def test_shc_validation():
"""Test the validation of hyper-parameters and input data in SHC"""
X, _ = generate_data(supervised=False, affinity=False)
with pytest.raises(ValueError):
clusterer = ScipyHierarchicalClustering(n_clusters=len(X) + 1)
labels = clusterer.fit_predict(X)
with pytest.raises(ValueError):
clusterer = ScipyHierarchicalClustering(n_clusters=-1)
labels = clusterer.fit_predict(X)
with pytest.raises(ValueError):
clusterer = ScipyHierarchicalClustering(scoring_data="affinity")
labels = clusterer.fit_predict(X)
def test_shc_custom_affinity():
"""Test custom affinity function in SHC."""
X, _ = generate_data(supervised=False, affinity=False)
clusterer = ScipyHierarchicalClustering(affinity=euclidean_distances,
n_clusters=4)
labels = clusterer.fit_predict(X)
assert_array_equal([25, 25, 25, 25], np.bincount(labels))
def test_shc_precomputed_distance():
"""Test using precomputed distances in SHC."""
X, _ = generate_data(supervised=False, affinity=True)
clusterer = ScipyHierarchicalClustering(affinity="precomputed",
n_clusters=4)
labels = clusterer.fit_predict(X)
assert_array_equal([25, 25, 25, 25], np.bincount(labels))
def test_shc_precomputed_distance():
"""Test using precomputed distances in SHC."""
X, _ = generate_data(supervised=False, affinity=True)
clusterer = ScipyHierarchicalClustering(affinity="precomputed",
n_clusters=4)
labels = clusterer.fit_predict(X)
assert_array_equal([25, 25, 25, 25], np.bincount(labels))
def test_shc_custom_affinity():
"""Test custom affinity function in SHC."""
X, _ = generate_data(supervised=False, affinity=False)
clusterer = ScipyHierarchicalClustering(affinity=euclidean_distances,
n_clusters=4)
labels = clusterer.fit_predict(X)
assert_array_equal([25, 25, 25, 25], np.bincount(labels))
def test_shc_unsupervised_scoring_data_raw():
"""Test unsupervised clustering for SHC when scoring_data='raw'."""
X, _ = generate_data(supervised=False, affinity=False)
_scoring = partial(silhouette_score, metric="euclidean")
clusterer = ScipyHierarchicalClustering(affinity=euclidean_distances,
scoring=_scoring,
scoring_data="raw")
labels = clusterer.fit_predict(X)
assert_array_equal([25, 25, 25, 25], np.bincount(labels))
def test_shc_unsupervised_scoring_data_affinity():
"""Test unsupervised clustering for SHC when scoring_data='affinity'."""
# Passing feature matrix
X, _ = generate_data(supervised=False, affinity=False)
_scoring = partial(silhouette_score, metric="precomputed")
clusterer = ScipyHierarchicalClustering(affinity=euclidean_distances,
scoring=_scoring,
scoring_data="affinity")
labels = clusterer.fit_predict(X)
assert_array_equal([25, 25, 25, 25], np.bincount(labels))
# Passing affinity matrix
X, _ = generate_data(supervised=False, affinity=True)
_scoring = partial(silhouette_score, metric="precomputed")
clusterer = ScipyHierarchicalClustering(affinity="precomputed",
scoring=_scoring,
scoring_data="affinity")
labels = clusterer.fit_predict(X)
assert_array_equal([25, 25, 25, 25], np.bincount(labels))
def test_shc_unsupervised_scoring_data_None():
"""Test unsupervised clustering for SHC when scoring_data is None."""
X, _ = generate_data(supervised=False, affinity=False)
def _scoring(labels_pred):
return -np.inf
clusterer = ScipyHierarchicalClustering(affinity=euclidean_distances,
scoring=_scoring)
labels = clusterer.fit_predict(X)
assert_array_equal([100], np.bincount(labels))
def test_shc_threshold():
"""Test changing threshold in SHC."""
X, _ = generate_data(supervised=False, affinity=True)
clusterer = ScipyHierarchicalClustering(affinity="precomputed",
scoring_data="affinity",
n_clusters=4)
labels = clusterer.fit_predict(X)
clusterer.set_params(threshold=clusterer.linkage_[-4, 2])
labels = clusterer.labels_
assert_array_equal([25, 25, 25, 25], np.bincount(labels))
def test_shc_n_clusters():
"""Test changing number of clusters in SHC."""
X, _ = generate_data(supervised=False, affinity=True)
clusterer = ScipyHierarchicalClustering(affinity="precomputed",
n_clusters=4)
labels = clusterer.fit_predict(X)
assert_equal(len(np.unique(labels)), 4)
clusterer.set_params(n_clusters=10)
labels = clusterer.labels_
assert_equal(len(np.unique(labels)), 10)
def test_shc_n_clusters():
"""Test changing number of clusters in SHC."""
X, _ = generate_data(supervised=False, affinity=True)
clusterer = ScipyHierarchicalClustering(affinity="precomputed",
n_clusters=4)
labels = clusterer.fit_predict(X)
assert_equal(len(np.unique(labels)), 4)
clusterer.set_params(n_clusters=10)
labels = clusterer.labels_
assert_equal(len(np.unique(labels)), 10)
def test_shc_threshold():
"""Test changing threshold in SHC."""
X, _ = generate_data(supervised=False, affinity=True)
# n_clusters has precedence over threshold
clusterer = ScipyHierarchicalClustering(affinity="precomputed",
n_clusters=2)
labels1 = clusterer.fit_predict(X)
clusterer.set_params(threshold=clusterer.linkage_[-4, 2])
labels2 = clusterer.labels_
assert_array_equal(labels1, labels2)
assert_equal(len(np.unique(labels1)), 2)
# change threshold
clusterer.set_params(n_clusters=None, threshold=clusterer.linkage_[-5, 2])
labels = clusterer.labels_
assert_equal(len(np.unique(labels)), 5)
clusterer.set_params(threshold=clusterer.linkage_[-4, 2])
labels = clusterer.labels_
assert_equal(len(np.unique(labels)), 4)
def test_shc_threshold():
"""Test changing threshold in SHC."""
X, _ = generate_data(supervised=False, affinity=True)
# n_clusters has precedence over threshold
clusterer = ScipyHierarchicalClustering(affinity="precomputed",
n_clusters=2)
labels1 = clusterer.fit_predict(X)
clusterer.set_params(threshold=clusterer.linkage_[-4, 2])
labels2 = clusterer.labels_
assert_array_equal(labels1, labels2)
assert_equal(len(np.unique(labels1)), 2)
# change threshold
clusterer.set_params(n_clusters=None, threshold=clusterer.linkage_[-5, 2])
labels = clusterer.labels_
assert_equal(len(np.unique(labels)), 5)
clusterer.set_params(threshold=clusterer.linkage_[-4, 2])
labels = clusterer.labels_
assert_equal(len(np.unique(labels)), 4)
def test_shc_default_euclidean():
"""Test default parameters of SHC, using euclidean distance."""
X, _ = generate_data(supervised=False, affinity=False)
clusterer = ScipyHierarchicalClustering(n_clusters=4)
labels = clusterer.fit_predict(X)
assert_array_equal([25, 25, 25, 25], np.bincount(labels))