def test_nmf_negative_beta_loss():
# Test that an error is raised if beta_loss < 0 and X contains zeros.
# Test that the output has not NaN values when the input contains zeros.
n_samples = 6
n_features = 5
n_components = 3
rng = np.random.mtrand.RandomState(42)
X = rng.randn(n_samples, n_features)
np.clip(X, 0, None, out=X)
X_csr = sp.csr_matrix(X)
def _assert_nmf_no_nan(X, beta_loss):
W, H, _ = non_negative_factorization(X,
init='random',
n_components=n_components,
solver='mu',
beta_loss=beta_loss,
random_state=0,
max_iter=1000)
assert not np.any(np.isnan(W))
assert not np.any(np.isnan(H))
msg = "When beta_loss <= 0 and X contains zeros, the solver may diverge."
for beta_loss in (-0.6, 0.):
assert_raise_message(ValueError, msg, _assert_nmf_no_nan, X, beta_loss)
_assert_nmf_no_nan(X + 1e-9, beta_loss)
for beta_loss in (0.2, 1., 1.2, 2., 2.5):
_assert_nmf_no_nan(X, beta_loss)
_assert_nmf_no_nan(X_csr, beta_loss)
def test_bayesian_mixture_weights_prior_initialisation():
rng = np.random.RandomState(0)
n_samples, n_components, n_features = 10, 5, 2
X = rng.rand(n_samples, n_features)
# Check raise message for a bad value of weight_concentration_prior
bad_weight_concentration_prior_ = 0.
bgmm = BayesianGaussianMixture(
weight_concentration_prior=bad_weight_concentration_prior_,
random_state=0)
assert_raise_message(
ValueError, "The parameter 'weight_concentration_prior' "
"should be greater than 0., but got %.3f." %
bad_weight_concentration_prior_, bgmm.fit, X)
# Check correct init for a given value of weight_concentration_prior
weight_concentration_prior = rng.rand()
bgmm = BayesianGaussianMixture(
weight_concentration_prior=weight_concentration_prior,
random_state=rng).fit(X)
assert_almost_equal(weight_concentration_prior,
bgmm.weight_concentration_prior_)
# Check correct init for the default value of weight_concentration_prior
bgmm = BayesianGaussianMixture(n_components=n_components,
random_state=rng).fit(X)
assert_almost_equal(1. / n_components, bgmm.weight_concentration_prior_)
def test_score():
covar_type = 'full'
rng = np.random.RandomState(0)
rand_data = RandomData(rng, scale=7)
n_components = rand_data.n_components
X = rand_data.X[covar_type]
# Check the error message if we don't call fit
gmm1 = GaussianMixture(n_components=n_components,
n_init=1,
max_iter=1,
reg_covar=0,
random_state=rng,
covariance_type=covar_type)
assert_raise_message(
NotFittedError, "This GaussianMixture instance is not fitted "
"yet. Call 'fit' with appropriate arguments "
"before using this estimator.", gmm1.score, X)
# Check score value
with warnings.catch_warnings():
warnings.simplefilter("ignore", ConvergenceWarning)
gmm1.fit(X)
gmm_score = gmm1.score(X)
gmm_score_proba = gmm1.score_samples(X).mean()
assert_almost_equal(gmm_score, gmm_score_proba)
# Check if the score increase
gmm2 = GaussianMixture(n_components=n_components,
n_init=1,
reg_covar=0,
random_state=rng,
covariance_type=covar_type).fit(X)
assert gmm2.score(X) > gmm1.score(X)
def test_column_transformer_invalid_columns(remainder):
X_array = np.array([[0, 1, 2], [2, 4, 6]]).T
# general invalid
for col in [1.5, ['string', 1], slice(1, 's'), np.array([1.])]:
ct = ColumnTransformer([('trans', Trans(), col)], remainder=remainder)
assert_raise_message(ValueError, "No valid specification", ct.fit,
X_array)
# invalid for arrays
for col in ['string', ['string', 'other'], slice('a', 'b')]:
ct = ColumnTransformer([('trans', Trans(), col)], remainder=remainder)
assert_raise_message(ValueError, "Specifying the columns", ct.fit,
X_array)
# transformed n_features does not match fitted n_features
col = [0, 1]
ct = ColumnTransformer([('trans', Trans(), col)], remainder=remainder)
ct.fit(X_array)
X_array_more = np.array([[0, 1, 2], [2, 4, 6], [3, 6, 9]]).T
msg = ("Given feature/column names or counts do not match the ones for "
"the data given during fit.")
