def test_raises_value_error_if_sample_weights_greater_than_1d():
# Sample weights must be either scalar or 1D
n_sampless = [2, 3]
n_featuress = [3, 2]
rng = np.random.RandomState(42)
for n_samples, n_features in zip(n_sampless, n_featuress):
X = rng.randn(n_samples, n_features)
y = rng.randn(n_samples)
sample_weights_OK = rng.randn(n_samples)**2 + 1
sample_weights_OK_1 = 1.
sample_weights_OK_2 = 2.
sample_weights_not_OK = sample_weights_OK[:, np.newaxis]
sample_weights_not_OK_2 = sample_weights_OK[np.newaxis, :]
ridge = Ridge(alpha=1)
# make sure the "OK" sample weights actually work
ridge.fit(X, y, sample_weights_OK)
ridge.fit(X, y, sample_weights_OK_1)
ridge.fit(X, y, sample_weights_OK_2)
def fit_ridge_not_ok():
ridge.fit(X, y, sample_weights_not_OK)
def fit_ridge_not_ok_2():
ridge.fit(X, y, sample_weights_not_OK_2)
assert_raise_message(ValueError,
"Sample weights must be 1D array or scalar",
fit_ridge_not_ok)
assert_raise_message(ValueError,
"Sample weights must be 1D array or scalar",
fit_ridge_not_ok_2)
def test_gaussian_mixture_predict_predict_proba():
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
Y = rand_data.Y
g = GaussianMixture(n_components=rand_data.n_components,
random_state=rng,
weights_init=rand_data.weights,
means_init=rand_data.means,
precisions_init=rand_data.precisions[covar_type],
covariance_type=covar_type)
# Check a warning message arrive if we don't do fit
assert_raise_message(
NotFittedError, "This GaussianMixture instance is not fitted "
"yet. Call 'fit' with appropriate arguments "
"before using this method.", g.predict, X)
g.fit(X)
Y_pred = g.predict(X)
Y_pred_proba = g.predict_proba(X).argmax(axis=1)
assert_array_equal(Y_pred, Y_pred_proba)
assert adjusted_rand_score(Y, Y_pred) > .95
def test_warm_start():
X = X_iris
y = y_iris
y_2classes = np.array([0] * 75 + [1] * 75)
y_3classes = np.array([0] * 40 + [1] * 40 + [2] * 70)
y_3classes_alt = np.array([0] * 50 + [1] * 50 + [3] * 50)
y_4classes = np.array([0] * 37 + [1] * 37 + [2] * 38 + [3] * 38)
y_5classes = np.array([0] * 30 + [1] * 30 + [2] * 30 + [3] * 30 + [4] * 30)
# No error raised
clf = MLPClassifier(hidden_layer_sizes=2, solver='lbfgs',
warm_start=True).fit(X, y)
clf.fit(X, y)
clf.fit(X, y_3classes)
for y_i in (y_2classes, y_3classes_alt, y_4classes, y_5classes):
clf = MLPClassifier(hidden_layer_sizes=2,
solver='lbfgs',
warm_start=True).fit(X, y)
message = ('warm_start can only be used where `y` has the same '
'classes as in the previous call to fit.'
' Previously got [0 1 2], `y` has %s' % np.unique(y_i))
assert_raise_message(ValueError, message, clf.fit, X, y_i)
def test_column_transformer_special_strings():
# one 'drop' -> ignore
X_array = np.array([[0., 1., 2.], [2., 4., 6.]]).T
ct = ColumnTransformer([('trans1', Trans(), [0]), ('trans2', 'drop', [1])])
exp = np.array([[0.], [1.], [2.]])
