def test_class_weight_auto_classifiers():
"""Test that class_weight="auto" improves f1-score"""
# This test is broken; its success depends on:
# * a rare fortuitous RNG seed for make_classification; and
# * the use of binary F1 over a seemingly arbitrary positive class for two
# datasets, and weighted average F1 for the third.
# Its expectations need to be clarified and reimplemented.
raise SkipTest("This test requires redefinition")
classifiers = all_estimators(type_filter="classifier")
clean_warning_registry()
with warnings.catch_warnings(record=True):
classifiers = [c for c in classifiers if "class_weight" in c[1]().get_params().keys()]
for n_classes, weights in zip([2, 3], [[0.8, 0.2], [0.8, 0.1, 0.1]]):
# create unbalanced dataset
X, y = make_classification(
n_classes=n_classes, n_samples=200, n_features=10, weights=weights, random_state=0, n_informative=n_classes
)
X = StandardScaler().fit_transform(X)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=0)
for name, Classifier in classifiers:
if (
name != "NuSVC"
# the sparse version has a parameter that doesn't do anything
and not name.startswith("RidgeClassifier")
# RidgeClassifier behaves unexpected
# FIXME!
and not name.endswith("NB")
):
# NaiveBayes classifiers have a somewhat different interface.
# FIXME SOON!
yield (check_class_weight_auto_classifiers, name, Classifier, X_train, y_train, X_test, y_test, weights)
def test_auc_score_non_binary_class():
# Test that roc_auc_score function returns an error when trying
# to compute AUC for non-binary class values.
rng = check_random_state(404)
y_pred = rng.rand(10)
# y_true contains only one class value
y_true = np.zeros(10, dtype="int")
assert_raise_message(ValueError, "ROC AUC score is not defined", roc_auc_score, y_true, y_pred)
y_true = np.ones(10, dtype="int")
assert_raise_message(ValueError, "ROC AUC score is not defined", roc_auc_score, y_true, y_pred)
y_true = -np.ones(10, dtype="int")
assert_raise_message(ValueError, "ROC AUC score is not defined", roc_auc_score, y_true, y_pred)
# y_true contains three different class values
y_true = rng.randint(0, 3, size=10)
assert_raise_message(ValueError, "multiclass format is not supported", roc_auc_score, y_true, y_pred)
clean_warning_registry()
with warnings.catch_warnings(record=True):
rng = check_random_state(404)
y_pred = rng.rand(10)
# y_true contains only one class value
y_true = np.zeros(10, dtype="int")
assert_raise_message(ValueError, "ROC AUC score is not defined", roc_auc_score, y_true, y_pred)
y_true = np.ones(10, dtype="int")
assert_raise_message(ValueError, "ROC AUC score is not defined", roc_auc_score, y_true, y_pred)
y_true = -np.ones(10, dtype="int")
assert_raise_message(ValueError, "ROC AUC score is not defined", roc_auc_score, y_true, y_pred)
# y_true contains three different class values
y_true = rng.randint(0, 3, size=10)
assert_raise_message(ValueError, "multiclass format is not supported", roc_auc_score, y_true, y_pred)
def test_tfidf_no_smoothing():
X = [[1, 1, 1],
[1, 1, 0],
[1, 0, 0]]
tr = TfidfTransformer(smooth_idf=False, norm='l2')
tfidf = tr.fit_transform(X).toarray()
assert_true((tfidf >= 0).all())
# check normalization
assert_array_almost_equal((tfidf ** 2).sum(axis=1), [1., 1., 1.])
