def test_hdbscan_feature_vector():
labels, p, persist, ctree, ltree, mtree = hdbscan(X)
n_clusters_1 = len(set(labels)) - int(-1 in labels)
assert n_clusters_1 == n_clusters
labels = HDBSCAN().fit(X).labels_
n_clusters_2 = len(set(labels)) - int(-1 in labels)
assert n_clusters_2 == n_clusters
validity = validity_index(X, labels)
assert validity >= 0.4
def test_hdbscan_feature_vector():
labels, p, persist, ctree, ltree, mtree = hdbscan(X)
n_clusters_1 = len(set(labels)) - int(-1 in labels)
assert_equal(n_clusters_1, n_clusters)
labels = HDBSCAN().fit(X).labels_
n_clusters_2 = len(set(labels)) - int(-1 in labels)
assert_equal(n_clusters_2, n_clusters)
validity = validity_index(X, labels)
assert_greater_equal(validity, 0.4)
def test_hdbscan_feature_vector():
labels, p, persist, ctree, ltree, mtree = hdbscan(X)
n_clusters_1 = len(set(labels)) - int(-1 in labels)
assert_equal(n_clusters_1, n_clusters)
labels = HDBSCAN().fit(X).labels_
n_clusters_2 = len(set(labels)) - int(-1 in labels)
assert_equal(n_clusters_2, n_clusters)
validity = validity_index(X, labels)
assert_greater_equal(validity, 0.4)
def test_hdbscan_distance_matrix():
D = distance.squareform(distance.pdist(X))
D /= np.max(D)
labels, p, persist, ctree, ltree, mtree = hdbscan(D, metric="precomputed")
# number of clusters, ignoring noise if present
n_clusters_1 = len(set(labels)) - int(-1 in labels) # ignore noise
assert n_clusters_1 == n_clusters
labels = HDBSCAN(metric="precomputed").fit(D).labels_
n_clusters_2 = len(set(labels)) - int(-1 in labels)
assert n_clusters_2 == n_clusters
validity = validity_index(D, labels, metric="precomputed", d=2)
assert validity >= 0.6
def test_hdbscan_distance_matrix():
D = distance.squareform(distance.pdist(X))
D /= np.max(D)
labels, p, persist, ctree, ltree, mtree = hdbscan(D, metric='precomputed')
# number of clusters, ignoring noise if present
n_clusters_1 = len(set(labels)) - int(-1 in labels) # ignore noise
assert_equal(n_clusters_1, n_clusters)
labels = HDBSCAN(metric="precomputed").fit(D).labels_
n_clusters_2 = len(set(labels)) - int(-1 in labels)
assert_equal(n_clusters_2, n_clusters)
validity = validity_index(D, labels, metric='precomputed', d=2)
assert_greater_equal(validity, 0.6)