def test_hdbscan_cluster_patterns_extract_clusters(
dataset, nrows, connectivity, cluster_selection_epsilon,
cluster_selection_method, min_cluster_size, allow_single_cluster,
max_cluster_size, min_samples):
# This also tests duplicate data points
X, y = get_pattern(dataset, nrows)[0]
cuml_agg = HDBSCAN(verbose=logger.level_info,
allow_single_cluster=allow_single_cluster,
min_samples=min_samples,
max_cluster_size=max_cluster_size,
min_cluster_size=min_cluster_size,
cluster_selection_epsilon=cluster_selection_epsilon,
cluster_selection_method=cluster_selection_method)
sk_agg = hdbscan.HDBSCAN(
allow_single_cluster=allow_single_cluster,
approx_min_span_tree=False,
gen_min_span_tree=True,
min_samples=min_samples,
min_cluster_size=min_cluster_size,
cluster_selection_epsilon=cluster_selection_epsilon,
cluster_selection_method=cluster_selection_method,
algorithm="generic")
sk_agg.fit(cp.asnumpy(X))
cuml_agg._extract_clusters(sk_agg.condensed_tree_)
assert adjusted_rand_score(cuml_agg.labels_test, sk_agg.labels_) == 1.0
assert np.allclose(cp.asnumpy(cuml_agg.probabilities_test),
sk_agg.probabilities_)
def test_hdbscan_sklearn_datasets(dataset, connectivity,
cluster_selection_epsilon,
cluster_selection_method,
min_samples_cluster_size_bounds,
allow_single_cluster):
min_samples, min_cluster_size, max_cluster_size = \
min_samples_cluster_size_bounds
X = dataset.data
cuml_agg = HDBSCAN(verbose=logger.level_info,
allow_single_cluster=allow_single_cluster,
gen_min_span_tree=True,
min_samples=min_samples,
max_cluster_size=max_cluster_size,
min_cluster_size=min_cluster_size,
cluster_selection_epsilon=cluster_selection_epsilon,
cluster_selection_method=cluster_selection_method)
cuml_agg.fit(X)
sk_agg = hdbscan.HDBSCAN(
allow_single_cluster=allow_single_cluster,
approx_min_span_tree=False,
gen_min_span_tree=True,
min_samples=min_samples,
min_cluster_size=min_cluster_size,
cluster_selection_epsilon=cluster_selection_epsilon,
cluster_selection_method=cluster_selection_method,
algorithm="generic")
sk_agg.fit(cp.asnumpy(X))
assert_condensed_trees(sk_agg, min_cluster_size)
assert_cluster_counts(sk_agg, cuml_agg)
assert (len(np.unique(sk_agg.labels_)) == len(cp.unique(cuml_agg.labels_)))
assert (adjusted_rand_score(cuml_agg.labels_, sk_agg.labels_) > 0.85)
assert np.allclose(np.sort(sk_agg.cluster_persistence_),
np.sort(cuml_agg.cluster_persistence_),
rtol=0.1,
atol=0.1)
def test_hdbscan_blobs(nrows, ncols, nclusters, connectivity,
cluster_selection_epsilon, cluster_selection_method,
allow_single_cluster, min_cluster_size,
max_cluster_size, min_samples):
X, y = make_blobs(n_samples=int(nrows),
n_features=ncols,
centers=nclusters,
cluster_std=0.7,
shuffle=False,
random_state=42)
cuml_agg = HDBSCAN(verbose=logger.level_info,
allow_single_cluster=allow_single_cluster,
min_samples=min_samples,
max_cluster_size=max_cluster_size,
min_cluster_size=min_cluster_size,
cluster_selection_epsilon=cluster_selection_epsilon,
cluster_selection_method=cluster_selection_method)
cuml_agg.fit(X)
sk_agg = hdbscan.HDBSCAN(
allow_single_cluster=allow_single_cluster,
approx_min_span_tree=False,
gen_min_span_tree=True,
min_samples=min_samples,
min_cluster_size=min_cluster_size,
cluster_selection_epsilon=cluster_selection_epsilon,
