def test_check_estimator():
# tests that the estimator actually fails on "bad" estimators.
# not a complete test of all checks, which are very extensive.
# check that we have a set_params and can clone
msg = "it does not implement a 'get_params' methods"
assert_raises_regex(TypeError, msg, check_estimator, object)
# check that we have a fit method
msg = "object has no attribute 'fit'"
assert_raises_regex(AttributeError, msg, check_estimator, BaseEstimator)
# check that fit does input validation
msg = "TypeError not raised by fit"
assert_raises_regex(AssertionError, msg, check_estimator, BaseBadClassifier)
# check that predict does input validation (doesn't accept dicts in input)
msg = "Estimator doesn't check for NaN and inf in predict"
assert_raises_regex(AssertionError, msg, check_estimator, NoCheckinPredict)
# check for sparse matrix input handling
msg = "Estimator type doesn't seem to fail gracefully on sparse data"
# the check for sparse input handling prints to the stdout,
# instead of raising an error, so as not to remove the original traceback.
# that means we need to jump through some hoops to catch it.
old_stdout = sys.stdout
string_buffer = StringIO()
sys.stdout = string_buffer
try:
check_estimator(NoSparseClassifier)
except:
pass
finally:
sys.stdout = old_stdout
assert_true(msg in string_buffer.getvalue())
# doesn't error on actual estimator
check_estimator(AdaBoostClassifier)
def test_sklearn_estimator(self):
'''
Tests each regression / classification model by invoking extensive
sklearn test suite
'''
for estimator in ESTIMATORS:
check_estimator(estimator)
def __test_estimator_checks():
try:
from sklearn.utils.estimator_checks import check_estimator
except ImportError:
raise SkipTest("need scikit-learn 0.17+ for check_estimator()")
check_estimator(MSTClustering)
def test_check_estimator_clones():
# check that check_estimator doesn't modify the estimator it receives
from sklearn.datasets import load_iris
iris = load_iris()
for Estimator in [GaussianMixture, LinearRegression,
RandomForestClassifier, NMF, SGDClassifier,
MiniBatchKMeans]:
with ignore_warnings(category=FutureWarning):
# when 'est = SGDClassifier()'
est = Estimator()
set_checking_parameters(est)
set_random_state(est)
# without fitting
old_hash = joblib.hash(est)
check_estimator(est)
assert_equal(old_hash, joblib.hash(est))
with ignore_warnings(category=FutureWarning):
# when 'est = SGDClassifier()'
est = Estimator()
set_checking_parameters(est)
set_random_state(est)
# with fitting
est.fit(iris.data + 10, iris.target)
old_hash = joblib.hash(est)
check_estimator(est)
assert_equal(old_hash, joblib.hash(est))
def test_valid_estimator_syl():
"""Test whether ovk.OVKRidge is a valid sklearn estimator."""
from sklearn import __version__
# Adding patch revision number causes crash
if LooseVersion(__version__) >= LooseVersion('0.18'):
check_estimator(ovk.OVKRidge)
else:
warn('sklearn\'s check_estimator seems to be broken in __version__ <='
' 0.17.x... skipping')
def test_rca(self):
def stable_init(self, num_dims=None, pca_comps=None,
chunk_size=2, preprocessor=None):
# this init makes RCA stable for scikit-learn examples.
RCA_Supervised.__init__(self, num_chunks=2, num_dims=num_dims,
pca_comps=pca_comps, chunk_size=chunk_size,
preprocessor=preprocessor)
dRCA.__init__ = stable_init
check_estimator(dRCA)
def test_check_estimator_pairwise():
# check that check_estimator() works on estimator with _pairwise
# kernel or metric
# test precomputed kernel
est = SVC(kernel='precomputed')
check_estimator(est)
# test precomputed metric
est = KNeighborsRegressor(metric='precomputed')
check_estimator(est)
def test_sdml(self):
def stable_init(self, sparsity_param=0.01, num_labeled='deprecated',
num_constraints=None, verbose=False, preprocessor=None):
# this init makes SDML stable for scikit-learn examples.
SDML_Supervised.__init__(self, sparsity_param=sparsity_param,
num_labeled=num_labeled,
num_constraints=num_constraints,
verbose=verbose,
preprocessor=preprocessor,
balance_param=1e-5, use_cov=False)
dSDML.__init__ = stable_init
check_estimator(dSDML)
def _validate_estimator(self, default=None):
"""Check the value of alpha and beta and clustering algorithm.