assert_array_equal(ct.fit_transform(X_array), exp)
assert_array_equal(ct.fit(X_array).transform(X_array), exp)
assert len(ct.transformers_) == 2
assert ct.transformers_[-1][0] != 'remainder'
# all 'drop' -> return shape 0 array
ct = ColumnTransformer([('trans1', 'drop', [0]), ('trans2', 'drop', [1])])
assert_array_equal(ct.fit(X_array).transform(X_array).shape, (3, 0))
assert_array_equal(ct.fit_transform(X_array).shape, (3, 0))
assert len(ct.transformers_) == 2
assert ct.transformers_[-1][0] != 'remainder'
# 'passthrough'
X_array = np.array([[0., 1., 2.], [2., 4., 6.]]).T
ct = ColumnTransformer([('trans1', Trans(), [0]),
('trans2', 'passthrough', [1])])
exp = X_array
assert_array_equal(ct.fit_transform(X_array), exp)
assert_array_equal(ct.fit(X_array).transform(X_array), exp)
assert len(ct.transformers_) == 2
assert ct.transformers_[-1][0] != 'remainder'
# None itself / other string is not valid
for val in [None, 'other']:
ct = ColumnTransformer([('trans1', Trans(), [0]),
('trans2', None, [1])])
assert_raise_message(TypeError, "All estimators should implement",
ct.fit_transform, X_array)
assert_raise_message(TypeError, "All estimators should implement",
ct.fit, X_array)
def test_column_transformer_error_msg_1D():
X_array = np.array([[0., 1., 2.], [2., 4., 6.]]).T
col_trans = ColumnTransformer([('trans', StandardScaler(), 0)])
assert_raise_message(ValueError, "1D data passed to a transformer",
col_trans.fit, X_array)
assert_raise_message(ValueError, "1D data passed to a transformer",
col_trans.fit_transform, X_array)
col_trans = ColumnTransformer([('trans', TransRaise(), 0)])
for func in [col_trans.fit, col_trans.fit_transform]:
assert_raise_message(ValueError, "specific message", func, X_array)
def test_error_messages_on_wrong_input():
for score_func in score_funcs:
expected = ('labels_true and labels_pred must have same size,'
' got 2 and 3')
assert_raise_message(ValueError, expected, score_func,
[0, 1], [1, 1, 1])
expected = "labels_true must be 1D: shape is (2"
assert_raise_message(ValueError, expected, score_func,
[[0, 1], [1, 0]], [1, 1, 1])
expected = "labels_pred must be 1D: shape is (2"
assert_raise_message(ValueError, expected, score_func,
[0, 1, 0], [[1, 1], [0, 0]])
def test_params_validation():
# Test that invalid parameters raise value error
X = np.arange(12).reshape(4, 3)
y = [1, 1, 2, 2]
NCA = NeighborhoodComponentsAnalysis
rng = np.random.RandomState(42)
# TypeError
assert_raises(TypeError, NCA(max_iter='21').fit, X, y)
assert_raises(TypeError, NCA(verbose='true').fit, X, y)
assert_raises(TypeError, NCA(tol='1').fit, X, y)
assert_raises(TypeError, NCA(n_components='invalid').fit, X, y)
assert_raises(TypeError, NCA(warm_start=1).fit, X, y)
# ValueError
assert_raise_message(ValueError,
"`init` must be 'auto', 'pca', 'lda', 'identity', "
"'random' or a numpy array of shape "
"(n_components, n_features).",
NCA(init=1).fit, X, y)
assert_raise_message(ValueError,
'`max_iter`= -1, must be >= 1.',
NCA(max_iter=-1).fit, X, y)
init = rng.rand(5, 3)
assert_raise_message(ValueError,
'The output dimensionality ({}) of the given linear '
'transformation `init` cannot be greater than its '
'input dimensionality ({}).'
