def test_score_memmap():
# Ensure a scalar score of memmap type is accepted
iris = load_iris()
X, y = iris.data, iris.target
clf = MockClassifier()
tf = tempfile.NamedTemporaryFile(mode='wb', delete=False)
tf.write(b'Hello world!!!!!')
tf.close()
scores = np.memmap(tf.name, dtype=np.float64)
score = np.memmap(tf.name, shape=(), mode='r', dtype=np.float64)
try:
cross_val_score(clf, X, y, scoring=lambda est, X, y: score)
# non-scalar should still fail
assert_raises(ValueError,
cross_val_score,
clf,
X,
y,
scoring=lambda est, X, y: scores)
finally:
# Best effort to release the mmap file handles before deleting the
# backing file under Windows
scores, score = None, None
for _ in range(3):
try:
os.unlink(tf.name)
break
except WindowsError:
sleep(1.)
def test_cross_val_score_sparse_fit_params():
iris = load_iris()
X, y = iris.data, iris.target
clf = MockClassifier()
fit_params = {'sparse_sample_weight': coo_matrix(np.eye(X.shape[0]))}
a = cross_val_score(clf, X, y, fit_params=fit_params)
assert_array_equal(a, np.ones(3))
def test_cross_val_score_fit_params():
clf = MockClassifier()
n_samples = X.shape[0]
n_classes = len(np.unique(y))
W_sparse = coo_matrix((np.array([1]), (np.array([1]), np.array([0]))),
shape=(10, 1))
P_sparse = coo_matrix(np.eye(5))
DUMMY_INT = 42
DUMMY_STR = '42'
DUMMY_OBJ = object()
def assert_fit_params(clf):
# Function to test that the values are passed correctly to the
# classifier arguments for non-array type
assert_equal(clf.dummy_int, DUMMY_INT)
assert_equal(clf.dummy_str, DUMMY_STR)
assert_equal(clf.dummy_obj, DUMMY_OBJ)
fit_params = {
'sample_weight': np.ones(n_samples),
'class_prior': np.ones(n_classes) / n_classes,
'sparse_sample_weight': W_sparse,
'sparse_param': P_sparse,
'dummy_int': DUMMY_INT,
'dummy_str': DUMMY_STR,
'dummy_obj': DUMMY_OBJ,
'callback': assert_fit_params
}
cross_val_score(clf, X, y, fit_params=fit_params)
def test_cross_val_score_allow_nans():
# Check that cross_val_score allows input data with NaNs
X = np.arange(200, dtype=np.float64).reshape(10, -1)
X[2, :] = np.nan
y = np.repeat([0, 1], X.shape[0] / 2)
p = Pipeline([
('imputer', Imputer(strategy='mean', missing_values='NaN')),
('classifier', MockClassifier()),
])
cross_val_score(p, X, y, cv=5)
def test_cross_val_score_score_func():
clf = MockClassifier()
_score_func_args = []
def score_func(y_test, y_predict):
_score_func_args.append((y_test, y_predict))
return 1.0
with warnings.catch_warnings(record=True):
scoring = make_scorer(score_func)
score = cross_val_score(clf, X, y, scoring=scoring)
assert_array_equal(score, [1.0, 1.0, 1.0])
assert len(_score_func_args) == 3
def test_cross_val_score():
clf = MockClassifier()
for a in range(-10, 10):
clf.a = a
# Smoke test
scores = cross_val_score(clf, X, y2)
assert_array_equal(scores, clf.score(X, y2))
# test with multioutput y
multioutput_y = np.column_stack([y2, y2[::-1]])
scores = cross_val_score(clf, X_sparse, multioutput_y)
assert_array_equal(scores, clf.score(X_sparse, multioutput_y))
scores = cross_val_score(clf, X_sparse, y2)
assert_array_equal(scores, clf.score(X_sparse, y2))
# test with multioutput y
scores = cross_val_score(clf, X_sparse, multioutput_y)
assert_array_equal(scores, clf.score(X_sparse, multioutput_y))
# test with X and y as list
list_check = lambda x: isinstance(x, list)
clf = CheckingClassifier(check_X=list_check)
scores = cross_val_score(clf, X.tolist(), y2.tolist())
clf = CheckingClassifier(check_y=list_check)
scores = cross_val_score(clf, X, y2.tolist())
assert_raises(ValueError, cross_val_score, clf, X, y2, scoring="sklearn")
# test with 3d X and
X_3d = X[:, :, np.newaxis]
clf = MockClassifier(allow_nd=True)
scores = cross_val_score(clf, X_3d, y2)
clf = MockClassifier(allow_nd=False)
assert_raises(ValueError, cross_val_score, clf, X_3d, y2)