def make_paragraph_for_estimator_type(estimator_type):
intro = nodes.list_item()
intro += nodes.strong(
text="Estimators that allow NaN values for type ")
intro += nodes.literal(text=f"{estimator_type}")
intro += nodes.strong(text=":\n")
exists = False
lst = nodes.bullet_list()
for name, est_class in all_estimators(type_filter=estimator_type):
with suppress(SkipTest):
est = _construct_instance(est_class)
if est._get_tags().get("allow_nan"):
module_name = ".".join(est_class.__module__.split(".")[:2])
class_title = f"{est_class.__name__}"
class_url = f"generated/{module_name}.{class_title}.html"
item = nodes.list_item()
para = nodes.paragraph()
para += nodes.reference(class_title,
text=class_title,
internal=False,
refuri=class_url)
exists = True
item += para
lst += item
intro += lst
return [intro] if exists else None
def _tested_estimators(type_filter=None):
for name, Estimator in all_estimators(type_filter=type_filter):
try:
estimator = _construct_instance(Estimator)
except SkipTest:
continue
yield estimator
def _tested_estimators():
for name, Estimator in all_estimators():
try:
estimator = _construct_instance(Estimator)
except SkipTest:
continue
yield estimator
def test_fit_docstring_attributes(name, Estimator):
pytest.importorskip("numpydoc")
from numpydoc import docscrape
if Estimator.__name__ in _DOCSTRING_IGNORES:
return
doc = docscrape.ClassDoc(Estimator)
attributes = doc["Attributes"]
if Estimator.__name__ == "Pipeline":
est = _construct_compose_pipeline_instance(Estimator)
else:
est = _construct_instance(Estimator)
X, y = make_classification(
n_samples=20,
n_features=3,
n_redundant=0,
n_classes=2,
random_state=2,
)
y = _enforce_estimator_tags_y(est, y)
X = _enforce_estimator_tags_x(est, X)
if "oob_score" in est.get_params():
est.set_params(oob_score=True)
if is_sampler(est):
est.fit_resample(X, y)
else:
est.fit(X, y)
skipped_attributes = set([])
for attr in attributes:
if attr.name in skipped_attributes:
continue
desc = " ".join(attr.desc).lower()
# As certain attributes are present "only" if a certain parameter is
# provided, this checks if the word "only" is present in the attribute
# description, and if not the attribute is required to be present.
if "only " in desc:
continue
# ignore deprecation warnings
with ignore_warnings(category=FutureWarning):
assert hasattr(est, attr.name)
fit_attr = _get_all_fitted_attributes(est)
fit_attr_names = [attr.name for attr in attributes]
undocumented_attrs = set(fit_attr).difference(fit_attr_names)
undocumented_attrs = set(undocumented_attrs).difference(skipped_attributes)
if undocumented_attrs:
raise AssertionError(
f"Undocumented attributes for {Estimator.__name__}: {undocumented_attrs}"
)
def _tested_estimators():
for name, Estimator in all_estimators():
if issubclass(Estimator, BiclusterMixin):
continue
try:
estimator = _construct_instance(Estimator)
except SkipTest:
continue
yield estimator
def _tested_estimators():
for name, Estimator in all_estimators():
try:
estimator = _construct_instance(Estimator)
set_random_state(estimator)
except SkipTest:
continue
if isinstance(estimator, NearMiss):
# For NearMiss, let's check the three algorithms
for version in (1, 2, 3):
yield clone(estimator).set_params(version=version)
else:
yield estimator
def test_fit_docstring_attributes(name, Estimator):
pytest.importorskip("numpydoc")
from numpydoc import docscrape
doc = docscrape.ClassDoc(Estimator)
attributes = doc["Attributes"]
if Estimator.__name__ in (
"HalvingRandomSearchCV",
"RandomizedSearchCV",
"HalvingGridSearchCV",
"GridSearchCV",
):
est = _construct_searchcv_instance(Estimator)
elif Estimator.__name__ in (
"ColumnTransformer",
"Pipeline",
"FeatureUnion",
):
est = _construct_compose_pipeline_instance(Estimator)
elif Estimator.__name__ == "SparseCoder":
est = _construct_sparse_coder(Estimator)
else:
est = _construct_instance(Estimator)
if Estimator.__name__ == "SelectKBest":
est.set_params(k=2)
elif Estimator.__name__ == "DummyClassifier":
est.set_params(strategy="stratified")
