def test_affinity_passed_to_fix_connectivity():
# Test that the affinity parameter is actually passed to the pairwise
# function
size = 2
rng = np.random.RandomState(0)
X = rng.randn(size, size)
mask = np.array([True, False, False, True])
connectivity = grid_to_graph(n_x=size,
n_y=size,
mask=mask,
return_as=np.ndarray)
class FakeAffinity:
def __init__(self):
self.counter = 0
def increment(self, *args, **kwargs):
self.counter += 1
return self.counter
fa = FakeAffinity()
linkage_tree(X, connectivity=connectivity, affinity=fa.increment)
assert fa.counter == 3
def test_zero_cosine_linkage_tree():
# Check that zero vectors in X produce an error when
# 'cosine' affinity is used
X = np.array([[0, 1], [0, 0]])
msg = 'Cosine affinity cannot be used when X contains zero vectors'
with pytest.raises(ValueError, match=msg):
linkage_tree(X, affinity='cosine')
def test_linkage_misc():
# Misc tests on linkage
rng = np.random.RandomState(42)
X = rng.normal(size=(5, 5))
with pytest.raises(ValueError):
AgglomerativeClustering(linkage='foo').fit(X)
with pytest.raises(ValueError):
linkage_tree(X, linkage='foo')
with pytest.raises(ValueError):
linkage_tree(X, connectivity=np.ones((4, 4)))
# Smoke test FeatureAgglomeration
FeatureAgglomeration().fit(X)
# test hierarchical clustering on a precomputed distances matrix
dis = cosine_distances(X)
res = linkage_tree(dis, affinity="precomputed")
assert_array_equal(res[0], linkage_tree(X, affinity="cosine")[0])
# test hierarchical clustering on a precomputed distances matrix
res = linkage_tree(X, affinity=manhattan_distances)
assert_array_equal(res[0], linkage_tree(X, affinity="manhattan")[0])
def test_ward_linkage_tree_return_distance():
# Test return_distance option on linkage and ward trees
# test that return_distance when set true, gives same
# output on both structured and unstructured clustering.
n, p = 10, 5
rng = np.random.RandomState(0)
connectivity = np.ones((n, n))
for i in range(5):
X = .1 * rng.normal(size=(n, p))
X -= 4. * np.arange(n)[:, np.newaxis]
X -= X.mean(axis=1)[:, np.newaxis]
out_unstructured = ward_tree(X, return_distance=True)
out_structured = ward_tree(X,
connectivity=connectivity,
return_distance=True)
# get children
children_unstructured = out_unstructured[0]
children_structured = out_structured[0]
# check if we got the same clusters
assert_array_equal(children_unstructured, children_structured)
# check if the distances are the same
dist_unstructured = out_unstructured[-1]
dist_structured = out_structured[-1]
assert_array_almost_equal(dist_unstructured, dist_structured)
for linkage in ['average', 'complete', 'single']:
structured_items = linkage_tree(X,
connectivity=connectivity,
linkage=linkage,
return_distance=True)[-1]
unstructured_items = linkage_tree(X,
linkage=linkage,
return_distance=True)[-1]
structured_dist = structured_items[-1]
unstructured_dist = unstructured_items[-1]
structured_children = structured_items[0]
unstructured_children = unstructured_items[0]
assert_array_almost_equal(structured_dist, unstructured_dist)
assert_array_almost_equal(structured_children,
unstructured_children)
# test on the following dataset where we know the truth
# taken from scipy/cluster/tests/hierarchy_test_data.py
X = np.array([[1.43054825, -7.5693489], [6.95887839, 6.82293382],
[2.87137846, -9.68248579], [7.87974764, -6.05485803],
[8.24018364, -6.09495602], [7.39020262, 8.54004355]])
# truth
linkage_X_ward = np.array([[3., 4., 0.36265956, 2.],
[1., 5., 1.77045373, 2.],
[0., 2., 2.55760419, 2.],
[6., 8., 9.10208346, 4.],
[7., 9., 24.7784379, 6.]])
linkage_X_complete = np.array([[3., 4., 0.36265956, 2.],
[1., 5., 1.77045373, 2.],
[0., 2., 2.55760419, 2.],
[6., 8., 6.96742194, 4.],
[7., 9., 18.77445997, 6.]])
linkage_X_average = np.array([[3., 4., 0.36265956, 2.],
[1., 5., 1.77045373, 2.],
[0., 2., 2.55760419, 2.],
[6., 8., 6.55832839, 4.],
[7., 9., 15.44089605, 6.]])
n_samples, n_features = np.shape(X)
connectivity_X = np.ones((n_samples, n_samples))
out_X_unstructured = ward_tree(X, return_distance=True)
out_X_structured = ward_tree(X,
connectivity=connectivity_X,
return_distance=True)
# check that the labels are the same
assert_array_equal(linkage_X_ward[:, :2], out_X_unstructured[0])
assert_array_equal(linkage_X_ward[:, :2], out_X_structured[0])
# check that the distances are correct
assert_array_almost_equal(linkage_X_ward[:, 2], out_X_unstructured[4])
assert_array_almost_equal(linkage_X_ward[:, 2], out_X_structured[4])
linkage_options = ['complete', 'average', 'single']
X_linkage_truth = [linkage_X_complete, linkage_X_average]
for (linkage, X_truth) in zip(linkage_options, X_linkage_truth):
out_X_unstructured = linkage_tree(X,
return_distance=True,
linkage=linkage)
out_X_structured = linkage_tree(X,
connectivity=connectivity_X,
linkage=linkage,
return_distance=True)
# check that the labels are the same
assert_array_equal(X_truth[:, :2], out_X_unstructured[0])
assert_array_equal(X_truth[:, :2], out_X_structured[0])
# check that the distances are correct
assert_array_almost_equal(X_truth[:, 2], out_X_unstructured[4])
assert_array_almost_equal(X_truth[:, 2], out_X_structured[4])