"""
check_parameter(self.alpha, low=0, high=1, param_name='alpha',
include_left=False, include_right=False)
check_parameter(self.beta, low=1, param_name='beta',
include_left=False)
if self.clustering_estimator is not None:
self.clustering_estimator_ = self.clustering_estimator
else:
self.clustering_estimator_ = default
# make sure the base clustering algorithm is valid
if self.clustering_estimator_ is None:
raise ValueError("clustering algorithm cannot be None")
if self.check_estimator:
check_estimator(self.clustering_estimator_)
def _validate_estimator(self, default=None):
"""Check the estimator and the n_estimator attribute, set the
`base_estimator_` attribute."""
if not isinstance(self.n_estimators, (numbers.Integral, np.integer)):
raise ValueError("n_estimators must be an integer, "
"got {0}.".format(type(self.n_estimators)))
if self.n_estimators <= 0:
raise ValueError("n_estimators must be greater than zero, "
"got {0}.".format(self.n_estimators))
if self.base_estimator is not None:
self.base_estimator_ = self.base_estimator
else:
self.base_estimator_ = default
if self.base_estimator_ is None:
raise ValueError("base_estimator cannot be None")
# make sure estimator is consistent with sklearn
if self.check_estimator:
check_estimator(self.base_estimator_)
def test_check_estimator():
# tests that the estimator actually fails on "bad" estimators.
# not a complete test of all checks, which are very extensive.
# check that we have a set_params and can clone
msg = "it does not implement a 'get_params' methods"
assert_raises_regex(TypeError, msg, check_estimator, object)
# check that we have a fit method
msg = "object has no attribute 'fit'"
assert_raises_regex(AttributeError, msg, check_estimator, BaseEstimator)
# check that fit does input validation
msg = "TypeError not raised"
assert_raises_regex(AssertionError, msg, check_estimator, BaseBadClassifier)
# check that sample_weights in fit accepts pandas.Series type
try:
from pandas import Series # noqa
msg = (
"Estimator NoSampleWeightPandasSeriesType raises error if "
"'sample_weight' parameter is of type pandas.Series"
)
assert_raises_regex(ValueError, msg, check_estimator, NoSampleWeightPandasSeriesType)
except ImportError:
pass
# check that predict does input validation (doesn't accept dicts in input)
msg = "Estimator doesn't check for NaN and inf in predict"
assert_raises_regex(AssertionError, msg, check_estimator, NoCheckinPredict)
# check that estimator state does not change
# at transform/predict/predict_proba time
msg = "Estimator changes __dict__ during predict"
assert_raises_regex(AssertionError, msg, check_estimator, ChangesDict)
# check for sparse matrix input handling
name = NoSparseClassifier.__name__
msg = "Estimator " + name + " doesn't seem to fail gracefully on sparse data"
# the check for sparse input handling prints to the stdout,
# instead of raising an error, so as not to remove the original traceback.
# that means we need to jump through some hoops to catch it.
old_stdout = sys.stdout
string_buffer = StringIO()
sys.stdout = string_buffer
try:
check_estimator(NoSparseClassifier)
except:
pass
finally:
sys.stdout = old_stdout
assert_true(msg in string_buffer.getvalue())
# doesn't error on actual estimator
check_estimator(AdaBoostClassifier)
check_estimator(MultiTaskElasticNet)
def test_lsml(self): check_estimator(dLSML)
def test_mlkr(self): check_estimator(MLKR)
def test_nearmiss_sk_estimator():
"""Test the sklearn estimator compatibility"""
check_estimator(NearMiss)
def test_logistic_regression_estimators():
"""[Utils] LogisticRegression: check estimators."""