with pytest.warns(FutureWarning, match=msg):
ct.transform(X_array_more) # Should accept added columns, for now
X_array_fewer = np.array([
[0, 1, 2],
]).T
err_msg = 'Number of features'
with pytest.raises(ValueError, match=err_msg):
ct.transform(X_array_fewer)
def test_bayesian_mixture_predict_predict_proba():
# this is the same test as test_gaussian_mixture_predict_predict_proba()
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
for prior_type in PRIOR_TYPE:
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
Y = rand_data.Y
bgmm = BayesianGaussianMixture(
n_components=rand_data.n_components,
random_state=rng,
weight_concentration_prior_type=prior_type,
covariance_type=covar_type)
# Check a warning message arrive if we don't do fit
assert_raise_message(
NotFittedError, "This BayesianGaussianMixture instance"
" is not fitted yet. Call 'fit' with "
"appropriate arguments before using "
"this estimator.", bgmm.predict, X)
bgmm.fit(X)
Y_pred = bgmm.predict(X)
Y_pred_proba = bgmm.predict_proba(X).argmax(axis=1)
assert_array_equal(Y_pred, Y_pred_proba)
assert adjusted_rand_score(Y, Y_pred) >= .95
def test_step_name_validation():
bad_steps1 = [('a__q', Mult(2)), ('b', Mult(3))]
bad_steps2 = [('a', Mult(2)), ('a', Mult(3))]
for cls, param in [(Pipeline, 'steps'),
(FeatureUnion, 'transformer_list')]:
# we validate in construction (despite scikit-learn convention)
bad_steps3 = [('a', Mult(2)), (param, Mult(3))]
for bad_steps, message in [
(bad_steps1, "Estimator names must not contain __: got ['a__q']"),
(bad_steps2, "Names provided are not unique: ['a', 'a']"),
(bad_steps3, "Estimator names conflict with constructor "
"arguments: ['%s']" % param),
]:
# three ways to make invalid:
# - construction
assert_raise_message(ValueError, message, cls,
**{param: bad_steps})
# - setattr
est = cls(**{param: [('a', Mult(1))]})
setattr(est, param, bad_steps)
assert_raise_message(ValueError, message, est.fit, [[1]], [1])
assert_raise_message(ValueError, message, est.fit_transform, [[1]],
[1])
# - set_params
est = cls(**{param: [('a', Mult(1))]})
est.set_params(**{param: bad_steps})
assert_raise_message(ValueError, message, est.fit, [[1]], [1])
assert_raise_message(ValueError, message, est.fit_transform, [[1]],
[1])
def check_svm_model_equal(dense_svm, sparse_svm, X_train, y_train, X_test):
dense_svm.fit(X_train.toarray(), y_train)
if sparse.isspmatrix(X_test):
X_test_dense = X_test.toarray()
else:
X_test_dense = X_test
sparse_svm.fit(X_train, y_train)
assert sparse.issparse(sparse_svm.support_vectors_)
assert sparse.issparse(sparse_svm.dual_coef_)
assert_array_almost_equal(dense_svm.support_vectors_,
sparse_svm.support_vectors_.toarray())
assert_array_almost_equal(dense_svm.dual_coef_,
sparse_svm.dual_coef_.toarray())
if dense_svm.kernel == "linear":
assert sparse.issparse(sparse_svm.coef_)
assert_array_almost_equal(dense_svm.coef_, sparse_svm.coef_.toarray())
assert_array_almost_equal(dense_svm.support_, sparse_svm.support_)
assert_array_almost_equal(dense_svm.predict(X_test_dense),
sparse_svm.predict(X_test))
assert_array_almost_equal(dense_svm.decision_function(X_test_dense),
sparse_svm.decision_function(X_test))
assert_array_almost_equal(dense_svm.decision_function(X_test_dense),
sparse_svm.decision_function(X_test_dense))
if isinstance(dense_svm, svm.OneClassSVM):
msg = "cannot use sparse input in 'OneClassSVM' trained on dense data"
else:
assert_array_almost_equal(dense_svm.predict_proba(X_test_dense),
sparse_svm.predict_proba(X_test), 4)
msg = "cannot use sparse input in 'SVC' trained on dense data"
if sparse.isspmatrix(X_test):
assert_raise_message(ValueError, msg, dense_svm.predict, X_test)
def test_fetch_nonexiting(monkeypatch, gzip_response):
# there is no active version of glass2
data_id = 40675
_monkey_patch_webbased_functions(monkeypatch, data_id, gzip_response)
# Note that we only want to search by name (not data id)
assert_raise_message(ValueError, "No active dataset glass2 found",
fetch_openml, name='glass2', cache=False)
def test_zero_cosine_linkage_tree():
# Check that zero vectors in X produce an error when
# 'cosine' affinity is used
X = np.array([[0, 1],
[0, 0]])
msg = 'Cosine affinity cannot be used when X contains zero vectors'
assert_raise_message(ValueError, msg, linkage_tree, X, affinity='cosine')
def test_n_iter():
"""Check value of n_iter."""