elif Estimator.__name__ == "CCA" or Estimator.__name__.startswith("PLS"):
# default = 2 is invalid for single target
est.set_params(n_components=1)
elif Estimator.__name__ in (
"GaussianRandomProjection",
"SparseRandomProjection",
):
# default="auto" raises an error with the shape of `X`
est.set_params(n_components=2)
# FIXME: TO BE REMOVED in 1.4 (avoid FutureWarning)
if Estimator.__name__ in (
"OrthogonalMatchingPursuit",
"OrthogonalMatchingPursuitCV",
"Lars",
"LarsCV",
"LassoLars",
"LassoLarsCV",
"LassoLarsIC",
):
est.set_params(normalize=False)
# FIXME: TO BE REMOVED for 1.2 (avoid FutureWarning)
if Estimator.__name__ == "TSNE":
est.set_params(learning_rate=200.0, init="random")
# FIXME: TO BE REMOVED for 1.3 (avoid FutureWarning)
if Estimator.__name__ == "SequentialFeatureSelector":
est.set_params(n_features_to_select="auto")
# For PLS, TODO remove in 1.1
skipped_attributes = {"x_scores_", "y_scores_"}
# FIXME: TO BE REMOVED for 1.3 (avoid FutureWarning)
if Estimator.__name__ == "FastICA":
est.set_params(whiten="unit-variance")
if Estimator.__name__.endswith("Vectorizer"):
# Vectorizer require some specific input data
if Estimator.__name__ in (
"CountVectorizer",
"HashingVectorizer",
"TfidfVectorizer",
):
X = [
"This is the first document.",
"This document is the second document.",
"And this is the third one.",
"Is this the first document?",
]
elif Estimator.__name__ == "DictVectorizer":
X = [{"foo": 1, "bar": 2}, {"foo": 3, "baz": 1}]
y = None
else:
X, y = make_classification(
n_samples=20,
n_features=3,
n_redundant=0,
n_classes=2,
random_state=2,
)
y = _enforce_estimator_tags_y(est, y)
X = _enforce_estimator_tags_x(est, X)
if "1dlabels" in est._get_tags()["X_types"]:
est.fit(y)
elif "2dlabels" in est._get_tags()["X_types"]:
est.fit(np.c_[y, y])
else:
est.fit(X, y)
for attr in attributes:
if attr.name in skipped_attributes:
continue
desc = " ".join(attr.desc).lower()
# As certain attributes are present "only" if a certain parameter is
# provided, this checks if the word "only" is present in the attribute
# description, and if not the attribute is required to be present.
if "only " in desc:
continue
# ignore deprecation warnings
with ignore_warnings(category=FutureWarning):
assert hasattr(est, attr.name)
fit_attr = _get_all_fitted_attributes(est)
fit_attr_names = [attr.name for attr in attributes]
undocumented_attrs = set(fit_attr).difference(fit_attr_names)
undocumented_attrs = set(undocumented_attrs).difference(skipped_attributes)
if undocumented_attrs:
raise AssertionError(
f"Undocumented attributes for {Estimator.__name__}: {undocumented_attrs}"
)
def test_fit_docstring_attributes(name, Estimator):
pytest.importorskip('numpydoc')
from numpydoc import docscrape
doc = docscrape.ClassDoc(Estimator)
attributes = doc['Attributes']
if Estimator.__name__ in (
"HalvingRandomSearchCV",
"RandomizedSearchCV",
"HalvingGridSearchCV",
"GridSearchCV",
):
est = _construct_searchcv_instance(Estimator)
elif Estimator.__name__ in (
"ColumnTransformer",
"Pipeline",
"FeatureUnion",
):
est = _construct_compose_pipeline_instance(Estimator)
elif Estimator.__name__ == "SparseCoder":
est = _construct_sparse_coder(Estimator)
else:
est = _construct_instance(Estimator)
if Estimator.__name__ == 'SelectKBest':
est.set_params(k=2)
elif Estimator.__name__ == 'DummyClassifier':
est.set_params(strategy="stratified")
elif Estimator.__name__ == 'CCA' or Estimator.__name__.startswith('PLS'):
# default = 2 is invalid for single target
est.set_params(n_components=1)
elif Estimator.__name__ in (
"GaussianRandomProjection",
"SparseRandomProjection",
):
# default="auto" raises an error with the shape of `X`
est.set_params(n_components=2)
# FIXME: TO BE REMOVED for 1.1 (avoid FutureWarning)
if Estimator.__name__ == 'NMF':
est.set_params(init='nndsvda')
# FIXME: TO BE REMOVED for 1.2 (avoid FutureWarning)
if Estimator.__name__ == 'TSNE':
est.set_params(learning_rate=200.0, init='random')
# For PLS, TODO remove in 1.1
skipped_attributes = {"x_scores_", "y_scores_"}
