def test_check_estimator_clones():
# check that check_estimator doesn't modify the estimator it receives
from mrex.datasets import load_iris
iris = load_iris()
for Estimator in [
GaussianMixture, LinearRegression, RandomForestClassifier, NMF,
SGDClassifier, MiniBatchKMeans
]:
with ignore_warnings(category=(FutureWarning, DeprecationWarning)):
# when 'est = SGDClassifier()'
est = Estimator()
set_checking_parameters(est)
set_random_state(est)
# without fitting
old_hash = joblib.hash(est)
check_estimator(est)
assert old_hash == joblib.hash(est)
with ignore_warnings(category=(FutureWarning, DeprecationWarning)):
# 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 old_hash == joblib.hash(est)
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_check_estimator_generate_only():
estimator_cls_gen_checks = check_estimator(LogisticRegression,
generate_only=True)
all_instance_gen_checks = check_estimator(LogisticRegression(),
generate_only=True)
assert isgenerator(estimator_cls_gen_checks)
assert isgenerator(all_instance_gen_checks)
estimator_cls_checks = list(estimator_cls_gen_checks)
all_instance_checks = list(all_instance_gen_checks)
# all classes checks include check_parameters_default_constructible
assert len(estimator_cls_checks) == len(all_instance_checks) + 1
# TODO: meta-estimators like GridSearchCV has required parameters
# that do not have default values. This is expected to change in the future
with pytest.raises(SkipTest):
for estimator, check in check_estimator(GridSearchCV,
generate_only=True):
check(estimator)
def test_check_estimators_voting_estimator(estimator):
# FIXME: to be removed when meta-estimators can be specified themselves
# their testing parameters (for required parameters).
check_estimator(estimator)
check_no_attributes_set_in_init(estimator.__class__.__name__, estimator)
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_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 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
check_estimator(RequiresPositiveYRegressor)