X = np.array([[1], [2], [6], [8], [10]])
y = np.array([1, 2, 6, 8, 10])
clf = BayesianRidge(n_iter=0)
msg = "n_iter should be greater than or equal to 1."
assert_raise_message(ValueError, msg, clf.fit, X, y)
def test_enet_l1_ratio():
# Test that an error message is raised if an estimator that
# uses _alpha_grid is called with l1_ratio=0
msg = ("Automatic alpha grid generation is not supported for l1_ratio=0. "
"Please supply a grid by providing your estimator with the "
"appropriate `alphas=` argument.")
X = np.array([[1, 2, 4, 5, 8], [3, 5, 7, 7, 8]]).T
y = np.array([12, 10, 11, 21, 5])
assert_raise_message(ValueError, msg,
ElasticNetCV(l1_ratio=0, random_state=42).fit, X, y)
assert_raise_message(
ValueError, msg,
MultiTaskElasticNetCV(l1_ratio=0, random_state=42).fit, X, y[:, None])
# Test that l1_ratio=0 is allowed if we supply a grid manually
alphas = [0.1, 10]
estkwds = {'alphas': alphas, 'random_state': 42}
est_desired = ElasticNetCV(l1_ratio=0.00001, **estkwds)
est = ElasticNetCV(l1_ratio=0, **estkwds)
with ignore_warnings():
est_desired.fit(X, y)
est.fit(X, y)
assert_array_almost_equal(est.coef_, est_desired.coef_, decimal=5)
est_desired = MultiTaskElasticNetCV(l1_ratio=0.00001, **estkwds)
est = MultiTaskElasticNetCV(l1_ratio=0, **estkwds)
with ignore_warnings():
est.fit(X, y[:, None])
est_desired.fit(X, y[:, None])
assert_array_almost_equal(est.coef_, est_desired.coef_, decimal=5)
def test_n_components():
rng = np.random.RandomState(42)
X = np.arange(12).reshape(4, 3)
y = [1, 1, 2, 2]
init = rng.rand(X.shape[1] - 1, 3)
# n_components = X.shape[1] != transformation.shape[0]
n_components = X.shape[1]
nca = NeighborhoodComponentsAnalysis(init=init, n_components=n_components)
assert_raise_message(ValueError,
'The preferred dimensionality of the '
'projected space `n_components` ({}) does not match '
'the output dimensionality of the given '
'linear transformation `init` ({})!'
.format(n_components, init.shape[0]),
nca.fit, X, y)
# n_components > X.shape[1]
n_components = X.shape[1] + 2
nca = NeighborhoodComponentsAnalysis(init=init, n_components=n_components)
assert_raise_message(ValueError,
'The preferred dimensionality of the '
'projected space `n_components` ({}) cannot '
'be greater than the given data '
'dimensionality ({})!'
.format(n_components, X.shape[1]),
nca.fit, X, y)
# n_components < X.shape[1]
nca = NeighborhoodComponentsAnalysis(n_components=2, init='identity')
nca.fit(X, y)
def test_ovo_float_y():
# Test that the OvO errors on float targets
X = iris.data
y = iris.data[:, 0]
ovo = OneVsOneClassifier(LinearSVC())
assert_raise_message(ValueError, "Unknown label type", ovo.fit, X, y)
def test_ovo_one_class():
# Test error for OvO with one class
X = np.eye(4)
y = np.array(['a'] * 4)
ovo = OneVsOneClassifier(LinearSVC())
assert_raise_message(ValueError, "when only one class", ovo.fit, X, y)
def test_regularisation():
