def test_spectral_clustering_with_arpack_amg_solvers():
# Test that spectral_clustering is the same for arpack and amg solver
# Based on toy example from plot_segmentation_toy.py
# a small two coin image
x, y = np.indices((40, 40))
center1, center2 = (14, 12), (20, 25)
radius1, radius2 = 8, 7
circle1 = (x - center1[0]) ** 2 + (y - center1[1]) ** 2 < radius1 ** 2
circle2 = (x - center2[0]) ** 2 + (y - center2[1]) ** 2 < radius2 ** 2
circles = circle1 | circle2
mask = circles.copy()
img = circles.astype(float)
graph = img_to_graph(img, mask=mask)
graph.data = np.exp(-graph.data / graph.data.std())
labels_arpack = spectral_clustering(
graph, n_clusters=2, eigen_solver="arpack", random_state=0
)
assert len(np.unique(labels_arpack)) == 2
if amg_loaded:
labels_amg = spectral_clustering(
graph, n_clusters=2, eigen_solver="amg", random_state=0
)
assert adjusted_rand_score(labels_arpack, labels_amg) == 1
else:
with pytest.raises(ValueError):
spectral_clustering(graph, n_clusters=2, eigen_solver="amg", random_state=0)
def img_to_graph(image):
"""Converts an image to a graph.
This function takes in an image and returns a
4-connected grid graph. The nodes of this graph
are labeled as such: every pixel is a node,
the label of each node is the corresponding
(x, y) coordinates.
Args:
image (numpy_array): The input image.
Returns:
A network X graph.
"""
image = image.astype(np.int16)
coo_matrix = feature_extraction.img_to_graph(image)
graph = nx.from_scipy_sparse_matrix(coo_matrix)
node_labels = graph.nodes()
node_labels = np.array(node_labels)
node_labels = node_labels.reshape(image.shape)
mapping = {}
for index, x in np.ndenumerate(node_labels):
mapping[x] = index
graph = nx.relabel_nodes(graph, mapping)
graph.remove_edges_from(graph.selfloop_edges())
return graph
def test_spectral_clustering_with_arpack_amg_solvers():
# Test that spectral_clustering is the same for arpack and amg solver
# Based on toy example from plot_segmentation_toy.py
# a small two coin image
x, y = np.indices((40, 40))
center1, center2 = (14, 12), (20, 25)
radius1, radius2 = 8, 7
circle1 = (x - center1[0]) ** 2 + (y - center1[1]) ** 2 < radius1 ** 2
circle2 = (x - center2[0]) ** 2 + (y - center2[1]) ** 2 < radius2 ** 2
circles = circle1 | circle2
mask = circles.copy()
img = circles.astype(float)
graph = img_to_graph(img, mask=mask)
graph.data = np.exp(-graph.data / graph.data.std())
labels_arpack = spectral_clustering(
graph, n_clusters=2, eigen_solver='arpack', random_state=0)
assert len(np.unique(labels_arpack)) == 2
if amg_loaded:
labels_amg = spectral_clustering(
graph, n_clusters=2, eigen_solver='amg', random_state=0)
assert adjusted_rand_score(labels_arpack, labels_amg) == 1
else:
assert_raises(
ValueError, spectral_clustering,
graph, n_clusters=2, eigen_solver='amg', random_state=0)
def make_graph(self):
"""Создание графов
@return Список графов, причем индекс графа совпадает с индексом изображения
"""
result = []
for image in self.image_list:
graph = img_to_graph(image)
graph.data = np.exp(- self.graph_beta * graph.data / graph.data.std()) + self.graph_eps
result.append(graph)
return result