if check_estimator is not None:
check_estimator(LogisticRegression)
def test_common():
return check_estimator(TemplateEstimator)
def test_novelty_true_common_tests():
# the common tests are run for the default LOF (novelty=False).
# here we run these common tests for LOF when novelty=True
check_estimator(neighbors.LocalOutlierFactor(novelty=True))
def test_hdbscan_is_sklearn_estimator():
check_estimator(HDBSCAN)
def test_nearmiss_sk_estimator():
"""Test the sklearn estimator compatibility"""
check_estimator(NearMiss)
def test_check_estimator(model):
"""Test if check_estimator works."""
check_estimator(model)
def test_estimator_spherical_k_means():
return check_estimator(SphericalKMeans)
def test_ols_estimators():
"""[Utils] OLS: check estimators."""
if check_estimator is not None:
check_estimator(OLS)
def test_init_mixin():
"""[Utils] InitMixin: test mixin."""
if check_estimator is not None:
check_estimator(TestMixin)
def test_scale_estimators():
"""[Utils] Scale: check estimators"""
if check_estimator is not None:
check_estimator(Scale)
def test_cmaes(self): check_estimator(dCMAES)
def test_sklearn_integration(self):
check_estimator(self.estimator_class())
def test_mmc(self): check_estimator(dMMC)
def test_check_estimators_voting_estimator(estimator):
# FIXME: to be removed when meta-estimators can specified themselves
# their testing parameters (for required parameters).
check_estimator(estimator)
check_no_attributes_set_in_init(estimator.__class__.__name__, estimator)
def test_sklearn_estimator_checks_transformer():
"""Run the sklearn estimator validation checks on SymbolicTransformer"""
check_estimator(SymbolicTransformer)
def test_check_estimator():
# tests that the estimator actually fails on "bad" estimators.
# not a complete test of all checks, which are very extensive.
# check that we have a set_params and can clone
msg = "it does not implement a 'get_params' method"
assert_raises_regex(TypeError, msg, check_estimator, object)
assert_raises_regex(TypeError, msg, check_estimator, object())
# check that values returned by get_params match set_params
msg = "get_params result does not match what was passed to set_params"
assert_raises_regex(AssertionError, msg, check_estimator,
ModifiesValueInsteadOfRaisingError())
assert_warns(UserWarning, check_estimator, RaisesErrorInSetParams())
assert_raises_regex(AssertionError, msg, check_estimator,
ModifiesAnotherValue())
# check that we have a fit method
msg = "object has no attribute 'fit'"
assert_raises_regex(AttributeError, msg, check_estimator, BaseEstimator)
assert_raises_regex(AttributeError, msg, check_estimator, BaseEstimator())
# check that fit does input validation
msg = "ValueError not raised"
assert_raises_regex(AssertionError, msg, check_estimator,
BaseBadClassifier)
assert_raises_regex(AssertionError, msg, check_estimator,
BaseBadClassifier())
# check that sample_weights in fit accepts pandas.Series type
try:
from pandas import Series # noqa
msg = ("Estimator NoSampleWeightPandasSeriesType raises error if "
"'sample_weight' parameter is of type pandas.Series")
assert_raises_regex(ValueError, msg, check_estimator,
NoSampleWeightPandasSeriesType)
except ImportError:
pass
# check that predict does input validation (doesn't accept dicts in input)
msg = "Estimator doesn't check for NaN and inf in predict"
assert_raises_regex(AssertionError, msg, check_estimator, NoCheckinPredict)
assert_raises_regex(AssertionError, msg, check_estimator,
NoCheckinPredict())
# check that estimator state does not change
# at transform/predict/predict_proba time
msg = 'Estimator changes __dict__ during predict'
assert_raises_regex(AssertionError, msg, check_estimator, ChangesDict)
# check that `fit` only changes attribures that
# are private (start with an _ or end with a _).
msg = ('Estimator ChangesWrongAttribute should not change or mutate '
'the parameter wrong_attribute from 0 to 1 during fit.')
assert_raises_regex(AssertionError, msg, check_estimator,
ChangesWrongAttribute)
check_estimator(ChangesUnderscoreAttribute)
# check that `fit` doesn't add any public attribute
msg = (r'Estimator adds public attribute\(s\) during the fit method.'