# We train the GaussianMixture on degenerate data by defining two clusters
# of a 0 covariance.
rng = np.random.RandomState(0)
n_samples, n_features = 10, 5
X = np.vstack((np.ones(
(n_samples // 2, n_features)), np.zeros((n_samples // 2, n_features))))
for covar_type in COVARIANCE_TYPE:
gmm = GaussianMixture(n_components=n_samples,
reg_covar=0,
covariance_type=covar_type,
random_state=rng)
with warnings.catch_warnings():
warnings.simplefilter("ignore", RuntimeWarning)
assert_raise_message(
ValueError, "Fitting the mixture model failed because "
"some components have ill-defined empirical "
"covariance (for instance caused by "
"singleton or collapsed samples). Try to "
"decrease the number of components, or "
"increase reg_covar.", gmm.fit, X)
gmm.set_params(reg_covar=1e-6).fit(X)
def test_pls_errors():
d = load_linnerud()
X = d.data
Y = d.target
for clf in [pls_.PLSCanonical(), pls_.PLSRegression(), pls_.PLSSVD()]:
clf.n_components = 4
assert_raise_message(ValueError, "Invalid number of components",
clf.fit, X, Y)
def test_string_attribute_without_dataframe(monkeypatch, gzip_response):
data_id = 40945
_monkey_patch_webbased_functions(monkeypatch, data_id, gzip_response)
# single column test
assert_raise_message(ValueError,
('STRING attributes are not supported for '
'array representation. Try as_frame=True'),
fetch_openml, data_id=data_id, cache=False)
def test_raises_illegal_multitarget(monkeypatch, gzip_response):
data_id = 61
targets = ['sepalwidth', 'class']
_monkey_patch_webbased_functions(monkeypatch, data_id, gzip_response)
# Note that we only want to search by name (not data id)
assert_raise_message(ValueError,
"Can only handle homogeneous multi-target datasets,",
fetch_openml, data_id=data_id,
target_column=targets, cache=False)
def test_base_zero_n_estimators():
# Check that instantiating a BaseEnsemble with n_estimators<=0 raises
# a ValueError.
ensemble = BaggingClassifier(base_estimator=Perceptron(),
n_estimators=0)
iris = load_iris()
assert_raise_message(ValueError,
"n_estimators must be greater than zero, got 0.",
ensemble.fit, iris.data, iris.target)
def test_linear_svc_intercept_scaling():
# Test that the right error message is thrown when intercept_scaling <= 0
for i in [-1, 0]:
lsvc = svm.LinearSVC(intercept_scaling=i)
msg = ('Intercept scaling is %r but needs to be greater than 0.'
' To disable fitting an intercept,'
' set fit_intercept=False.' % lsvc.intercept_scaling)
assert_raise_message(ValueError, msg, lsvc.fit, X, Y)
def test_column_transformer_remainder():
X_array = np.array([[0, 1, 2], [2, 4, 6]]).T
X_res_first = np.array([0, 1, 2]).reshape(-1, 1)
X_res_second = np.array([2, 4, 6]).reshape(-1, 1)
X_res_both = X_array
# default drop
ct = ColumnTransformer([('trans1', Trans(), [0])])
assert_array_equal(ct.fit_transform(X_array), X_res_first)
assert_array_equal(ct.fit(X_array).transform(X_array), X_res_first)
assert len(ct.transformers_) == 2
assert ct.transformers_[-1][0] == 'remainder'
assert ct.transformers_[-1][1] == 'drop'
assert_array_equal(ct.transformers_[-1][2], [1])
# specify passthrough
ct = ColumnTransformer([('trans', Trans(), [0])], remainder='passthrough')
assert_array_equal(ct.fit_transform(X_array), X_res_both)
assert_array_equal(ct.fit(X_array).transform(X_array), X_res_both)
assert len(ct.transformers_) == 2
assert ct.transformers_[-1][0] == 'remainder'
assert ct.transformers_[-1][1] == 'passthrough'
assert_array_equal(ct.transformers_[-1][2], [1])
# column order is not preserved (passed through added to end)
ct = ColumnTransformer([('trans1', Trans(), [1])], remainder='passthrough')
assert_array_equal(ct.fit_transform(X_array), X_res_both[:, ::-1])
assert_array_equal(ct.fit(X_array).transform(X_array), X_res_both[:, ::-1])
assert len(ct.transformers_) == 2
assert ct.transformers_[-1][0] == 'remainder'
assert ct.transformers_[-1][1] == 'passthrough'
assert_array_equal(ct.transformers_[-1][2], [0])
# passthrough when all actual transformers are skipped
ct = ColumnTransformer([('trans1', 'drop', [0])], remainder='passthrough')
assert_array_equal(ct.fit_transform(X_array), X_res_second)
assert_array_equal(ct.fit(X_array).transform(X_array), X_res_second)
assert len(ct.transformers_) == 2
assert ct.transformers_[-1][0] == 'remainder'
assert ct.transformers_[-1][1] == 'passthrough'
assert_array_equal(ct.transformers_[-1][2], [1])
# error on invalid arg
ct = ColumnTransformer([('trans1', Trans(), [0])], remainder=1)
assert_raise_message(
ValueError,
"remainder keyword needs to be one of \'drop\', \'passthrough\', "
"or estimator.", ct.fit, X_array)
assert_raise_message(
ValueError,
"remainder keyword needs to be one of \'drop\', \'passthrough\', "
"or estimator.", ct.fit_transform, X_array)
# check default for make_column_transformer
ct = make_column_transformer((Trans(), [0]))
assert ct.remainder == 'drop'
def test_classifier_single_class():
"""tests if ValueError is thrown with only one class"""
X = [[1, 2], [3, 4]]
y = [1, 1]
assert_raise_message(
ValueError, "This solver needs samples of at least 2 classes "
"in the data",
LogisticRegression(solver='sag').fit, X, y)
def test_check_array_accept_large_sparse_raise_exception(X_64bit):
# When large sparse are not allowed
msg = ("Only sparse matrices with 32-bit integer indices "
"are accepted. Got int64 indices.")
