar'])
def test_bagging_sample_weight_unsupported_but_passed():
estimator = BaggingClassifier(DummyZeroEstimator())
rng = check_random_state(0)
estimator.fit(iris.data, iris.target).predict(iris.data)
assert_raises(ValueError,
estimator.fit,
iris.data,
iris.target,
sample_weight=rng.randint(10, size=(iris.data.shape[0])))
def test_oob_score_removed_on_warm_start():
X, y = make_hastie_10_2(n_samples=2000, random_state=1)
clf = BaggingClassifier(n_estimators=50, oob_score=True)
clf.fit(X, y)
clf.set_params(warm_start=True, oob_score=False, n_estimators=100)
clf.fit(X, y)
assert_raises(AttributeError, getattr, clf, "oob_score_")
def test_isotonic_regression_oob_bad():
# Set y and x
y = np.array([3, 7, 5, 9, 8, 7, 10])
x = np.arange(len(y))
# Create model and fit
ir = IsotonicRegression(increasing='auto', out_of_bounds="xyz")
# Make sure that we throw an error for bad out_of_bounds value
assert_raises(ValueError, ir.fit, x, y)