.format(init.shape[0], init.shape[1]),
NCA(init=init).fit, X, y)
n_components = 10
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(n_components=n_components).fit, X, y)
def test_column_transformer_get_feature_names():
X_array = np.array([[0., 1., 2.], [2., 4., 6.]]).T
ct = ColumnTransformer([('trans', Trans(), [0, 1])])
# raise correct error when not fitted
with pytest.raises(NotFittedError):
ct.get_feature_names()
# raise correct error when no feature names are available
ct.fit(X_array)
assert_raise_message(
AttributeError, "Transformer trans (type Trans) does not provide "
"get_feature_names", ct.get_feature_names)
# working example
X = np.array([[{
'a': 1,
'b': 2
}, {
'a': 3,
'b': 4
}], [{
'c': 5
}, {
'c': 6
}]],
dtype=object).T
ct = ColumnTransformer([('col' + str(i), DictVectorizer(), i)
for i in range(2)])
ct.fit(X)
assert ct.get_feature_names() == ['col0__a', 'col0__b', 'col1__c']
# passthrough transformers not supported
ct = ColumnTransformer([('trans', 'passthrough', [0, 1])])
ct.fit(X)
assert_raise_message(NotImplementedError,
'get_feature_names is not yet supported',
ct.get_feature_names)
ct = ColumnTransformer([('trans', DictVectorizer(), 0)],
remainder='passthrough')
ct.fit(X)
assert_raise_message(NotImplementedError,
'get_feature_names is not yet supported',
ct.get_feature_names)
# drop transformer
ct = ColumnTransformer([('col0', DictVectorizer(), 0),
('col1', 'drop', 1)])
ct.fit(X)
assert ct.get_feature_names() == ['col0__a', 'col0__b']
def test_fetch_openml_raises_illegal_argument():
assert_raise_message(ValueError,
"Dataset data_id=",
fetch_openml,
data_id=-1,
name="name")
assert_raise_message(ValueError,
"Dataset data_id=",
fetch_openml,
data_id=-1,
name=None,
version="version")
assert_raise_message(ValueError,
"Dataset data_id=",
fetch_openml,
data_id=-1,
name="name",
version="version")
assert_raise_message(
ValueError, "Neither name nor data_id are provided. "
"Please provide name or data_id.", fetch_openml)
def test_assert_allclose_dense_sparse():
x = np.arange(9).reshape(3, 3)
msg = "Not equal to tolerance "
y = sparse.csc_matrix(x)
for X in [x, y]:
# basic compare
assert_raise_message(AssertionError, msg, assert_allclose_dense_sparse,
X, X * 2)
assert_allclose_dense_sparse(X, X)
assert_raise_message(ValueError, "Can only compare two sparse",
assert_allclose_dense_sparse, x, y)
A = sparse.diags(np.ones(5), offsets=0).tocsr()
B = sparse.csr_matrix(np.ones((1, 5)))
assert_raise_message(AssertionError, "Arrays are not equal",
assert_allclose_dense_sparse, B, A)
def test_check_weights():
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
n_components = rand_data.n_components
X = rand_data.X['full']
g = GaussianMixture(n_components=n_components)
# Check bad shape
weights_bad_shape = rng.rand(n_components, 1)
g.weights_init = weights_bad_shape
assert_raise_message(
ValueError, "The parameter 'weights' should have the shape of "
"(%d,), but got %s" % (n_components, str(weights_bad_shape.shape)),
g.fit, X)
# Check bad range
weights_bad_range = rng.rand(n_components) + 1
g.weights_init = weights_bad_range
assert_raise_message(
ValueError, "The parameter 'weights' should be in the range "
"[0, 1], but got max value %.5f, min value %.5f" %
(np.min(weights_bad_range), np.max(weights_bad_range)), g.fit, X)
# Check bad normalization
weights_bad_norm = rng.rand(n_components)
weights_bad_norm = weights_bad_norm / (weights_bad_norm.sum() + 1)
g.weights_init = weights_bad_norm
assert_raise_message(
ValueError, "The parameter 'weights' should be normalized, "
"but got sum(weights) = %.5f" % np.sum(weights_bad_norm), g.fit, X)
# Check good weights matrix
weights = rand_data.weights
g = GaussianMixture(weights_init=weights, n_components=n_components)
g.fit(X)
assert_array_equal(weights, g.weights_init)
def test_l1_min_c_l2_loss():
# loss='l2' should raise ValueError
assert_raise_message(ValueError, "loss type not in",
l1_min_c, dense_X, Y1, "l2")
def test_bayesian_mixture_precisions_prior_initialisation():
rng = np.random.RandomState(0)
n_samples, n_features = 10, 2
X = rng.rand(n_samples, n_features)
# Check raise message for a bad value of degrees_of_freedom_prior
bad_degrees_of_freedom_prior_ = n_features - 1.
bgmm = BayesianGaussianMixture(
degrees_of_freedom_prior=bad_degrees_of_freedom_prior_,
random_state=rng)
assert_raise_message(
ValueError, "The parameter 'degrees_of_freedom_prior' should be "
"greater than %d, but got %.3f." %
(n_features - 1, bad_degrees_of_freedom_prior_), bgmm.fit, X)
# Check correct init for a given value of degrees_of_freedom_prior
degrees_of_freedom_prior = rng.rand() + n_features - 1.