' Estimators are only allowed to add private attributes'
' either started with _ or ended'
' with _ but wrong_attribute added')
assert_raises_regex(AssertionError, msg, check_estimator,
SetsWrongAttribute)
# check for invariant method
name = NotInvariantPredict.__name__
method = 'predict'
msg = ("{method} of {name} is not invariant when applied "
"to a subset.").format(method=method, name=name)
assert_raises_regex(AssertionError, msg, check_estimator,
NotInvariantPredict)
# check for sparse matrix input handling
name = NoSparseClassifier.__name__
msg = "Estimator %s doesn't seem to fail gracefully on sparse data" % name
# the check for sparse input handling prints to the stdout,
# instead of raising an error, so as not to remove the original traceback.
# that means we need to jump through some hoops to catch it.
old_stdout = sys.stdout
string_buffer = StringIO()
sys.stdout = string_buffer
try:
check_estimator(NoSparseClassifier)
except:
pass
finally:
sys.stdout = old_stdout
assert msg in string_buffer.getvalue()
# Large indices test on bad estimator
msg = ('Estimator LargeSparseNotSupportedClassifier doesn\'t seem to '
r'support \S{3}_64 matrix, and is not failing gracefully.*')
assert_raises_regex(AssertionError, msg, check_estimator,
LargeSparseNotSupportedClassifier)
# does error on binary_only untagged estimator
msg = 'Only 2 classes are supported'
assert_raises_regex(ValueError, msg, check_estimator,
UntaggedBinaryClassifier)
# non-regression test for estimators transforming to sparse data
check_estimator(SparseTransformer())
# doesn't error on actual estimator
check_estimator(LogisticRegression)
check_estimator(LogisticRegression(C=0.01))
check_estimator(MultiTaskElasticNet)
check_estimator(MultiTaskElasticNet())
# doesn't error on binary_only tagged estimator
check_estimator(TaggedBinaryClassifier)
# Check regressor with requires_positive_y estimator tag
msg = 'negative y values not supported!'
assert_raises_regex(ValueError, msg, check_estimator,
RequiresPositiveYRegressor)
def test_ncr_sk_estimator():
"""Test the sklearn estimator compatibility"""
check_estimator(NeighbourhoodCleaningRule)
def test_smote_sk_estimator():
"""Test the sklearn estimator compatibility"""
check_estimator(SMOTE)
def test_check_estimator():
# tests that the estimator actually fails on "bad" estimators.
# not a complete test of all checks, which are very extensive.
# check that we have a set_params and can clone
msg = "it does not implement a 'get_params' methods"
assert_raises_regex(TypeError, msg, check_estimator, object)
assert_raises_regex(TypeError, msg, check_estimator, object())
# check that we have a fit method
msg = "object has no attribute 'fit'"
assert_raises_regex(AttributeError, msg, check_estimator, BaseEstimator)
assert_raises_regex(AttributeError, msg, check_estimator, BaseEstimator())
# check that fit does input validation
msg = "TypeError not raised"
assert_raises_regex(AssertionError, msg, check_estimator,
BaseBadClassifier)
assert_raises_regex(AssertionError, msg, check_estimator,
BaseBadClassifier())
# check that sample_weights in fit accepts pandas.Series type
try:
from pandas import Series # noqa
msg = ("Estimator NoSampleWeightPandasSeriesType raises error if "
"'sample_weight' parameter is of type pandas.Series")
assert_raises_regex(
ValueError, msg, check_estimator, NoSampleWeightPandasSeriesType)
except ImportError:
pass
# check that predict does input validation (doesn't accept dicts in input)
msg = "Estimator doesn't check for NaN and inf in predict"
assert_raises_regex(AssertionError, msg, check_estimator, NoCheckinPredict)
assert_raises_regex(AssertionError, msg, check_estimator,
NoCheckinPredict())
# check that estimator state does not change
# at transform/predict/predict_proba time
msg = 'Estimator changes __dict__ during predict'
assert_raises_regex(AssertionError, msg, check_estimator, ChangesDict)
# check that `fit` only changes attribures that
# are private (start with an _ or end with a _).
msg = ('Estimator ChangesWrongAttribute should not change or mutate '
'the parameter wrong_attribute from 0 to 1 during fit.')
assert_raises_regex(AssertionError, msg,
check_estimator, ChangesWrongAttribute)
check_estimator(ChangesUnderscoreAttribute)
# check that `fit` doesn't add any public attribute
msg = ('Estimator adds public attribute\(s\) during the fit method.'