cluster_selection_method=cluster_selection_method,
algorithm="generic")
sk_agg.fit(cp.asnumpy(X))
assert_condensed_trees(sk_agg, min_cluster_size)
assert_cluster_counts(sk_agg, cuml_agg)
assert (adjusted_rand_score(cuml_agg.labels_, sk_agg.labels_) >= 0.95)
assert (len(np.unique(sk_agg.labels_)) == len(cp.unique(cuml_agg.labels_)))
assert np.allclose(np.sort(sk_agg.cluster_persistence_),
np.sort(cuml_agg.cluster_persistence_),
rtol=0.01,
atol=0.01)
def test_hdbscan_empty_cluster_tree():
raw_tree = np.recarray(shape=(5, ),
formats=[np.intp, np.intp, float, np.intp],
names=('parent', 'child', 'lambda_val',
'child_size'))
raw_tree['parent'] = np.asarray([5, 5, 5, 5, 5])
raw_tree['child'] = [0, 1, 2, 3, 4]
raw_tree['lambda_val'] = [1.0, 1.0, 1.0, 1.0, 1.0]
raw_tree['child_size'] = [1, 1, 1, 1, 1]
condensed_tree = CondensedTree(raw_tree, 0.0, True)
cuml_agg = HDBSCAN(allow_single_cluster=True,
cluster_selection_method="eom")
cuml_agg._extract_clusters(condensed_tree)
# We just care that all points are assigned to the root cluster
assert np.sum(cuml_agg.labels_test.to_output("numpy")) == 0
def test_hdbscan_cluster_patterns(dataset, nrows, connectivity,
cluster_selection_epsilon,
cluster_selection_method, min_cluster_size,
allow_single_cluster, max_cluster_size,
min_samples):
# This also tests duplicate data points
X, y = get_pattern(dataset, nrows)[0]
cuml_agg = HDBSCAN(verbose=logger.level_info,
allow_single_cluster=allow_single_cluster,
min_samples=min_samples,
max_cluster_size=max_cluster_size,
min_cluster_size=min_cluster_size,
cluster_selection_epsilon=cluster_selection_epsilon,
cluster_selection_method=cluster_selection_method)
cuml_agg.fit(X)
sk_agg = hdbscan.HDBSCAN(
allow_single_cluster=allow_single_cluster,
approx_min_span_tree=False,
gen_min_span_tree=True,
min_samples=min_samples,
min_cluster_size=min_cluster_size,
cluster_selection_epsilon=cluster_selection_epsilon,
cluster_selection_method=cluster_selection_method,
algorithm="generic")
sk_agg.fit(cp.asnumpy(X))
assert_condensed_trees(sk_agg, min_cluster_size)
assert_cluster_counts(sk_agg, cuml_agg)
assert (len(np.unique(sk_agg.labels_)) == len(cp.unique(cuml_agg.labels_)))
assert (adjusted_rand_score(cuml_agg.labels_, sk_agg.labels_) > 0.95)
assert np.allclose(np.sort(sk_agg.cluster_persistence_),
np.sort(cuml_agg.cluster_persistence_),
rtol=0.1,
atol=0.1)
def test_hdbscan_core_dists_bug_4054():
"""
This test explicitly verifies that the MRE from
https://github.com/rapidsai/cuml/issues/4054
matches the reference impl
"""
X, y = datasets.make_moons(n_samples=10000, noise=0.12, random_state=0)
cu_labels_ = HDBSCAN(min_samples=25, min_cluster_size=25).fit_predict(X)
sk_labels_ = hdbscan.HDBSCAN(min_samples=25,
min_cluster_size=25,
approx_min_span_tree=False).fit_predict(X)
assert adjusted_rand_score(cu_labels_, sk_labels_) > 0.99
def test_hdbscan_plots():
X, y = make_blobs(n_samples=int(100),
n_features=100,
centers=10,
cluster_std=0.7,
shuffle=False,
random_state=42)
cuml_agg = HDBSCAN(gen_min_span_tree=True)
cuml_agg.fit(X)
assert cuml_agg.condensed_tree_ is not None
assert cuml_agg.minimum_spanning_tree_ is not None
assert cuml_agg.single_linkage_tree_ is not None
cuml_agg = HDBSCAN(gen_min_span_tree=False)
cuml_agg.fit(X)
assert cuml_agg.minimum_spanning_tree_ is None