bgmm = BayesianGaussianMixture(
degrees_of_freedom_prior=degrees_of_freedom_prior,
random_state=rng).fit(X)
assert_almost_equal(degrees_of_freedom_prior,
bgmm.degrees_of_freedom_prior_)
# Check correct init for the default value of degrees_of_freedom_prior
degrees_of_freedom_prior_default = n_features
bgmm = BayesianGaussianMixture(
degrees_of_freedom_prior=degrees_of_freedom_prior_default,
random_state=rng).fit(X)
assert_almost_equal(degrees_of_freedom_prior_default,
bgmm.degrees_of_freedom_prior_)
# Check correct init for a given value of covariance_prior
covariance_prior = {
'full': np.cov(X.T, bias=1) + 10,
'tied': np.cov(X.T, bias=1) + 5,
'diag': np.diag(np.atleast_2d(np.cov(X.T, bias=1))) + 3,
'spherical': rng.rand()
}
bgmm = BayesianGaussianMixture(random_state=rng)
for cov_type in ['full', 'tied', 'diag', 'spherical']:
bgmm.covariance_type = cov_type
bgmm.covariance_prior = covariance_prior[cov_type]
bgmm.fit(X)
assert_almost_equal(covariance_prior[cov_type], bgmm.covariance_prior_)
# Check raise message for a bad spherical value of covariance_prior
bad_covariance_prior_ = -1.
bgmm = BayesianGaussianMixture(covariance_type='spherical',
covariance_prior=bad_covariance_prior_,
random_state=rng)
assert_raise_message(
ValueError, "The parameter 'spherical covariance_prior' "
"should be greater than 0., but got %.3f." % bad_covariance_prior_,
bgmm.fit, X)
# Check correct init for the default value of covariance_prior
covariance_prior_default = {
'full': np.atleast_2d(np.cov(X.T)),
'tied': np.atleast_2d(np.cov(X.T)),
'diag': np.var(X, axis=0, ddof=1),
'spherical': np.var(X, axis=0, ddof=1).mean()
}
bgmm = BayesianGaussianMixture(random_state=0)
for cov_type in ['full', 'tied', 'diag', 'spherical']:
bgmm.covariance_type = cov_type
bgmm.fit(X)
assert_almost_equal(covariance_prior_default[cov_type],
bgmm.covariance_prior_)
def assert_raises_on_only_one_label(func):
"""Assert message when there is only one label"""
rng = np.random.RandomState(seed=0)
assert_raise_message(ValueError, "Number of labels is", func,
rng.rand(10, 2), np.zeros(10))
def assert_raises_on_all_points_same_cluster(func):
"""Assert message when all point are in different clusters"""
rng = np.random.RandomState(seed=0)
assert_raise_message(ValueError, "Number of labels is", func,
rng.rand(10, 2), np.arange(10))
def test_fast_mcd_on_invalid_input():
X = np.arange(100)
assert_raise_message(ValueError, 'Expected 2D array, got 1D array instead',
fast_mcd, X)
def test_max_iter_error():
km = KMeans(max_iter=-1)
assert_raise_message(ValueError, 'Number of iterations should be', km.fit,
X)
def test_check_classification_targets():
# Test that check_classification_target return correct type. #5782
y = np.array([0.0, 1.1, 2.0, 3.0])
msg = type_of_target(y)
assert_raise_message(ValueError, msg, check_classification_targets, y)
def test_check_docstring_parameters():
try:
import numpydoc # noqa
except ImportError:
raise SkipTest("numpydoc is required to test the docstrings")
incorrect = check_docstring_parameters(f_ok)
assert incorrect == []
incorrect = check_docstring_parameters(f_ok, ignore=['b'])
assert incorrect == []
incorrect = check_docstring_parameters(f_missing, ignore=['b'])
assert incorrect == []
assert_raise_message(RuntimeError, 'Unknown section Results',
check_docstring_parameters, f_bad_sections)
assert_raise_message(RuntimeError, 'Unknown section Parameter',
check_docstring_parameters, Klass.f_bad_sections)
incorrect = check_docstring_parameters(f_check_param_definition)
assert (incorrect == [
"mrex.utils.tests.test_testing.f_check_param_definition There "
"was no space between the param name and colon ('a: int')",
"mrex.utils.tests.test_testing.f_check_param_definition There "
"was no space between the param name and colon ('b:')",
"mrex.utils.tests.test_testing.f_check_param_definition "
"Parameter 'c :' has an empty type spec. Remove the colon",
"mrex.utils.tests.test_testing.f_check_param_definition There "
"was no space between the param name and colon ('d:int')",
])
messages = [
[
"In function: mrex.utils.tests.test_testing.f_bad_order",
"There's a parameter name mismatch in function docstring w.r.t."