' Estimators are only allowed to add private attributes'
' either started with _ or ended'
' with _ but wrong_attribute added')
assert_raises_regex(AssertionError, msg,
check_estimator, SetsWrongAttribute)
# check for invariant method
name = NotInvariantPredict.__name__
method = 'predict'
msg = ("{method} of {name} is not invariant when applied "
"to a subset.").format(method=method, name=name)
assert_raises_regex(AssertionError, msg,
check_estimator, NotInvariantPredict)
# check for sparse matrix input handling
name = NoSparseClassifier.__name__
msg = "Estimator %s doesn't seem to fail gracefully on sparse data" % name
# the check for sparse input handling prints to the stdout,
# instead of raising an error, so as not to remove the original traceback.
# that means we need to jump through some hoops to catch it.
old_stdout = sys.stdout
string_buffer = StringIO()
sys.stdout = string_buffer
try:
check_estimator(NoSparseClassifier)
except:
pass
finally:
sys.stdout = old_stdout
assert_true(msg in string_buffer.getvalue())
# doesn't error on actual estimator
check_estimator(AdaBoostClassifier)
check_estimator(AdaBoostClassifier())
check_estimator(MultiTaskElasticNet)
check_estimator(MultiTaskElasticNet())
def test_estimator():
"""Test HDP estimator"""
return check_estimator(HierarchicalDirichletProcess)
def test_regressor():
lr = wrap(LinearRegression)
check_estimator(lr)
assert hasattr(lr, 'predict')
assert hasattr(lr, 'score')
def test_enn_sk_estimator():
"""Test the sklearn estimator compatibility"""
check_estimator(RepeatedEditedNearestNeighbours)
def test_xfail_ignored_in_check_estimator():
# Make sure checks marked as xfail are just ignored and not run by
# check_estimator(), but still raise a warning.
with warnings.catch_warnings(record=True) as records:
check_estimator(NuSVC())
assert SkipTestWarning in [rec.category for rec in records]
def test_check_estimator():
# tests that the estimator actually fails on "bad" estimators.
# not a complete test of all checks, which are very extensive.
# check that we have a set_params and can clone
msg = "Passing a class was deprecated"
with raises(TypeError, match=msg):
check_estimator(object)
msg = (
"Parameter 'p' of estimator 'HasMutableParameters' is of type "
"object which is not allowed"
)
# check that the "default_constructible" test checks for mutable parameters
check_estimator(HasImmutableParameters()) # should pass
with raises(AssertionError, match=msg):
check_estimator(HasMutableParameters())
# check that values returned by get_params match set_params
msg = "get_params result does not match what was passed to set_params"
with raises(AssertionError, match=msg):
check_estimator(ModifiesValueInsteadOfRaisingError())
assert_warns(UserWarning, check_estimator, RaisesErrorInSetParams())
with raises(AssertionError, match=msg):
check_estimator(ModifiesAnotherValue())
# check that we have a fit method
msg = "object has no attribute 'fit'"
with raises(AttributeError, match=msg):
check_estimator(BaseEstimator())
# check that fit does input validation
msg = "Did not raise"
with raises(AssertionError, match=msg):
check_estimator(BaseBadClassifier())
# check that sample_weights in fit accepts pandas.Series type
try:
from pandas import Series # noqa
msg = (
"Estimator NoSampleWeightPandasSeriesType raises error if "
"'sample_weight' parameter is of type pandas.Series"
)
with raises(ValueError, match=msg):
check_estimator(NoSampleWeightPandasSeriesType())
except ImportError:
pass
# check that predict does input validation (doesn't accept dicts in input)
msg = "Estimator doesn't check for NaN and inf in predict"
with raises(AssertionError, match=msg):
check_estimator(NoCheckinPredict())
# check that estimator state does not change
# at transform/predict/predict_proba time
msg = "Estimator changes __dict__ during predict"
with raises(AssertionError, match=msg):
check_estimator(ChangesDict())
# check that `fit` only changes attribures that
# are private (start with an _ or end with a _).
msg = (
"Estimator ChangesWrongAttribute should not change or mutate "
"the parameter wrong_attribute from 0 to 1 during fit."