# the lack of smoothing make IDF fragile in the presence of feature with
# only zeros
X = [[1, 1, 0],
[1, 1, 0],
[1, 0, 0]]
tr = TfidfTransformer(smooth_idf=False, norm='l2')
clean_warning_registry()
with warnings.catch_warnings(record=True) as w:
1. / np.array([0.])
numpy_provides_div0_warning = len(w) == 1
in_warning_message = 'divide by zero'
tfidf = assert_warns_message(RuntimeWarning, in_warning_message,
tr.fit_transform, X).toarray()
if not numpy_provides_div0_warning:
raise SkipTest("Numpy does not provide div 0 warnings.")
def test_configure():
# Smoke test the 'configure' step of setup, this tests all the
# 'configure' functions in the setup.pys in the scikit
cwd = os.getcwd()
setup_path = os.path.abspath(os.path.join(sklearn.__path__[0], ".."))
setup_filename = os.path.join(setup_path, "setup.py")
if not os.path.exists(setup_filename):
return
try:
os.chdir(setup_path)
old_argv = sys.argv
sys.argv = ["setup.py", "config"]
clean_warning_registry()
with warnings.catch_warnings():
# The configuration spits out warnings when not finding
# Blas/Atlas development headers
warnings.simplefilter("ignore", UserWarning)
if PY3:
with open("setup.py") as f:
exec(f.read(), dict(__name__="__main__"))
else:
execfile("setup.py", dict(__name__="__main__"))
finally:
sys.argv = old_argv
os.chdir(cwd)
def _tested_linear_classifiers():
classifiers = all_estimators(type_filter='classifier')
clean_warning_registry()
with warnings.catch_warnings(record=True):
for name, clazz in classifiers:
if ('class_weight' in clazz().get_params().keys() and
issubclass(clazz, LinearClassifierMixin)):
yield name, clazz
def test_warning_scaling_integers():
# Check warning when scaling integer data
X = np.array([[1, 2, 0],
[0, 0, 0]], dtype=np.uint8)
w = "Data with input dtype uint8 was converted to float64"
clean_warning_registry()
assert_warns_message(DataConversionWarning, w, scale, X)
assert_warns_message(DataConversionWarning, w, StandardScaler().fit, X)
assert_warns_message(DataConversionWarning, w, MinMaxScaler().fit, X)
def test_warning_scaling_integers():
# Check warning when scaling integer data
X = np.array([[1, 2, 0],
[0, 0, 0]], dtype=np.uint8)
w = "assumes floating point values as input, got uint8"
clean_warning_registry()
assert_warns_message(UserWarning, w, scale, X)
assert_warns_message(UserWarning, w, StandardScaler().fit, X)
assert_warns_message(UserWarning, w, MinMaxScaler().fit, X)
def test_chi2_unused_feature():
# Unused feature should evaluate to NaN
# and should issue no runtime warning
clean_warning_registry()
with warnings.catch_warnings(record=True) as warned:
warnings.simplefilter('always')
chi, p = chi2([[1, 0], [0, 0]], [1, 0])
for w in warned:
if 'divide by zero' in repr(w):
raise AssertionError('Found unexpected warning %s' % w)
assert_array_equal(chi, [1, np.nan])
assert_array_equal(p[1], np.nan)
def test_class_weight_balanced_linear_classifiers():
classifiers = all_estimators(type_filter='classifier')
clean_warning_registry()
with warnings.catch_warnings(record=True):
linear_classifiers = [
(name, clazz)
for name, clazz in classifiers
if 'class_weight' in clazz().get_params().keys()
and issubclass(clazz, LinearClassifierMixin)]
for name, Classifier in linear_classifiers:
yield check_class_weight_balanced_linear_classifier, name, Classifier
def test_warning_scaling_integers():
"""Check warning when scaling integer data"""
X = np.array([[1, 2, 0],
[0, 0, 0]], dtype=np.uint8)
clean_warning_registry()
with warnings.catch_warnings(record=True):
warnings.simplefilter("always")
assert_warns(UserWarning, StandardScaler().fit, X)
clean_warning_registry()
with warnings.catch_warnings(record=True):
warnings.simplefilter("always")
assert_warns(UserWarning, MinMaxScaler().fit, X)
def test_recall_warnings():
assert_no_warnings(recall_score,
np.array([[1, 1], [1, 1]]),
np.array([[0, 0], [0, 0]]),
average='micro')
clean_warning_registry()
with warnings.catch_warnings(record=True) as record:
warnings.simplefilter('always')
recall_score(np.array([[0, 0], [0, 0]]),
np.array([[1, 1], [1, 1]]),
average='micro')
assert_equal(str(record.pop().message),
'Recall is ill-defined and '
'being set to 0.0 due to no true samples.')