if Estimator.__name__.endswith("Vectorizer"):
# Vectorizer require some specific input data
if Estimator.__name__ in (
"CountVectorizer",
"HashingVectorizer",
"TfidfVectorizer",
):
X = [
"This is the first document.",
"This document is the second document.",
"And this is the third one.",
"Is this the first document?",
]
elif Estimator.__name__ == "DictVectorizer":
X = [{"foo": 1, "bar": 2}, {"foo": 3, "baz": 1}]
y = None
else:
X, y = make_classification(
n_samples=20,
n_features=3,
n_redundant=0,
n_classes=2,
random_state=2,
)
y = _enforce_estimator_tags_y(est, y)
X = _enforce_estimator_tags_x(est, X)
if '1dlabels' in est._get_tags()['X_types']:
est.fit(y)
elif '2dlabels' in est._get_tags()['X_types']:
est.fit(np.c_[y, y])
else:
est.fit(X, y)
module = est.__module__.split(".")[1]
if module in N_FEATURES_MODULES_TO_IGNORE:
skipped_attributes.add("n_features_in_")
for attr in attributes:
if attr.name in skipped_attributes:
continue
desc = ' '.join(attr.desc).lower()
# As certain attributes are present "only" if a certain parameter is
# provided, this checks if the word "only" is present in the attribute
# description, and if not the attribute is required to be present.
if 'only ' in desc:
continue
# ignore deprecation warnings
with ignore_warnings(category=FutureWarning):
assert hasattr(est, attr.name)
fit_attr = _get_all_fitted_attributes(est)
fit_attr_names = [attr.name for attr in attributes]
undocumented_attrs = set(fit_attr).difference(fit_attr_names)
undocumented_attrs = set(undocumented_attrs).difference(skipped_attributes)
assert not undocumented_attrs,\
"Undocumented attributes: {}".format(undocumented_attrs)
def test_fit_docstring_attributes(name, Estimator):
pytest.importorskip('numpydoc')
from numpydoc import docscrape
doc = docscrape.ClassDoc(Estimator)
attributes = doc['Attributes']
IGNORED = {'ClassifierChain', 'ColumnTransformer',
'CountVectorizer', 'DictVectorizer', 'FeatureUnion',
'GaussianRandomProjection',
'MultiOutputClassifier', 'MultiOutputRegressor',
'NoSampleWeightWrapper', 'OneVsOneClassifier',
'OutputCodeClassifier', 'Pipeline', 'RFE', 'RFECV',
'RegressorChain', 'SelectFromModel',
'SparseCoder', 'SparseRandomProjection',
'SpectralBiclustering', 'StackingClassifier',
'StackingRegressor', 'TfidfVectorizer', 'VotingClassifier',
'VotingRegressor', 'SequentialFeatureSelector',
'HalvingGridSearchCV', 'HalvingRandomSearchCV'}
if Estimator.__name__ in IGNORED or Estimator.__name__.startswith('_'):
pytest.skip("Estimator cannot be fit easily to test fit attributes")
if Estimator.__name__ in ("RandomizedSearchCV", "GridSearchCV"):
est = _construct_searchcv_instance(Estimator)
else:
est = _construct_instance(Estimator)
if Estimator.__name__ == 'SelectKBest':
est.k = 2
if Estimator.__name__ == 'DummyClassifier':
est.strategy = "stratified"
if 'PLS' in Estimator.__name__ or 'CCA' in Estimator.__name__:
est.n_components = 1 # default = 2 is invalid for single target.
# FIXME: TO BE REMOVED for 1.0 (avoid FutureWarning)
if Estimator.__name__ == 'AffinityPropagation':
est.random_state = 63
# FIXME: TO BE REMOVED for 1.1 (avoid FutureWarning)
if Estimator.__name__ == 'NMF':
est.init = 'nndsvda'
# FIXME: TO BE REMOVED for 1.2 (avoid FutureWarning)
if Estimator.__name__ == 'TSNE':
est.learning_rate = 200.0
est.init = 'random'
X, y = make_classification(n_samples=20, n_features=3,
n_redundant=0, n_classes=2,
random_state=2)
y = _enforce_estimator_tags_y(est, y)
X = _enforce_estimator_tags_x(est, X)
if '1dlabels' in est._get_tags()['X_types']:
est.fit(y)
elif '2dlabels' in est._get_tags()['X_types']:
est.fit(np.c_[y, y])
else:
est.fit(X, y)
skipped_attributes = {'x_scores_', # For PLS, TODO remove in 1.1
'y_scores_'} # For PLS, TODO remove in 1.1
module = est.__module__.split(".")[1]
if module in N_FEATURES_MODULES_TO_IGNORE:
skipped_attributes.add("n_features_in_")
for attr in attributes:
if attr.name in skipped_attributes:
continue
desc = ' '.join(attr.desc).lower()
