def test_parameters_default_constructible(estimator):
name = estimator.__class__.__name__
if sk_version >= parse_version("0.24"):
Estimator = estimator
else:
Estimator = estimator.__class__
sklearn_checks.check_parameters_default_constructible(name, Estimator)
def check_estimator(Estimator, run_sampler_tests=True):
"""Check if estimator adheres to scikit-learn conventions and
imbalanced-learn
This estimator will run an extensive test-suite for input validation,
shapes, etc.
Additional tests samplers if the Estimator inherits from the corresponding
mixin from imblearn.base
Parameters
----------
Estimator : class
Class to check. Estimator is a class object (not an instance)
run_sampler_tests=True : bool, default=True
Will run or not the samplers tests.
"""
name = Estimator.__name__
# monkey patch check_dtype_object for the sampler allowing strings
import sklearn.utils.estimator_checks
sklearn.utils.estimator_checks.check_dtype_object = \
monkey_patch_check_dtype_object
# scikit-learn common tests
sklearn_check_estimator(Estimator)
check_parameters_default_constructible(name, Estimator)
if run_sampler_tests:
for check in _yield_all_checks(name, Estimator):
check(name, Estimator)
def test_sklearn_api():
name = DataFrameETL.__name__
check_parameters_default_constructible(name, DataFrameETL)
check_no_fit_attributes_set_in_init(name, DataFrameETL)
estimator = DataFrameETL()
for check in [
check_transformers_unfitted,
check_transformer_n_iter,
check_get_params_invariance]:
check(name, estimator)
# these are known failures
for check in [
check_transformer_data_not_an_array,
check_transformer_general,
check_fit2d_predict1d,
check_fit2d_1sample,
check_fit2d_1feature,
check_fit1d_1feature,
check_fit1d_1sample,
check_dict_unchanged,
check_dont_overwrite_parameters]:
with pytest.raises(TypeError) as e:
check(name, estimator)
assert (
"ETL transformer must be fit "
"to a dataframe.") in str(e.value)
def check_estimator(Estimator, run_sampler_tests=True):
"""Check if estimator adheres to scikit-learn conventions and
imbalanced-learn
This estimator will run an extensive test-suite for input validation,
shapes, etc.
Additional tests samplers if the Estimator inherits from the corresponding
mixin from imblearn.base
Parameters
----------
Estimator : class
Class to check. Estimator is a class object (not an instance)
run_sampler_tests=True : bool, default=True
Will run or not the samplers tests.
"""
name = Estimator.__name__
# monkey patch check_dtype_object for the sampler allowing strings
import sklearn.utils.estimator_checks
sklearn.utils.estimator_checks.check_dtype_object = \
monkey_patch_check_dtype_object
# scikit-learn common tests
sklearn_check_estimator(Estimator)
check_parameters_default_constructible(name, Estimator)
if run_sampler_tests:
for check in _yield_all_checks(name, Estimator):
check(name, Estimator)
def custom_check_estimator(Estimator):
# Same as sklearn.check_estimator, skipping tests that can't succeed.
if isinstance(Estimator, type):
# got a class
name = Estimator.__name__
estimator = Estimator()
check_parameters_default_constructible(name, Estimator)
check_no_attributes_set_in_init(name, estimator)
else:
# got an instance
estimator = Estimator
name = type(estimator).__name__
for check in _yield_all_checks(name, estimator):
if (check is estimator_checks.check_estimators_dtypes
or check is estimator_checks.check_fit_score_takes_y
or check is estimator_checks.check_dtype_object
or check is estimator_checks.check_sample_weights_list
or check is estimator_checks.check_estimators_overwrite_params
or check is estimator_checks.check_classifiers_classes
or check is estimator_checks.check_supervised_y_2d
or check is estimator_checks.check_fit2d_predict1d
or check is estimator_checks.check_class_weight_classifiers
or check is estimator_checks.check_methods_subset_invariance
or check is estimator_checks.check_dont_overwrite_parameters
or "check_estimators_fit_returns_self" in check.__repr__()
or "check_classifiers_train" in check.__repr__()):
continue
try:
check(name, estimator)
except SkipTest as exception:
