def test_scikit_vs_scipy():
# Test scikit linkage with full connectivity (i.e. unstructured) vs scipy
n, p, k = 10, 5, 3
rng = np.random.RandomState(0)
# Not using a lil_matrix here, just to check that non sparse
# matrices are well handled
connectivity = np.ones((n, n))
for linkage in _TREE_BUILDERS.keys():
for i in range(5):
X = .1 * rng.normal(size=(n, p))
X -= 4. * np.arange(n)[:, np.newaxis]
X -= X.mean(axis=1)[:, np.newaxis]
out = hierarchy.linkage(X, method=linkage)
children_ = out[:, :2].astype(np.int, copy=False)
children, _, n_leaves, _ = _TREE_BUILDERS[linkage](X, connectivity)
# Sort the order of child nodes per row for consistency
children.sort(axis=1)
assert_array_equal(children, children_, 'linkage tree differs'
' from scipy impl for'
' linkage: ' + linkage)
cut = _hc_cut(k, children, n_leaves)
cut_ = _hc_cut(k, children_, n_leaves)
assess_same_labelling(cut, cut_)
# Test error management in _hc_cut
with pytest.raises(ValueError):
_hc_cut(n_leaves + 1, children, n_leaves)
def test_agglomerative_clustering_with_distance_threshold(linkage):
# Check that we obtain the correct number of clusters with
# agglomerative clustering with distance_threshold.
rng = np.random.RandomState(0)
mask = np.ones([10, 10], dtype=np.bool)
n_samples = 100
X = rng.randn(n_samples, 50)
connectivity = grid_to_graph(*mask.shape)
# test when distance threshold is set to 10
distance_threshold = 10
for conn in [None, connectivity]:
clustering = AgglomerativeClustering(
n_clusters=None,
distance_threshold=distance_threshold,
connectivity=conn, linkage=linkage)
clustering.fit(X)
clusters_produced = clustering.labels_
num_clusters_produced = len(np.unique(clustering.labels_))
# test if the clusters produced match the point in the linkage tree
# where the distance exceeds the threshold
tree_builder = _TREE_BUILDERS[linkage]
children, n_components, n_leaves, parent, distances = \
tree_builder(X, connectivity=conn, n_clusters=None,
return_distance=True)
num_clusters_at_threshold = np.count_nonzero(
distances >= distance_threshold) + 1
# test number of clusters produced
assert num_clusters_at_threshold == num_clusters_produced
# test clusters produced
clusters_at_threshold = _hc_cut(n_clusters=num_clusters_produced,
children=children,
n_leaves=n_leaves)
assert np.array_equiv(clusters_produced,
clusters_at_threshold)
def test_vector_scikit_single_vs_scipy_single(seed):
n_samples, n_features, n_clusters = 10, 5, 3
rng = np.random.RandomState(seed)
X = .1 * rng.normal(size=(n_samples, n_features))
X -= 4. * np.arange(n_samples)[:, np.newaxis]
X -= X.mean(axis=1)[:, np.newaxis]
out = hierarchy.linkage(X, method='single')
children_scipy = out[:, :2].astype(np.int)
children, _, n_leaves, _ = _TREE_BUILDERS['single'](X)
# Sort the order of child nodes per row for consistency
children.sort(axis=1)
assert_array_equal(
children, children_scipy, 'linkage tree differs'
' from scipy impl for'
' single linkage.')
cut = _hc_cut(n_clusters, children, n_leaves)
cut_scipy = _hc_cut(n_clusters, children_scipy, n_leaves)
assess_same_labelling(cut, cut_scipy)
def fit(self, X, y=None):
"""Fit the agglomerative clustering from features or distance matrix.
The stopping rule is used to determine :attr:`n_clusters_``, and the
full dendrogram is cut there to compute :attr:`labels_`.
Parameters
----------
X : ndarray, shape (n_samples, n_features) or (n_samples, n_samples)
Training instances to cluster, or distances between instances if
``affinity='precomputed'``.
y : ignored
Not used, present here for API consistency by convention.
Returns
-------
self
"""
X = check_array(X)
if X.shape[0] == 1:
self.labels_ = np.array([0])
return self
self._build_tree(X)
self.n_clusters_ = _num_clusters_histogram(self.distances_,
self.freq_threshold,
self.n_bins_start)
# Cut the tree to find labels
# TODO verify whether Daniel Mullner's implementation of this step
# offers any advantage
self.labels_ = _hc_cut(self.n_clusters_, self.children_,
self.n_leaves_)
return self