)
with raises(AssertionError, match=msg):
check_estimator(ChangesWrongAttribute())
check_estimator(ChangesUnderscoreAttribute())
# check that `fit` doesn't add any public attribute
msg = (
r"Estimator adds public attribute\(s\) during the fit method."
" Estimators are only allowed to add private attributes"
" either started with _ or ended"
" with _ but wrong_attribute added"
)
with raises(AssertionError, match=msg):
check_estimator(SetsWrongAttribute())
# check for sample order invariance
name = NotInvariantSampleOrder.__name__
method = "predict"
msg = (
"{method} of {name} is not invariant when applied to a dataset"
"with different sample order."
).format(method=method, name=name)
with raises(AssertionError, match=msg):
check_estimator(NotInvariantSampleOrder())
# check for invariant method
name = NotInvariantPredict.__name__
method = "predict"
msg = ("{method} of {name} is not invariant when applied " "to a subset.").format(
method=method, name=name
)
with raises(AssertionError, match=msg):
check_estimator(NotInvariantPredict())
# check for sparse matrix input handling
name = NoSparseClassifier.__name__
msg = "Estimator %s doesn't seem to fail gracefully on sparse data" % name
with raises(AssertionError, match=msg):
check_estimator(NoSparseClassifier())
# Large indices test on bad estimator
msg = (
"Estimator LargeSparseNotSupportedClassifier doesn't seem to "
r"support \S{3}_64 matrix, and is not failing gracefully.*"
)
with raises(AssertionError, match=msg):
check_estimator(LargeSparseNotSupportedClassifier())
# does error on binary_only untagged estimator
msg = "Only 2 classes are supported"
with raises(ValueError, match=msg):
check_estimator(UntaggedBinaryClassifier())
# non-regression test for estimators transforming to sparse data
check_estimator(SparseTransformer())
# doesn't error on actual estimator
check_estimator(LogisticRegression())
check_estimator(LogisticRegression(C=0.01))
check_estimator(MultiTaskElasticNet())
# doesn't error on binary_only tagged estimator
check_estimator(TaggedBinaryClassifier())
# Check regressor with requires_positive_y estimator tag
msg = "negative y values not supported!"
with raises(ValueError, match=msg):
check_estimator(RequiresPositiveYRegressor())
# Does not raise error on classifier with poor_score tag
check_estimator(PoorScoreLogisticRegression())
def test_nca(self): check_estimator(NCA)
def test_check_estimator_transformer_no_mixin():
# check that TransformerMixin is not required for transformer tests to run
with raises(AttributeError, ".*fit_transform.*"):
check_estimator(BadTransformerWithoutMixin())
def test_itml(self): check_estimator(dITML)
def test_layer():
"""[Module | LayerEnsemble] test pass estimator checks"""
check_estimator(Tmp)
def test_jde(self): check_estimator(dJDE)
def test_check_estimator(self):
# run VW through the sklearn estimator validation check
# skip check until https://github.com/scikit-learn/scikit-learn/issues/16799 is closed
return
check_estimator(self.estimator())
def test_iht_sk_estimator():
"""Test the sklearn estimator compatibility"""
check_estimator(InstanceHardnessThreshold)
def test_check_estimator(self):
self.assertIsNone(check_estimator(self.sut))
def test_estimator():
from sklearn.utils.estimator_checks import check_estimator
check_estimator(FlexibleLinearRegression)
def test_all_estimators(Estimator):
return check_estimator(Estimator)
def test_bc_sk_estimator():
"""Test the sklearn estimator compatibility"""
check_estimator(BalanceCascade)
def test_KNeighborsClassifier(self):
check_estimator(KNeighborsClassifier(algorithm='kd_tree'))
def test_estimator_interface(self):
estimator_checks.check_estimator(LogitNet)
def test_check_estimator():