assert_raise_message(ValueError,
msg,
check_array,
X_64bit,
accept_sparse=True,
accept_large_sparse=False)
def test_agg_n_clusters():
# Test that an error is raised when n_clusters <= 0
rng = np.random.RandomState(0)
X = rng.rand(20, 10)
for n_clus in [-1, 0]:
agc = AgglomerativeClustering(n_clusters=n_clus)
msg = ("n_clusters should be an integer greater than 0."
" %s was provided." % str(agc.n_clusters))
assert_raise_message(ValueError, msg, agc.fit, X)
def test_gpr_correct_error_message():
X = np.arange(12).reshape(6, -1)
y = np.ones(6)
kernel = DotProduct()
gpr = GaussianProcessRegressor(kernel=kernel, alpha=0.0)
assert_raise_message(
np.linalg.LinAlgError, "The kernel, %s, is not returning a "
"positive definite matrix. Try gradually increasing "
"the 'alpha' parameter of your "
"GaussianProcessRegressor estimator." % kernel, gpr.fit, X, y)
def test_too_many_samples_to_find_a_safe_embedding():
data, _ = make_sparse_random_data(1000, 100, 1000)
for RandomProjection in all_RandomProjection:
rp = RandomProjection(n_components='auto', eps=0.1)
expected_msg = (
'eps=0.100000 and n_samples=1000 lead to a target dimension'
' of 5920 which is larger than the original space with'
' n_features=100')
assert_raise_message(ValueError, expected_msg, rp.fit, data)
def test_minimum_number_of_sample_check():
# test that we check a minimum number of samples
msg = "min_samples must be no greater than"
# Compute OPTICS
X = [[1, 1]]
clust = OPTICS(max_eps=5.0 * 0.3, min_samples=10, min_cluster_size=1)
# Run the fit
assert_raise_message(ValueError, msg, clust.fit, X)
def test_bayesian_mixture_check_is_fitted():
rng = np.random.RandomState(0)
n_samples, n_features = 10, 2
# Check raise message
bgmm = BayesianGaussianMixture(random_state=rng)
X = rng.rand(n_samples, n_features)
assert_raise_message(
ValueError, 'This BayesianGaussianMixture instance is not '
'fitted yet.', bgmm.score, X)
def test_2D_transformer_output():
X_array = np.array([[0, 1, 2], [2, 4, 6]]).T
# if one transformer is dropped, test that name is still correct
ct = ColumnTransformer([('trans1', 'drop', 0), ('trans2', TransNo2D(), 1)])
assert_raise_message(ValueError, "the 'trans2' transformer should be 2D",
ct.fit_transform, X_array)
# because fit is also doing transform, this raises already on fit
assert_raise_message(ValueError, "the 'trans2' transformer should be 2D",
ct.fit, X_array)
def test_lle_init_parameters():
X = np.random.rand(5, 3)
clf = manifold.LocallyLinearEmbedding(eigen_solver="error")
msg = "unrecognized eigen_solver 'error'"
assert_raise_message(ValueError, msg, clf.fit, X)
clf = manifold.LocallyLinearEmbedding(method="error")
msg = "unrecognized method 'error'"
assert_raise_message(ValueError, msg, clf.fit, X)