def test_class_weight_classifiers():
# test that class_weight works and that the semantics are consistent
classifiers = all_estimators(type_filter="classifier")
clean_warning_registry()
with warnings.catch_warnings(record=True):
classifiers = [c for c in classifiers if "class_weight" in c[1]().get_params().keys()]
for name, Classifier in classifiers:
if name == "NuSVC":
# the sparse version has a parameter that doesn't do anything
continue
if name.endswith("NB"):
# NaiveBayes classifiers have a somewhat different interface.
# FIXME SOON!
continue
yield check_class_weight_classifiers, name, Classifier
def test_warn_deviance():
"""Test if mdeviance and bdeviance give deprecated warning. """
for loss in ('bdeviance', 'mdeviance'):
clean_warning_registry()
with warnings.catch_warnings(record=True) as w:
# This will raise a DataConversionWarning that we want to
# "always" raise, elsewhere the warnings gets ignored in the
# later tests, and the tests that check for this warning fail
warnings.simplefilter("always", DataConversionWarning)
clf = GradientBoostingClassifier(loss=loss)
try:
clf.fit(X, y)
except:
# mdeviance will raise ValueError because only 2 classes
pass
# deprecated warning for bdeviance and mdeviance
assert len(w) == 1
def test_fscore_warnings():
clean_warning_registry()
with warnings.catch_warnings(record=True) as record:
warnings.simplefilter('always')
for score in [f1_score, partial(fbeta_score, beta=2)]:
score(np.array([[1, 1], [1, 1]]),
np.array([[0, 0], [0, 0]]),
average='micro')
assert_equal(str(record.pop().message),
'F-score is ill-defined and '
'being set to 0.0 due to no predicted samples.')
score(np.array([[0, 0], [0, 0]]),
np.array([[1, 1], [1, 1]]),
average='micro')
assert_equal(str(record.pop().message),
'F-score is ill-defined and '
'being set to 0.0 due to no true samples.')
def test_class_weight_auto_linear_classifiers():
classifiers = all_estimators(type_filter="classifier")
clean_warning_registry()
with warnings.catch_warnings(record=True):
linear_classifiers = [
(name, clazz)
for name, clazz in classifiers
if "class_weight" in clazz().get_params().keys() and issubclass(clazz, LinearClassifierMixin)
]
for name, Classifier in linear_classifiers:
if name == "LogisticRegressionCV":
# Contrary to RidgeClassifierCV, LogisticRegressionCV use actual
# CV folds and fit a model for each CV iteration before averaging
# the coef. Therefore it is expected to not behave exactly as the
# other linear model.
continue
yield check_class_weight_auto_linear_classifier, name, Classifier
def test_configure():
# Smoke test the 'configure' step of setup, this tests all the
# 'configure' functions in the setup.pys in scikit-learn
cwd = os.getcwd()
setup_path = os.path.abspath(os.path.join(sklearn.__path__[0], '..'))
setup_filename = os.path.join(setup_path, 'setup.py')
if not os.path.exists(setup_filename):
return
try:
os.chdir(setup_path)
old_argv = sys.argv
sys.argv = ['setup.py', 'config']
clean_warning_registry()
with warnings.catch_warnings():
# The configuration spits out warnings when not finding
# Blas/Atlas development headers
warnings.simplefilter('ignore', UserWarning)
with open('setup.py') as f:
exec(f.read(), dict(__name__='__main__'))
finally:
sys.argv = old_argv
os.chdir(cwd)
def test_tfidf_no_smoothing():
X = [[1, 1, 1], [1, 1, 0], [1, 0, 0]]
tr = TfidfTransformer(smooth_idf=False, norm='l2')
tfidf = tr.fit_transform(X).toarray()
assert_true((tfidf >= 0).all())
# check normalization
assert_array_almost_equal((tfidf**2).sum(axis=1), [1., 1., 1.])