# tests that the estimator actually fails on "bad" estimators.
# not a complete test of all checks, which are very extensive.
# check that we have a set_params and can clone
msg = "it does not implement a 'get_params' methods"
assert_raises_regex(TypeError, msg, check_estimator, object)
assert_raises_regex(TypeError, msg, check_estimator, object())
# check that we have a fit method
msg = "object has no attribute 'fit'"
assert_raises_regex(AttributeError, msg, check_estimator, BaseEstimator)
assert_raises_regex(AttributeError, msg, check_estimator, BaseEstimator())
# check that fit does input validation
msg = "TypeError not raised"
assert_raises_regex(AssertionError, msg, check_estimator,
BaseBadClassifier)
assert_raises_regex(AssertionError, msg, check_estimator,
BaseBadClassifier())
# check that sample_weights in fit accepts pandas.Series type
try:
from pandas import Series # noqa
msg = ("Estimator NoSampleWeightPandasSeriesType raises error if "
"'sample_weight' parameter is of type pandas.Series")
assert_raises_regex(ValueError, msg, check_estimator,
NoSampleWeightPandasSeriesType)
except ImportError:
pass
# check that predict does input validation (doesn't accept dicts in input)
msg = "Estimator doesn't check for NaN and inf in predict"
assert_raises_regex(AssertionError, msg, check_estimator, NoCheckinPredict)
assert_raises_regex(AssertionError, msg, check_estimator,
NoCheckinPredict())
# check that estimator state does not change
# at transform/predict/predict_proba time
msg = 'Estimator changes __dict__ during predict'
assert_raises_regex(AssertionError, msg, check_estimator, ChangesDict)
# check that `fit` only changes attribures that
# are private (start with an _ or end with a _).
msg = ('Estimator ChangesWrongAttribute should not change or mutate '
'the parameter wrong_attribute from 0 to 1 during fit.')
assert_raises_regex(AssertionError, msg, check_estimator,
ChangesWrongAttribute)
check_estimator(ChangesUnderscoreAttribute)
# check that `fit` doesn't add any public attribute
msg = (r'Estimator adds public attribute\(s\) during the fit method.'
' Estimators are only allowed to add private attributes'
' either started with _ or ended'
' with _ but wrong_attribute added')
assert_raises_regex(AssertionError, msg, check_estimator,
SetsWrongAttribute)
# check for invariant method
name = NotInvariantPredict.__name__
method = 'predict'
msg = ("{method} of {name} is not invariant when applied "
"to a subset.").format(method=method, name=name)
assert_raises_regex(AssertionError, msg, check_estimator,
NotInvariantPredict)
# check for sparse matrix input handling
name = NoSparseClassifier.__name__
msg = "Estimator %s doesn't seem to fail gracefully on sparse data" % name
# the check for sparse input handling prints to the stdout,
# instead of raising an error, so as not to remove the original traceback.
# that means we need to jump through some hoops to catch it.
old_stdout = sys.stdout
string_buffer = StringIO()
sys.stdout = string_buffer
try:
check_estimator(NoSparseClassifier)
except:
pass
finally:
sys.stdout = old_stdout
assert_true(msg in string_buffer.getvalue())
# doesn't error on actual estimator
check_estimator(AdaBoostClassifier)
check_estimator(AdaBoostClassifier())
check_estimator(MultiTaskElasticNet)
check_estimator(MultiTaskElasticNet())
def test_sklearn_estimator(self):
check_estimator(self.clf)
def test_cnn_sk_estimator():
"""Test the sklearn estimator compatibility"""
check_estimator(CondensedNearestNeighbour)
def test_enn_sk_estimator():
"""Test the sklearn estimator compatibility"""
check_estimator(RepeatedEditedNearestNeighbours)
def test_ros_sk_estimator():
"""Test the sklearn estimator compatibility"""
check_estimator(RandomOverSampler)
def test_GBTDAALClassifier(self):
check_estimator(GBTDAALClassifier)
def test_check_estimator():
check_estimator(SingleBest)
def test_ada_sk_estimator():
"""Test the sklearn estimator compatibility"""
check_estimator(ADASYN)
def test_AdaBoostClassifier(self):
check_estimator(AdaBoostClassifier)