" function signature, at index 0 diff: 'b' != 'a'", "Full diff:",
"- ['b', 'a']", "+ ['a', 'b']"
],
[
"In function: " +
"mrex.utils.tests.test_testing.f_too_many_param_docstring",
"Parameters in function docstring have more items w.r.t. function"
" signature, first extra item: c", "Full diff:", "- ['a', 'b']",
"+ ['a', 'b', 'c']", "? +++++"
],
[
"In function: mrex.utils.tests.test_testing.f_missing",
"Parameters in function docstring have less items w.r.t. function"
" signature, first missing item: b", "Full diff:", "- ['a', 'b']",
"+ ['a']"
],
[
"In function: mrex.utils.tests.test_testing.Klass.f_missing",
"Parameters in function docstring have less items w.r.t. function"
" signature, first missing item: X", "Full diff:", "- ['X', 'y']",
"+ []"
],
[
"In function: " +
"mrex.utils.tests.test_testing.MockMetaEstimator.predict",
"There's a parameter name mismatch in function docstring w.r.t."
" function signature, at index 0 diff: 'X' != 'y'", "Full diff:",
"- ['X']", "? ^", "+ ['y']", "? ^"
],
[
"In function: " +
"mrex.utils.tests.test_testing.MockMetaEstimator." +
"predict_proba",
"Parameters in function docstring have less items w.r.t. function"
" signature, first missing item: X", "Full diff:", "- ['X']",
"+ []"
],
[
"In function: " +
"mrex.utils.tests.test_testing.MockMetaEstimator.score",
"Parameters in function docstring have less items w.r.t. function"
" signature, first missing item: X", "Full diff:", "- ['X']",
"+ []"
],
[
"In function: " +
"mrex.utils.tests.test_testing.MockMetaEstimator.fit",
"Parameters in function docstring have less items w.r.t. function"
" signature, first missing item: X", "Full diff:", "- ['X', 'y']",
"+ []"
],
]
mock_meta = MockMetaEstimator(delegate=MockEst())
for msg, f in zip(messages, [
f_bad_order, f_too_many_param_docstring, f_missing,
Klass.f_missing, mock_meta.predict, mock_meta.predict_proba,
mock_meta.score, mock_meta.fit
]):
incorrect = check_docstring_parameters(f)
assert msg == incorrect, ('\n"%s"\n not in \n"%s"' % (msg, incorrect))
def test_meanshift_all_orphans():
# init away from the data, crash with a sensible warning
ms = MeanShift(bandwidth=0.1, seeds=[[-9, -9], [-10, -10]])
msg = "No point was within bandwidth=0.1"
assert_raise_message(ValueError, msg, ms.fit, X,)
def test_mcd_class_on_invalid_input():
X = np.arange(100)
mcd = MinCovDet()
assert_raise_message(ValueError, 'Expected 2D array, got 1D array instead',
mcd.fit, X)
def test_gaussian_mixture_attributes():
# test bad parameters
rng = np.random.RandomState(0)
X = rng.rand(10, 2)
n_components_bad = 0
gmm = GaussianMixture(n_components=n_components_bad)
assert_raise_message(
ValueError, "Invalid value for 'n_components': %d "
"Estimation requires at least one component" % n_components_bad,
gmm.fit, X)
# covariance_type should be in [spherical, diag, tied, full]
covariance_type_bad = 'bad_covariance_type'
gmm = GaussianMixture(covariance_type=covariance_type_bad)
assert_raise_message(
ValueError, "Invalid value for 'covariance_type': %s "
"'covariance_type' should be in "
"['spherical', 'tied', 'diag', 'full']" % covariance_type_bad, gmm.fit,
X)
tol_bad = -1
gmm = GaussianMixture(tol=tol_bad)
assert_raise_message(
ValueError, "Invalid value for 'tol': %.5f "
"Tolerance used by the EM must be non-negative" % tol_bad, gmm.fit, X)
reg_covar_bad = -1
gmm = GaussianMixture(reg_covar=reg_covar_bad)
assert_raise_message(
ValueError, "Invalid value for 'reg_covar': %.5f "
"regularization on covariance must be "
"non-negative" % reg_covar_bad, gmm.fit, X)
max_iter_bad = 0
gmm = GaussianMixture(max_iter=max_iter_bad)
assert_raise_message(
ValueError, "Invalid value for 'max_iter': %d "