# the lack of smoothing make IDF fragile in the presence of feature with
# only zeros
X = [[1, 1, 0], [1, 1, 0], [1, 0, 0]]
tr = TfidfTransformer(smooth_idf=False, norm='l2')
clean_warning_registry()
with warnings.catch_warnings(record=True) as w:
1. / np.array([0.])
numpy_provides_div0_warning = len(w) == 1
in_warning_message = 'divide by zero'
tfidf = assert_warns_message(RuntimeWarning, in_warning_message,
tr.fit_transform, X).toarray()
if not numpy_provides_div0_warning:
raise SkipTest("Numpy does not provide div 0 warnings.")
def test_l2_deprecation():
clean_warning_registry()
with warnings.catch_warnings(record=True) as w:
assert_equal(l1_min_c(dense_X, Y1, "l2"),
l1_min_c(dense_X, Y1, "squared_hinge"))
assert_equal(w[0].category, DeprecationWarning)
def test_scaler_int():
# test that scaler converts integer input to floating
# for both sparse and dense matrices
rng = np.random.RandomState(42)
X = rng.randint(20, size=(4, 5))
X[:, 0] = 0 # first feature is always of zero
X_csr = sparse.csr_matrix(X)
X_csc = sparse.csc_matrix(X)
null_transform = StandardScaler(with_mean=False, with_std=False, copy=True)
clean_warning_registry()
with warnings.catch_warnings(record=True):
X_null = null_transform.fit_transform(X_csr)
assert_array_equal(X_null.data, X_csr.data)
X_orig = null_transform.inverse_transform(X_null)
assert_array_equal(X_orig.data, X_csr.data)
clean_warning_registry()
with warnings.catch_warnings(record=True):
scaler = StandardScaler(with_mean=False).fit(X)
X_scaled = scaler.transform(X, copy=True)
assert_false(np.any(np.isnan(X_scaled)))
clean_warning_registry()
with warnings.catch_warnings(record=True):
scaler_csr = StandardScaler(with_mean=False).fit(X_csr)
X_csr_scaled = scaler_csr.transform(X_csr, copy=True)
assert_false(np.any(np.isnan(X_csr_scaled.data)))
clean_warning_registry()
with warnings.catch_warnings(record=True):
scaler_csc = StandardScaler(with_mean=False).fit(X_csc)
X_csc_scaled = scaler_csr.transform(X_csc, copy=True)
assert_false(np.any(np.isnan(X_csc_scaled.data)))
assert_equal(scaler.mean_, scaler_csr.mean_)
assert_array_almost_equal(scaler.std_, scaler_csr.std_)
assert_equal(scaler.mean_, scaler_csc.mean_)
assert_array_almost_equal(scaler.std_, scaler_csc.std_)
assert_array_almost_equal(
X_scaled.mean(axis=0),
[0., 1.109, 1.856, 21., 1.559], 2)
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
X_csr_scaled_mean, X_csr_scaled_std = mean_variance_axis(
X_csr_scaled.astype(np.float), 0)
assert_array_almost_equal(X_csr_scaled_mean, X_scaled.mean(axis=0))
assert_array_almost_equal(X_csr_scaled_std, X_scaled.std(axis=0))
# Check that X has not been modified (copy)
assert_true(X_scaled is not X)
assert_true(X_csr_scaled is not X_csr)
X_scaled_back = scaler.inverse_transform(X_scaled)
assert_true(X_scaled_back is not X)
assert_true(X_scaled_back is not X_scaled)
assert_array_almost_equal(X_scaled_back, X)
X_csr_scaled_back = scaler_csr.inverse_transform(X_csr_scaled)
assert_true(X_csr_scaled_back is not X_csr)
assert_true(X_csr_scaled_back is not X_csr_scaled)
