def test_rsl_feature_vector():
labels, tree = robust_single_linkage(X, 0.2)
n_clusters_1 = len(set(labels)) - int(-1 in labels)
#assert_equal(n_clusters_1, n_clusters)
labels = RobustSingleLinkage().fit(X).labels_
n_clusters_2 = len(set(labels)) - int(-1 in labels)
def test_rsl_feature_vector():
labels, tree = robust_single_linkage(X, 0.2)
n_clusters_1 = len(set(labels)) - int(-1 in labels)
#assert_equal(n_clusters_1, n_clusters)
labels = RobustSingleLinkage().fit(X).labels_
n_clusters_2 = len(set(labels)) - int(-1 in labels)
def test_rsl_prims_kdtree():
labels, tree = robust_single_linkage(X, 0.4, algorithm='prims_kdtree')
n_clusters_1 = len(set(labels)) - int(-1 in labels)
assert_equal(n_clusters_1, n_clusters)
labels = RobustSingleLinkage(algorithm='prims_kdtree').fit(X).labels_
n_clusters_2 = len(set(labels)) - int(-1 in labels)
assert_equal(n_clusters_2, n_clusters)
def test_rsl_boruvka_balltree():
labels, tree = robust_single_linkage(X, 0.45, algorithm='boruvka_balltree')
n_clusters_1 = len(set(labels)) - int(-1 in labels)
assert_equal(n_clusters_1, n_clusters)
labels = RobustSingleLinkage(cut=0.45,
algorithm='boruvka_balltree').fit(X).labels_
n_clusters_2 = len(set(labels)) - int(-1 in labels)
assert_equal(n_clusters_2, n_clusters)
def test_rsl_callable_metric():
# metric is the function reference, not the string key.
metric = distance.euclidean
labels, tree = robust_single_linkage(X, 0.2, metric=metric)
n_clusters_1 = len(set(labels)) - int(-1 in labels)
#assert_equal(n_clusters_1, n_clusters)
labels = RobustSingleLinkage(metric=metric).fit(X).labels_
n_clusters_2 = len(set(labels)) - int(-1 in labels)
def test_rsl_callable_metric():
# metric is the function reference, not the string key.
metric = distance.euclidean
labels, tree = robust_single_linkage(X, 0.2, metric=metric)
n_clusters_1 = len(set(labels)) - int(-1 in labels)
#assert_equal(n_clusters_1, n_clusters)
labels = RobustSingleLinkage(metric=metric).fit(X).labels_
n_clusters_2 = len(set(labels)) - int(-1 in labels)
def test_rsl_distance_matrix():
D = distance.squareform(distance.pdist(X))
D /= np.max(D)
labels, tree = robust_single_linkage(D, 0.25, 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 = RobustSingleLinkage(metric="precomputed").fit(D).labels_
n_clusters_2 = len(set(labels)) - int(-1 in labels)
def test_rsl_distance_matrix():
D = distance.squareform(distance.pdist(X))
D /= np.max(D)
labels, tree = robust_single_linkage(D, 0.25, 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 = RobustSingleLinkage(metric="precomputed").fit(D).labels_
n_clusters_2 = len(set(labels)) - int(-1 in labels)
def test_rsl_high_dimensional():
H, y = make_blobs(n_samples=50, random_state=0, n_features=64)
# H, y = shuffle(X, y, random_state=7)
H = StandardScaler().fit_transform(H)
labels, tree = robust_single_linkage(H, 5.5)
n_clusters_1 = len(set(labels)) - int(-1 in labels)
assert_equal(n_clusters_1, n_clusters)
labels = RobustSingleLinkage(cut=5.5,
algorithm='best',
metric='seuclidean',
V=np.ones(H.shape[1])).fit(H).labels_
n_clusters_2 = len(set(labels)) - int(-1 in labels)
assert_equal(n_clusters_2, n_clusters)
