def test_label_spreading_closed_form(global_dtype, Estimator, parameters,
alpha):
n_classes = 2
X, y = make_classification(n_classes=n_classes,
n_samples=200,
random_state=0)
X = X.astype(global_dtype, copy=False)
y[::3] = -1
gamma = 0.1
clf = label_propagation.LabelSpreading(gamma=gamma).fit(X, y)
# adopting notation from Zhou et al (2004):
S = clf._build_graph()
Y = np.zeros((len(y), n_classes + 1), dtype=X.dtype)
Y[np.arange(len(y)), y] = 1
Y = Y[:, :-1]
expected = np.dot(np.linalg.inv(np.eye(len(S), dtype=S.dtype) - alpha * S),
Y)
expected /= expected.sum(axis=1)[:, np.newaxis]
clf = label_propagation.LabelSpreading(max_iter=100,
alpha=alpha,
tol=1e-10,
gamma=gamma)
clf.fit(X, y)
assert_allclose(expected, clf.label_distributions_)
def test_predict_sparse_callable_kernel():
# This is a non-regression test for #15866
# Custom sparse kernel (top-K RBF)
def topk_rbf(X, Y=None, n_neighbors=10, gamma=1e-5):
nn = NearestNeighbors(n_neighbors=10, metric='euclidean', n_jobs=-1)
nn.fit(X)
W = -1 * nn.kneighbors_graph(Y, mode='distance').power(2) * gamma
np.exp(W.data, out=W.data)
assert issparse(W)
return W.T
n_classes = 4
n_samples = 500
n_test = 10
X, y = make_classification(n_classes=n_classes,
n_samples=n_samples,
n_features=20,
n_informative=20,
n_redundant=0,
n_repeated=0,
random_state=0)
X_train, X_test, y_train, y_test = train_test_split(X, y,
test_size=n_test,
random_state=0)
model = label_propagation.LabelSpreading(kernel=topk_rbf)
model.fit(X_train, y_train)
assert model.score(X_test, y_test) >= 0.9
model = label_propagation.LabelPropagation(kernel=topk_rbf)
model.fit(X_train, y_train)
assert model.score(X_test, y_test) >= 0.9
def test_valid_alpha():
n_classes = 2
X, y = make_classification(n_classes=n_classes, n_samples=200,
random_state=0)
for alpha in [-0.1, 0, 1, 1.1, None]:
with pytest.raises(ValueError):
label_propagation.LabelSpreading(alpha=alpha).fit(X, y)
def test_label_spreading_closed_form():
n_classes = 2
X, y = make_classification(n_classes=n_classes, n_samples=200, random_state=0)
y[::3] = -1
clf = label_propagation.LabelSpreading().fit(X, y)
# adopting notation from Zhou et al (2004):
S = clf._build_graph()
Y = np.zeros((len(y), n_classes + 1))
Y[np.arange(len(y)), y] = 1
Y = Y[:, :-1]
for alpha in [0.1, 0.3, 0.5, 0.7, 0.9]:
expected = np.dot(np.linalg.inv(np.eye(len(S)) - alpha * S), Y)
expected /= expected.sum(axis=1)[:, np.newaxis]
clf = label_propagation.LabelSpreading(max_iter=10000, alpha=alpha)
clf.fit(X, y)
assert_array_almost_equal(expected, clf.label_distributions_, 4)
def test_convergence_warning():
# This is a non-regression test for #5774
X = np.array([[1., 0.], [0., 1.], [1., 2.5]])
y = np.array([0, 1, -1])
mdl = label_propagation.LabelSpreading(kernel='rbf', max_iter=1)
assert_warns(ConvergenceWarning, mdl.fit, X, y)
assert mdl.n_iter_ == mdl.max_iter
mdl = label_propagation.LabelPropagation(kernel='rbf', max_iter=1)
assert_warns(ConvergenceWarning, mdl.fit, X, y)
assert mdl.n_iter_ == mdl.max_iter
mdl = label_propagation.LabelSpreading(kernel='rbf', max_iter=500)
assert_no_warnings(mdl.fit, X, y)
mdl = label_propagation.LabelPropagation(kernel='rbf', max_iter=500)
assert_no_warnings(mdl.fit, X, y)
def test_valid_alpha(global_dtype, alpha):
n_classes = 2
X, y = make_classification(n_classes=n_classes,
n_samples=200,
random_state=0)
X = X.astype(global_dtype)
with pytest.raises(ValueError):
label_propagation.LabelSpreading(alpha=alpha).fit(X, y)
def test_convergence_speed():
# This is a non-regression test for #5774
X = np.array([[1., 0.], [0., 1.], [1., 2.5]])
y = np.array([0, 1, -1])
mdl = label_propagation.LabelSpreading(kernel='rbf', max_iter=5000)
mdl.fit(X, y)
# this should converge quickly:
assert mdl.n_iter_ < 10
assert_array_equal(mdl.predict(X), [0, 1, 1])
def test_label_propagation_non_zero_normalizer():
# check that we don't divide by zero in case of null normalizer
# non-regression test for
# https://github.com/scikit-learn/scikit-learn/pull/15946
X = np.array([[100., 100.], [100., 100.], [0., 0.], [0., 0.]])