# the only SkipTest thrown currently results from not
# being able to import pandas.
warnings.warn(str(exception), SkipTestWarning)
def test_class_support_deprecated():
# Make sure passing classes to check_estimator or parametrize_with_checks
# is deprecated
msg = "Passing a class is deprecated"
with pytest.warns(FutureWarning, match=msg):
check_estimator(LogisticRegression)
with pytest.warns(FutureWarning, match=msg):
parametrize_with_checks([LogisticRegression])
# Make sure check_parameters_default_constructible accepts instances now
check_parameters_default_constructible('name', LogisticRegression())
def check_estimator_autofeat(Estimator):
# usually, this would be
# from sklearn.utils.estimator_checks import check_estimator
# but first this issue needs to be resolved:
# https://github.com/pandas-dev/pandas/issues/26247
# check class
name = Estimator.__name__
estimator = Estimator()
check_parameters_default_constructible(name, Estimator)
check_no_attributes_set_in_init(name, estimator)
# check with fewer feateng steps and featsel runs to speed things up
check_estimator(
Estimator(feateng_steps=1, featsel_runs=1, featsel_max_it=20))
def test_sklearn_integration(self):
# we cannot use `check_estimator` directly since there is no skip test mechanism
for name, estimator in ((lgb.sklearn.LGBMClassifier.__name__, lgb.sklearn.LGBMClassifier),
(lgb.sklearn.LGBMRegressor.__name__, lgb.sklearn.LGBMRegressor)):
check_parameters_default_constructible(name, estimator)
# we cannot leave default params (see https://github.com/microsoft/LightGBM/issues/833)
estimator = estimator(min_child_samples=1, min_data_in_bin=1)
for check in _yield_all_checks(name, estimator):
check_name = check.func.__name__ if hasattr(check, 'func') else check.__name__
if check_name == 'check_estimators_nan_inf':
continue # skip test because LightGBM deals with nan
try:
check(name, estimator)
except SkipTest as message:
warnings.warn(message, SkipTestWarning)
def test_sklearn_integration(self):
# we cannot use `check_estimator` directly since there is no skip test mechanism
for name, estimator in ((lgb.sklearn.LGBMClassifier.__name__, lgb.sklearn.LGBMClassifier),
(lgb.sklearn.LGBMRegressor.__name__, lgb.sklearn.LGBMRegressor)):
check_parameters_default_constructible(name, estimator)
check_no_fit_attributes_set_in_init(name, estimator)
# we cannot leave default params (see https://github.com/Microsoft/LightGBM/issues/833)
estimator = estimator(min_child_samples=1, min_data_in_bin=1)
for check in _yield_all_checks(name, estimator):
if check.__name__ == 'check_estimators_nan_inf':
continue # skip test because LightGBM deals with nan
try:
check(name, estimator)
except SkipTest as message:
warnings.warn(message, SkipTestWarning)
def test_sklearn_integration(self):
# sklearn <0.19 cannot accept instance, but many tests could be passed only with min_data=1 and min_data_in_bin=1
if sklearn_at_least_019:
# we cannot use `check_estimator` directly since there is no skip test mechanism
for name, estimator in ((lgb.sklearn.LGBMClassifier.__name__, lgb.sklearn.LGBMClassifier),
(lgb.sklearn.LGBMRegressor.__name__, lgb.sklearn.LGBMRegressor)):
check_parameters_default_constructible(name, estimator)
check_no_fit_attributes_set_in_init(name, estimator)
# we cannot leave default params (see https://github.com/Microsoft/LightGBM/issues/833)
estimator = estimator(min_child_samples=1, min_data_in_bin=1)
for check in _yield_all_checks(name, estimator):
if check.__name__ == 'check_estimators_nan_inf':
continue # skip test because LightGBM deals with nan
try:
check(name, estimator)
except SkipTest as message:
warnings.warn(message, SkipTestWarning)
def check_estimator(Estimator):
"""Check if estimator adheres to scikit-learn conventions.
This estimator will run an extensive test-suite for input validation,
shapes, etc.
Additional tests for classifiers, regressors, clustering or transformers
will be run if the Estimator class inherits from the corresponding mixin
from sklearn.base.
This test can be applied to classes or instances.
Classes currently have some additional tests that related to construction,
while passing instances allows the testing of multiple options.
Parameters
----------
estimator : estimator object or class
Estimator to check. Estimator is a class object or instance.