# As certain attributes are present "only" if a certain parameter is
# provided, this checks if the word "only" is present in the attribute
# description, and if not the attribute is required to be present.
if 'only ' in desc:
continue
# ignore deprecation warnings
with ignore_warnings(category=FutureWarning):
assert hasattr(est, attr.name)
IGNORED = {'Birch', 'LarsCV', 'Lasso',
'OrthogonalMatchingPursuit'}
if Estimator.__name__ in IGNORED:
pytest.xfail(
reason="Estimator has too many undocumented attributes.")
fit_attr = [k for k in est.__dict__.keys() if k.endswith('_')
and not k.startswith('_')]
fit_attr_names = [attr.name for attr in attributes]
undocumented_attrs = set(fit_attr).difference(fit_attr_names)
undocumented_attrs = set(undocumented_attrs).difference(skipped_attributes)
assert not undocumented_attrs,\
"Undocumented attributes: {}".format(undocumented_attrs)
def test_fit_docstring_attributes(name, Estimator):
pytest.importorskip('numpydoc')
from numpydoc import docscrape
doc = docscrape.ClassDoc(Estimator)
attributes = doc['Attributes']
IGNORED = {
'ClassifierChain', 'ColumnTransformer', 'CountVectorizer',
'DictVectorizer', 'FeatureUnion', 'GaussianRandomProjection',
'GridSearchCV', 'MultiOutputClassifier', 'MultiOutputRegressor',
'NoSampleWeightWrapper', 'OneVsOneClassifier', 'OutputCodeClassifier',
'Pipeline', 'RFE', 'RFECV', 'RandomizedSearchCV', 'RegressorChain',
'SelectFromModel', 'SparseCoder', 'SparseRandomProjection',
'SpectralBiclustering', 'StackingClassifier', 'StackingRegressor',
'TfidfVectorizer', 'VotingClassifier', 'VotingRegressor'
}
if Estimator.__name__ in IGNORED or Estimator.__name__.startswith('_'):
pytest.skip("Estimator cannot be fit easily to test fit attributes")
est = _construct_instance(Estimator)
if Estimator.__name__ == 'SelectKBest':
est.k = 2
if Estimator.__name__ == 'DummyClassifier':
est.strategy = "stratified"
# TO BE REMOVED for v0.25 (avoid FutureWarning)
if Estimator.__name__ == 'AffinityPropagation':
est.random_state = 63
X, y = make_classification(n_samples=20,
n_features=3,
n_redundant=0,
n_classes=2,
random_state=2)
y = _enforce_estimator_tags_y(est, y)
X = _enforce_estimator_tags_x(est, X)
if '1dlabels' in est._get_tags()['X_types']:
est.fit(y)
elif '2dlabels' in est._get_tags()['X_types']:
est.fit(np.c_[y, y])
else:
est.fit(X, y)
skipped_attributes = {'n_features_in_'}
for attr in attributes:
if attr.name in skipped_attributes:
continue
desc = ' '.join(attr.desc).lower()
# As certain attributes are present "only" if a certain parameter is
# provided, this checks if the word "only" is present in the attribute
# description, and if not the attribute is required to be present.
if 'only ' in desc:
continue
# ignore deprecation warnings
with ignore_warnings(category=FutureWarning):
assert hasattr(est, attr.name)
IGNORED = {
'BayesianRidge', 'Birch', 'CCA', 'CategoricalNB', 'KernelCenterer',
'LarsCV', 'Lasso', 'LassoLarsIC', 'MiniBatchKMeans',
'OrthogonalMatchingPursuit', 'PLSCanonical', 'PLSSVD',
'PassiveAggressiveClassifier'
}
if Estimator.__name__ in IGNORED:
pytest.xfail(reason="Estimator has too many undocumented attributes.")
fit_attr = [
k for k in est.__dict__.keys()
if k.endswith('_') and not k.startswith('_')
]
fit_attr_names = [attr.name for attr in attributes]
undocumented_attrs = set(fit_attr).difference(fit_attr_names)
undocumented_attrs = set(undocumented_attrs).difference(skipped_attributes)
assert not undocumented_attrs,\
"Undocumented attributes: {}".format(undocumented_attrs)