"Estimation requires at least one iteration" % max_iter_bad, gmm.fit,
X)
n_init_bad = 0
gmm = GaussianMixture(n_init=n_init_bad)
assert_raise_message(
ValueError, "Invalid value for 'n_init': %d "
"Estimation requires at least one run" % n_init_bad, gmm.fit, X)
init_params_bad = 'bad_method'
gmm = GaussianMixture(init_params=init_params_bad)
assert_raise_message(
ValueError,
"Unimplemented initialization method '%s'" % init_params_bad, gmm.fit,
X)
# test good parameters
n_components, tol, n_init, max_iter, reg_covar = 2, 1e-4, 3, 30, 1e-1
covariance_type, init_params = 'full', 'random'
gmm = GaussianMixture(n_components=n_components,
tol=tol,
n_init=n_init,
max_iter=max_iter,
reg_covar=reg_covar,
covariance_type=covariance_type,
init_params=init_params).fit(X)
assert gmm.n_components == n_components
assert gmm.covariance_type == covariance_type
assert gmm.tol == tol
assert gmm.reg_covar == reg_covar
assert gmm.max_iter == max_iter
assert gmm.n_init == n_init
assert gmm.init_params == init_params
def test_set_pipeline_step_passthrough(passthrough):
X = np.array([[1]])
y = np.array([1])
mult2 = Mult(mult=2)
mult3 = Mult(mult=3)
mult5 = Mult(mult=5)
def make():
return Pipeline([('m2', mult2), ('m3', mult3), ('last', mult5)])
pipeline = make()
exp = 2 * 3 * 5
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal([exp], pipeline.fit(X).predict(X))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
pipeline.set_params(m3=passthrough)
exp = 2 * 5
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal([exp], pipeline.fit(X).predict(X))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
assert (pipeline.get_params(deep=True) ==
{'steps': pipeline.steps,
'm2': mult2,
'm3': passthrough,
'last': mult5,
'memory': None,
'm2__mult': 2,
'last__mult': 5,
'verbose': False
})
pipeline.set_params(m2=passthrough)
exp = 5
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal([exp], pipeline.fit(X).predict(X))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
# for other methods, ensure no AttributeErrors on None:
other_methods = ['predict_proba', 'predict_log_proba',
'decision_function', 'transform', 'score']
for method in other_methods:
getattr(pipeline, method)(X)
pipeline.set_params(m2=mult2)
exp = 2 * 5
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal([exp], pipeline.fit(X).predict(X))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
pipeline = make()
pipeline.set_params(last=passthrough)
# mult2 and mult3 are active
exp = 6
assert_array_equal([[exp]], pipeline.fit(X, y).transform(X))
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
assert_raise_message(AttributeError,
"'str' object has no attribute 'predict'",
getattr, pipeline, 'predict')
# Check 'passthrough' step at construction time
exp = 2 * 5
pipeline = Pipeline(
[('m2', mult2), ('m3', passthrough), ('last', mult5)])
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal([exp], pipeline.fit(X).predict(X))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
def test_check_array():
# accept_sparse == False
# raise error on sparse inputs
X = [[1, 2], [3, 4]]
X_csr = sp.csr_matrix(X)
assert_raises(TypeError, check_array, X_csr)
# ensure_2d=False
X_array = check_array([0, 1, 2], ensure_2d=False)
assert X_array.ndim == 1
# ensure_2d=True with 1d array
assert_raise_message(ValueError,
'Expected 2D array, got 1D array instead',
check_array, [0, 1, 2],
ensure_2d=True)
# ensure_2d=True with scalar array
assert_raise_message(ValueError,
'Expected 2D array, got scalar array instead',
check_array,
10,
ensure_2d=True)
# don't allow ndim > 3
X_ndim = np.arange(8).reshape(2, 2, 2)
assert_raises(ValueError, check_array, X_ndim)
