def test_decoder_split_cv():
X, y = make_classification(n_samples=200,
n_features=125,
scale=3.0,
n_informative=5,
n_classes=4,
random_state=42)
X, mask = to_niimgs(X, [5, 5, 5])
rand_local = np.random.RandomState(42)
groups = rand_local.binomial(2, 0.3, size=len(y))
# Check whether ValueError is raised when cv is not set correctly
for cv in ['abc', LinearSVC()]:
model = Decoder(mask=NiftiMasker(), cv=cv)
pytest.raises(ValueError, model.fit, X, y)
# Check whether decoder raised warning when groups is set to specific
# value but CV Splitter is not set
expected_warning = ('groups parameter is specified but '
'cv parameter is not set to custom CV splitter. '
'Using default object LeaveOneGroupOut().')
with pytest.warns(UserWarning, match=expected_warning):
model = Decoder(mask=NiftiMasker())
model.fit(X, y, groups=groups)
# Check that warning is raised when n_features is lower than 50 after
# screening and clustering for fREM
with pytest.warns(UserWarning, match=".*screening_percentile parameters"):
model = fREMClassifier(clustering_percentile=10,
screening_percentile=10,
mask=NiftiMasker(),
cv=1)
model.fit(X, y)
def test_decoder_binary_classification():
X, y = make_classification(n_samples=200,
n_features=125,
scale=3.0,
n_informative=5,
n_classes=2,
random_state=42)
X, mask = to_niimgs(X, [5, 5, 5])
# check classification with masker object
model = Decoder(mask=NiftiMasker())
model.fit(X, y)
y_pred = model.predict(X)
assert accuracy_score(y, y_pred) > 0.95
# decoder object use predict_proba for scoring with logistic model
model = Decoder(estimator='logistic_l2', mask=mask)
model.fit(X, y)
y_pred = model.predict(X)
assert accuracy_score(y, y_pred) > 0.95
# check different screening_percentile value
for screening_percentile in [100, 20]:
model = Decoder(mask=mask, screening_percentile=screening_percentile)
model.fit(X, y)
y_pred = model.predict(X)
assert accuracy_score(y, y_pred) > 0.95
screening_percentile = 90
for clustering_percentile in [100, 99]:
model = fREMClassifier(estimator='logistic_l2',
mask=mask,
clustering_percentile=clustering_percentile,
screening_percentile=screening_percentile,
cv=5)
model.fit(X, y)
y_pred = model.predict(X)
assert accuracy_score(y, y_pred) > 0.9
# check cross-validation scheme and fit attribute with groups enabled
rand_local = np.random.RandomState(42)
for cv in [KFold(n_splits=5), LeaveOneGroupOut()]:
model = Decoder(estimator='svc', mask=mask, standardize=True, cv=cv)
if isinstance(cv, LeaveOneGroupOut):
groups = rand_local.binomial(2, 0.3, size=len(y))
else:
groups = None
model.fit(X, y, groups=groups)
assert accuracy_score(y, y_pred) > 0.9