def test_correct_number_of_clusters():
# in 'auto' mode
n_clusters = 3
X = generate_clustered_data(n_clusters=n_clusters)
# Parameters chosen specifically for this task.
# Compute OPTICS
clust = OPTICS(max_eps=5.0 * 6.0, min_samples=4, xi=.1)
clust.fit(X)
# number of clusters, ignoring noise if present
n_clusters_1 = len(set(clust.labels_)) - int(-1 in clust.labels_)
assert n_clusters_1 == n_clusters
# check attribute types and sizes
assert clust.labels_.shape == (len(X),)
assert clust.labels_.dtype.kind == 'i'
assert clust.reachability_.shape == (len(X),)
assert clust.reachability_.dtype.kind == 'f'
assert clust.core_distances_.shape == (len(X),)
assert clust.core_distances_.dtype.kind == 'f'
assert clust.ordering_.shape == (len(X),)
assert clust.ordering_.dtype.kind == 'i'
assert set(clust.ordering_) == set(range(len(X)))
def test_bad_reachability():
msg = "All reachability values are inf. Set a larger max_eps."
centers = [[1, 1], [-1, -1], [1, -1]]
X, labels_true = make_blobs(n_samples=750, centers=centers,
cluster_std=0.4, random_state=0)
with pytest.warns(UserWarning, match=msg):
clust = OPTICS(max_eps=5.0 * 0.003, min_samples=10, eps=0.015)
clust.fit(X)
def test_min_cluster_size(min_cluster_size):
redX = X[::2] # reduce for speed
clust = OPTICS(min_samples=9, min_cluster_size=min_cluster_size).fit(redX)
cluster_sizes = np.bincount(clust.labels_[clust.labels_ != -1])
if cluster_sizes.size:
assert min(cluster_sizes) >= min_cluster_size
# check behaviour is the same when min_cluster_size is a fraction
clust_frac = OPTICS(min_samples=9,
min_cluster_size=min_cluster_size / redX.shape[0])
clust_frac.fit(redX)
assert_array_equal(clust.labels_, clust_frac.labels_)
def test_wrong_cluster_method():
clust = OPTICS(cluster_method='superfancy')
with pytest.raises(ValueError, match="cluster_method should be one of "):
clust.fit(X)
def test_min_cluster_size_invalid2():
clust = OPTICS(min_cluster_size=len(X) + 1)
with pytest.raises(ValueError, match="must be no greater than the "):
clust.fit(X)
def test_min_cluster_size_invalid(min_cluster_size):
clust = OPTICS(min_cluster_size=min_cluster_size)
with pytest.raises(ValueError, match="must be a positive integer or a "):
clust.fit(X)