check_array(X_ndim, allow_nd=True) # doesn't raise
# dtype and order enforcement.
X_C = np.arange(4).reshape(2, 2).copy("C")
X_F = X_C.copy("F")
X_int = X_C.astype(np.int)
X_float = X_C.astype(np.float)
Xs = [X_C, X_F, X_int, X_float]
dtypes = [np.int32, np.int, np.float, np.float32, None, np.bool, object]
orders = ['C', 'F', None]
copys = [True, False]
for X, dtype, order, copy in product(Xs, dtypes, orders, copys):
X_checked = check_array(X, dtype=dtype, order=order, copy=copy)
if dtype is not None:
assert X_checked.dtype == dtype
else:
assert X_checked.dtype == X.dtype
if order == 'C':
assert X_checked.flags['C_CONTIGUOUS']
assert not X_checked.flags['F_CONTIGUOUS']
elif order == 'F':
assert X_checked.flags['F_CONTIGUOUS']
assert not X_checked.flags['C_CONTIGUOUS']
if copy:
assert X is not X_checked
else:
# doesn't copy if it was already good
if (X.dtype == X_checked.dtype and X_checked.flags['C_CONTIGUOUS']
== X.flags['C_CONTIGUOUS']
and X_checked.flags['F_CONTIGUOUS']
== X.flags['F_CONTIGUOUS']):
assert X is X_checked
# allowed sparse != None
X_csc = sp.csc_matrix(X_C)
X_coo = X_csc.tocoo()
X_dok = X_csc.todok()
X_int = X_csc.astype(np.int)
X_float = X_csc.astype(np.float)
Xs = [X_csc, X_coo, X_dok, X_int, X_float]
accept_sparses = [['csr', 'coo'], ['coo', 'dok']]
for X, dtype, accept_sparse, copy in product(Xs, dtypes, accept_sparses,
copys):
with warnings.catch_warnings(record=True) as w:
X_checked = check_array(X,
dtype=dtype,
accept_sparse=accept_sparse,
copy=copy)
if (dtype is object or sp.isspmatrix_dok(X)) and len(w):
message = str(w[0].message)
messages = [
"object dtype is not supported by sparse matrices",
"Can't check dok sparse matrix for nan or inf."
]
assert message in messages
else:
assert len(w) == 0
if dtype is not None:
assert X_checked.dtype == dtype
else:
assert X_checked.dtype == X.dtype
if X.format in accept_sparse:
# no change if allowed
assert X.format == X_checked.format
else:
# got converted
assert X_checked.format == accept_sparse[0]
if copy:
assert X is not X_checked
else:
# doesn't copy if it was already good
if X.dtype == X_checked.dtype and X.format == X_checked.format:
assert X is X_checked
# other input formats
# convert lists to arrays
X_dense = check_array([[1, 2], [3, 4]])
assert isinstance(X_dense, np.ndarray)
# raise on too deep lists
assert_raises(ValueError, check_array, X_ndim.tolist())
check_array(X_ndim.tolist(), allow_nd=True) # doesn't raise
# convert weird stuff to arrays
X_no_array = NotAnArray(X_dense)
result = check_array(X_no_array)
assert isinstance(result, np.ndarray)
# deprecation warning if string-like array with dtype="numeric"
expected_warn_regex = r"converted to decimal numbers if dtype='numeric'"
X_str = [['11', '12'], ['13', 'xx']]
for X in [X_str, np.array(X_str, dtype='U'), np.array(X_str, dtype='S')]:
with pytest.warns(FutureWarning, match=expected_warn_regex):
check_array(X, dtype="numeric")
# deprecation warning if byte-like array with dtype="numeric"
X_bytes = [[b'a', b'b'], [b'c', b'd']]
for X in [X_bytes, np.array(X_bytes, dtype='V1')]:
with pytest.warns(FutureWarning, match=expected_warn_regex):
check_array(X, dtype="numeric")
def test_check_X_y_informative_error():
X = np.ones((2, 2))
y = None
assert_raise_message(ValueError, "y cannot be None", check_X_y, X, y)
def test_check_array_min_samples_and_features_messages():
# empty list is considered 2D by default:
msg = "0 feature(s) (shape=(1, 0)) while a minimum of 1 is required."