assert_array_almost_equal(X_csr_scaled_back.toarray(), X)
X_csc_scaled_back = scaler_csr.inverse_transform(X_csc_scaled.tocsc())
assert_true(X_csc_scaled_back is not X_csc)
assert_true(X_csc_scaled_back is not X_csc_scaled)
assert_array_almost_equal(X_csc_scaled_back.toarray(), X)
def test_l2_deprecation():
clean_warning_registry()
with warnings.catch_warnings(record=True) as w:
assert_equal(l1_min_c(dense_X, Y1, "l2"),
l1_min_c(dense_X, Y1, "squared_hinge"))
assert_equal(w[0].category, DeprecationWarning)
def test_scaler_int():
# test that scaler converts integer input to floating
# for both sparse and dense matrices
rng = np.random.RandomState(42)
X = rng.randint(20, size=(4, 5))
X[:, 0] = 0 # first feature is always of zero
X_csr = sparse.csr_matrix(X)
X_csc = sparse.csc_matrix(X)
null_transform = StandardScaler(with_mean=False, with_std=False, copy=True)
clean_warning_registry()
with warnings.catch_warnings(record=True):
X_null = null_transform.fit_transform(X_csr)
assert_array_equal(X_null.data, X_csr.data)
X_orig = null_transform.inverse_transform(X_null)
assert_array_equal(X_orig.data, X_csr.data)
clean_warning_registry()
with warnings.catch_warnings(record=True):
scaler = StandardScaler(with_mean=False).fit(X)
X_scaled = scaler.transform(X, copy=True)
assert_false(np.any(np.isnan(X_scaled)))
clean_warning_registry()
with warnings.catch_warnings(record=True):
scaler_csr = StandardScaler(with_mean=False).fit(X_csr)
X_csr_scaled = scaler_csr.transform(X_csr, copy=True)
assert_false(np.any(np.isnan(X_csr_scaled.data)))
clean_warning_registry()
with warnings.catch_warnings(record=True):
scaler_csc = StandardScaler(with_mean=False).fit(X_csc)
X_csc_scaled = scaler_csr.transform(X_csc, copy=True)
assert_false(np.any(np.isnan(X_csc_scaled.data)))
assert_equal(scaler.mean_, scaler_csr.mean_)
assert_array_almost_equal(scaler.std_, scaler_csr.std_)
assert_equal(scaler.mean_, scaler_csc.mean_)
assert_array_almost_equal(scaler.std_, scaler_csc.std_)
assert_array_almost_equal(X_scaled.mean(axis=0),
[0., 1.109, 1.856, 21., 1.559], 2)
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
X_csr_scaled_mean, X_csr_scaled_std = mean_variance_axis(
X_csr_scaled.astype(np.float), 0)
assert_array_almost_equal(X_csr_scaled_mean, X_scaled.mean(axis=0))
assert_array_almost_equal(X_csr_scaled_std, X_scaled.std(axis=0))
# Check that X has not been modified (copy)
assert_true(X_scaled is not X)
assert_true(X_csr_scaled is not X_csr)
X_scaled_back = scaler.inverse_transform(X_scaled)
assert_true(X_scaled_back is not X)
assert_true(X_scaled_back is not X_scaled)
assert_array_almost_equal(X_scaled_back, X)
X_csr_scaled_back = scaler_csr.inverse_transform(X_csr_scaled)
assert_true(X_csr_scaled_back is not X_csr)
assert_true(X_csr_scaled_back is not X_csr_scaled)
assert_array_almost_equal(X_csr_scaled_back.toarray(), X)
X_csc_scaled_back = scaler_csr.inverse_transform(X_csc_scaled.tocsc())
assert_true(X_csc_scaled_back is not X_csc)
assert_true(X_csc_scaled_back is not X_csc_scaled)
assert_array_almost_equal(X_csc_scaled_back.toarray(), X)