def silhouette_samples(X, labels, verbose=False, cuda=False):
if not cuda:
return s_sil(X, labels)
X, labels = check_X_y(X, labels, accept_sparse=['csc', 'csr'])
le = LabelEncoder()
labels = le.fit_transform(labels)
n_samples = len(labels)
label_freqs = np.bincount(labels)
check_number_of_labels(len(le.classes_), n_samples)
reduce_func = functools.partial(_silhouette_reduce, labels=labels, label_freqs=label_freqs)
results = zip(*pairwise_distances_chunked_cuda(X, reduce_func=reduce_func, verbose=verbose))
intra_clust_dists, inter_clust_dists = results
intra_clust_dists = np.concatenate(intra_clust_dists)
inter_clust_dists = np.concatenate(inter_clust_dists)
denom = (label_freqs - 1).take(labels, mode='clip')
with np.errstate(divide="ignore", invalid="ignore"):
intra_clust_dists /= denom
sil_samples = inter_clust_dists - intra_clust_dists
with np.errstate(divide="ignore", invalid="ignore"):
sil_samples /= np.maximum(intra_clust_dists, inter_clust_dists)
# nan values are for clusters of size 1, and should be 0
return np.nan_to_num(sil_samples)
def test_label_encoder(values, classes, unknown):
# Test LabelEncoder's transform, fit_transform and
# inverse_transform methods
le = LabelEncoder()
le.fit(values)
assert_array_equal(le.classes_, classes)
assert_array_equal(le.transform(values), [1, 0, 2, 0, 2])
assert_array_equal(le.inverse_transform([1, 0, 2, 0, 2]), values)
le = LabelEncoder()
ret = le.fit_transform(values)
assert_array_equal(ret, [1, 0, 2, 0, 2])
with pytest.raises(ValueError, match="unseen labels"):
le.transform(unknown)