assert_raise_message(ValueError, msg, check_array, [[]])
# If considered a 1D collection when ensure_2d=False, then the minimum
# number of samples will break:
msg = "0 sample(s) (shape=(0,)) while a minimum of 1 is required."
assert_raise_message(ValueError, msg, check_array, [], ensure_2d=False)
# Invalid edge case when checking the default minimum sample of a scalar
msg = "Singleton array array(42) cannot be considered a valid collection."
assert_raise_message(TypeError, msg, check_array, 42, ensure_2d=False)
# Simulate a model that would need at least 2 samples to be well defined
X = np.ones((1, 10))
y = np.ones(1)
msg = "1 sample(s) (shape=(1, 10)) while a minimum of 2 is required."
assert_raise_message(ValueError,
msg,
check_X_y,
X,
y,
ensure_min_samples=2)
# The same message is raised if the data has 2 dimensions even if this is
# not mandatory
assert_raise_message(ValueError,
msg,
check_X_y,
X,
y,
ensure_min_samples=2,
ensure_2d=False)
# Simulate a model that would require at least 3 features (e.g. SelectKBest
# with k=3)
X = np.ones((10, 2))
y = np.ones(2)
msg = "2 feature(s) (shape=(10, 2)) while a minimum of 3 is required."
assert_raise_message(ValueError,
msg,
check_X_y,
X,
y,
ensure_min_features=3)
# Only the feature check is enabled whenever the number of dimensions is 2
# even if allow_nd is enabled:
assert_raise_message(ValueError,
msg,
check_X_y,
X,
y,
ensure_min_features=3,
allow_nd=True)
# Simulate a case where a pipeline stage as trimmed all the features of a
# 2D dataset.
X = np.empty(0).reshape(10, 0)
y = np.ones(10)
msg = "0 feature(s) (shape=(10, 0)) while a minimum of 1 is required."
assert_raise_message(ValueError, msg, check_X_y, X, y)
# nd-data is not checked for any minimum number of features by default:
X = np.ones((10, 0, 28, 28))
y = np.ones(10)
X_checked, y_checked = check_X_y(X, y, allow_nd=True)
assert_array_equal(X, X_checked)
assert_array_equal(y, y_checked)
def test_estimator_init():
eclf = VotingClassifier(estimators=[])
msg = ('Invalid `estimators` attribute, `estimators` should be'
' a list of (string, estimator) tuples')
assert_raise_message(AttributeError, msg, eclf.fit, X, y)
clf = LogisticRegression(random_state=1)
eclf = VotingClassifier(estimators=[('lr', clf)], voting='error')
msg = ('Voting must be \'soft\' or \'hard\'; got (voting=\'error\')')
assert_raise_message(ValueError, msg, eclf.fit, X, y)
eclf = VotingClassifier(estimators=[('lr', clf)], weights=[1, 2])
msg = ('Number of `estimators` and weights must be equal'
'; got 2 weights, 1 estimators')
assert_raise_message(ValueError, msg, eclf.fit, X, y)
eclf = VotingClassifier(estimators=[('lr', clf), ('lr', clf)],
weights=[1, 2])
msg = "Names provided are not unique: ['lr', 'lr']"
assert_raise_message(ValueError, msg, eclf.fit, X, y)
eclf = VotingClassifier(estimators=[('lr__', clf)])
msg = "Estimator names must not contain __: got ['lr__']"
assert_raise_message(ValueError, msg, eclf.fit, X, y)
eclf = VotingClassifier(estimators=[('estimators', clf)])
msg = "Estimator names conflict with constructor arguments: ['estimators']"
assert_raise_message(ValueError, msg, eclf.fit, X, y)
def test_estimate_bandwidth_with_sparse_matrix():
# Test estimate_bandwidth with sparse matrix
X = sparse.lil_matrix((1000, 1000))
msg = "A sparse matrix was passed, but dense data is required."
assert_raise_message(TypeError, msg, estimate_bandwidth, X, 200)
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_rational_quadratic_kernel():
kernel = RationalQuadratic(length_scale=[1., 1.])
assert_raise_message(
AttributeError, "RationalQuadratic kernel only supports isotropic "
"version, please use a single "
"scalar for length_scale", kernel, X)