"""
if isinstance(Estimator, type):
# got a class
name = Estimator.__name__
estimator = Estimator()
check_parameters_default_constructible(name, Estimator)
check_no_attributes_set_in_init(name, estimator)
else:
# got an instance
estimator = Estimator
name = type(estimator).__name__
if hasattr(estimator, 'max_iter'):
if (isinstance(estimator, ShapeletModel)
or isinstance(estimator, SerializableShapeletModel)):
estimator.set_params(max_iter=100)
else:
estimator.set_params(max_iter=10)
if hasattr(estimator, 'total_lengths'):
estimator.set_params(total_lengths=1)
if hasattr(estimator, 'probability'):
estimator.set_params(probability=True)
for check in checks._yield_all_checks(name, estimator):
try:
check(name, estimator)
except SkipTest as exception:
# the only SkipTest thrown currently results from not
# being able to import pandas.
warnings.warn(str(exception), SkipTestWarning)
def check_estimator(Estimator):
"""Check if estimator adheres to scikit-learn conventions and
imbalanced-learn
This estimator will run an extensive test-suite for input validation,
shapes, etc.
Additional tests samplers if the Estimator inherits from the corresponding
mixin from imblearn.base
Parameters
----------
Estimator : class
Class to check. Estimator is a class object (not an instance).
"""
name = Estimator.__name__
# test scikit-learn compatibility
sklearn_check_estimator(Estimator)
check_parameters_default_constructible(name, Estimator)
for check in _yield_all_checks(name, Estimator):
check(name, Estimator)
def check_estimator(Estimator):
"""Check if estimator adheres to scikit-learn conventions and
imbalanced-learn
This estimator will run an extensive test-suite for input validation,
shapes, etc.
Additional tests samplers if the Estimator inherits from the corresponding
mixin from imblearn.base
Parameters
----------
Estimator : class
Class to check. Estimator is a class object (not an instance).
"""
name = Estimator.__name__
# test scikit-learn compatibility
sklearn_check_estimator(Estimator)
check_parameters_default_constructible(name, Estimator)
for check in _yield_all_checks(name, Estimator):
check(name, Estimator)
def rewritten_check_estimator(Estimator):
# Same as sklearn.check_estimator, re-writing tests that can't succeed.
if isinstance(Estimator, type):
# got a class
name = Estimator.__name__
estimator = Estimator()
check_parameters_default_constructible(name, Estimator)
check_no_attributes_set_in_init(name, estimator)
else:
# got an instance
estimator = Estimator
name = type(estimator).__name__
for check in _yield_rewritten_checks(name, estimator):
try:
check(name, estimator)
except SkipTest as exception:
# the only SkipTest thrown currently results from not
# being able to import pandas.
warnings.warn(str(exception), SkipTestWarning)
def check_estimator(Estimator):
"""Check if estimator adheres to scikit-learn conventions.
This estimator will run an extensive test-suite for input validation,
shapes, etc.
Additional tests for classifiers, regressors, clustering or transformers
will be run if the Estimator class inherits from the corresponding mixin
from sklearn.base.
This test can be applied to classes or instances.
Classes currently have some additional tests that related to construction,
while passing instances allows the testing of multiple options.
Parameters
----------
estimator : estimator object or class
Estimator to check. Estimator is a class object or instance.
"""
warnings.filterwarnings(action='ignore', category=DataConversionWarning)
if isinstance(Estimator, type):
# got a class
name = Estimator.__name__
estimator = Estimator()
check_parameters_default_constructible(name, Estimator)
check_no_attributes_set_in_init(name, estimator)
else:
# got an instance
estimator = Estimator
name = type(estimator).__name__
for check in _yield_all_checks(name, estimator):
if hasattr(check, "__name__"):
if check.__name__ == "check_estimators_nan_inf":
# we allow NaNs in transform...
continue
print("##", check.__name__)
try:
check(name, estimator)
except SkipTest as exception:
# the only SkipTest thrown currently results from not
# being able to import pandas.
warnings.warn(str(exception), SkipTestWarning)
def test_parameters_default_constructible(name, Estimator):
# Test that estimators are default-constructible
check_parameters_default_constructible(name, Estimator)
def test_parameters_default_constructible(name, Estimator):
# Test that estimators are default-constructible
check_parameters_default_constructible(name, Estimator)
def test_parameters_default_constructible():
checks.check_parameters_default_constructible(NAME, CLF)
def test_parameters_default_constructible(estimator):
name, Estimator = estimator.__class__.__name__, estimator.__class__
sklearn_checks.check_parameters_default_constructible(name, Estimator)
