def test_compute_full_tree():
# Test that the full tree is computed if n_clusters is small
rng = np.random.RandomState(0)
X = rng.randn(10, 2)
connectivity = kneighbors_graph(X, 5, include_self=False)
# When n_clusters is less, the full tree should be built
# that is the number of merges should be n_samples - 1
agc = AgglomerativeClustering(n_clusters=2, connectivity=connectivity)
agc.fit(X)
n_samples = X.shape[0]
n_nodes = agc.children_.shape[0]
assert n_nodes == n_samples - 1
# When n_clusters is large, greater than max of 100 and 0.02 * n_samples.
# we should stop when there are n_clusters.
n_clusters = 101
X = rng.randn(200, 2)
connectivity = kneighbors_graph(X, 10, include_self=False)
agc = AgglomerativeClustering(n_clusters=n_clusters,
connectivity=connectivity)
agc.fit(X)
n_samples = X.shape[0]
n_nodes = agc.children_.shape[0]
assert n_nodes == n_samples - n_clusters
def test_connectivity_ignores_diagonal():
rng = np.random.RandomState(0)
X = rng.rand(20, 5)
connectivity = kneighbors_graph(X, 3, include_self=False)
connectivity_include_self = kneighbors_graph(X, 3, include_self=True)
aglc1 = AgglomerativeClustering(connectivity=connectivity)
aglc2 = AgglomerativeClustering(connectivity=connectivity_include_self)
aglc1.fit(X)
aglc2.fit(X)
assert_array_equal(aglc1.labels_, aglc2.labels_)
def test_connectivity_callable():
rng = np.random.RandomState(0)
X = rng.rand(20, 5)
connectivity = kneighbors_graph(X, 3, include_self=False)
aglc1 = AgglomerativeClustering(connectivity=connectivity)
aglc2 = AgglomerativeClustering(
connectivity=partial(kneighbors_graph, n_neighbors=3,
include_self=False))
aglc1.fit(X)
aglc2.fit(X)
assert_array_equal(aglc1.labels_, aglc2.labels_)
def test_isomap_reconstruction_error():
# Same setup as in test_isomap_simple_grid, with an added dimension
N_per_side = 5
Npts = N_per_side**2
n_neighbors = Npts - 1
# grid of equidistant points in 2D, n_components = n_dim
X = np.array(list(product(range(N_per_side), repeat=2)))
# add noise in a third dimension
rng = np.random.RandomState(0)
noise = 0.1 * rng.randn(Npts, 1)
X = np.concatenate((X, noise), 1)
# compute input kernel
G = neighbors.kneighbors_graph(X, n_neighbors, mode='distance').toarray()
centerer = preprocessing.KernelCenterer()
K = centerer.fit_transform(-0.5 * G**2)
for eigen_solver in eigen_solvers:
for path_method in path_methods:
clf = manifold.Isomap(n_neighbors=n_neighbors,
n_components=2,
eigen_solver=eigen_solver,
path_method=path_method)
clf.fit(X)
# compute output kernel
G_iso = neighbors.kneighbors_graph(clf.embedding_,
n_neighbors,
mode='distance').toarray()
K_iso = centerer.fit_transform(-0.5 * G_iso**2)
# make sure error agrees
reconstruction_error = np.linalg.norm(K - K_iso) / Npts
assert_almost_equal(reconstruction_error,
clf.reconstruction_error())
def test_connectivity_propagation():
# Check that connectivity in the ward tree is propagated correctly during
# merging.
X = np.array([(.014, .120), (.014, .099), (.014, .097),
(.017, .153), (.017, .153), (.018, .153),
(.018, .153), (.018, .153), (.018, .153),
(.018, .153), (.018, .153), (.018, .153),
(.018, .152), (.018, .149), (.018, .144)])
connectivity = kneighbors_graph(X, 10, include_self=False)
ward = AgglomerativeClustering(
n_clusters=4, connectivity=connectivity, linkage='ward')
# If changes are not propagated correctly, fit crashes with an
# IndexError
ward.fit(X)
def test_isomap_simple_grid():
# Isomap should preserve distances when all neighbors are used
N_per_side = 5
Npts = N_per_side**2
n_neighbors = Npts - 1
# grid of equidistant points in 2D, n_components = n_dim
X = np.array(list(product(range(N_per_side), repeat=2)))
# distances from each point to all others
G = neighbors.kneighbors_graph(X, n_neighbors, mode='distance').toarray()
for eigen_solver in eigen_solvers:
for path_method in path_methods:
clf = manifold.Isomap(n_neighbors=n_neighbors,
n_components=2,
eigen_solver=eigen_solver,
path_method=path_method)
clf.fit(X)
G_iso = neighbors.kneighbors_graph(clf.embedding_,
n_neighbors,
mode='distance').toarray()
assert_array_almost_equal(G, G_iso)
def test_sparse_precomputed_distance():
"""Make sure that TSNE works identically for sparse and dense matrix"""
random_state = check_random_state(0)
X = random_state.randn(100, 2)
D_sparse = kneighbors_graph(X,
n_neighbors=100,
mode='distance',
include_self=True)
D = pairwise_distances(X)
assert sp.issparse(D_sparse)
assert_almost_equal(D_sparse.A, D)
tsne = TSNE(metric="precomputed", random_state=0)
Xt_dense = tsne.fit_transform(D)
for fmt in ['csr', 'lil']:
Xt_sparse = tsne.fit_transform(D_sparse.asformat(fmt))
assert_almost_equal(Xt_dense, Xt_sparse)
def test_identical_points():
# Ensure identical points are handled correctly when using mst with
# a sparse connectivity matrix
X = np.array([[0, 0, 0], [0, 0, 0],
[1, 1, 1], [1, 1, 1],
[2, 2, 2], [2, 2, 2]])
true_labels = np.array([0, 0, 1, 1, 2, 2])
connectivity = kneighbors_graph(X, n_neighbors=3, include_self=False)
connectivity = 0.5 * (connectivity + connectivity.T)
connectivity, n_components = _fix_connectivity(X,
connectivity,
'euclidean')
for linkage in ('single', 'average', 'average', 'ward'):
clustering = AgglomerativeClustering(n_clusters=3,
linkage=linkage,
connectivity=connectivity)
clustering.fit(X)
assert_almost_equal(normalized_mutual_info_score(clustering.labels_,
true_labels), 1)