y = np.array([0, 1, -1, -1])
mdl = label_propagation.LabelSpreading(kernel='knn',
max_iter=100,
n_neighbors=1)
assert_no_warnings(mdl.fit, X, y)
def test_convergence_warning():
# This is a non-regression test for #5774
X = np.array([[1., 0.], [0., 1.], [1., 2.5]])
y = np.array([0, 1, -1])
mdl = label_propagation.LabelSpreading(kernel='rbf', max_iter=1)
warn_msg = ('max_iter=1 was reached without convergence.')
with pytest.warns(ConvergenceWarning, match=warn_msg):
mdl.fit(X, y)
assert mdl.n_iter_ == mdl.max_iter
mdl = label_propagation.LabelPropagation(kernel='rbf', max_iter=1)
with pytest.warns(ConvergenceWarning, match=warn_msg):
mdl.fit(X, y)
assert mdl.n_iter_ == mdl.max_iter
mdl = label_propagation.LabelSpreading(kernel='rbf', max_iter=500)
with pytest.warns(None) as record:
mdl.fit(X, y)
assert len(record) == 0
mdl = label_propagation.LabelPropagation(kernel='rbf', max_iter=500)
with pytest.warns(None) as record:
mdl.fit(X, y)
assert len(record) == 0
def test_convergence_warning():
# This is a non-regression test for #5774
X = np.array([[1.0, 0.0], [0.0, 1.0], [1.0, 2.5]])
y = np.array([0, 1, -1])
mdl = label_propagation.LabelSpreading(kernel="rbf", max_iter=1)
warn_msg = "max_iter=1 was reached without convergence."
with pytest.warns(ConvergenceWarning, match=warn_msg):
mdl.fit(X, y)
assert mdl.n_iter_ == mdl.max_iter
mdl = label_propagation.LabelPropagation(kernel="rbf", max_iter=1)
with pytest.warns(ConvergenceWarning, match=warn_msg):
mdl.fit(X, y)
assert mdl.n_iter_ == mdl.max_iter
mdl = label_propagation.LabelSpreading(kernel="rbf", max_iter=500)
with warnings.catch_warnings():
warnings.simplefilter("error", ConvergenceWarning)
mdl.fit(X, y)
mdl = label_propagation.LabelPropagation(kernel="rbf", max_iter=500)
with warnings.catch_warnings():
warnings.simplefilter("error", ConvergenceWarning)
mdl.fit(X, y)
def test_convergence_warning():
# This is a non-regression test for #5774
X = np.array([[1.0, 0.0], [0.0, 1.0], [1.0, 2.5]])
y = np.array([0, 1, -1])
mdl = label_propagation.LabelSpreading(kernel="rbf", max_iter=1)
warn_msg = "max_iter=1 was reached without convergence."
with pytest.warns(ConvergenceWarning, match=warn_msg):
mdl.fit(X, y)
assert mdl.n_iter_ == mdl.max_iter
mdl = label_propagation.LabelPropagation(kernel="rbf", max_iter=1)
with pytest.warns(ConvergenceWarning, match=warn_msg):
mdl.fit(X, y)
assert mdl.n_iter_ == mdl.max_iter
mdl = label_propagation.LabelSpreading(kernel="rbf", max_iter=500)
with pytest.warns(None) as record:
mdl.fit(X, y)
assert not [w.message for w in record]
mdl = label_propagation.LabelPropagation(kernel="rbf", max_iter=500)
with pytest.warns(None) as record:
mdl.fit(X, y)
assert not [w.message for w in record]
