def test_knn_graph_sparse():
k = 3
n_pca = 20
pca = TruncatedSVD(n_pca, random_state=42).fit(data)
data_nu = pca.transform(data)
pdx = squareform(pdist(data_nu, metric="euclidean"))
knn_dist = np.partition(pdx, k, axis=1)[:, :k]
epsilon = np.max(knn_dist, axis=1)
K = np.empty_like(pdx)
for i in range(len(pdx)):
K[i, pdx[i, :] <= epsilon[i]] = 1
K[i, pdx[i, :] > epsilon[i]] = 0
K = K + K.T
W = np.divide(K, 2)
np.fill_diagonal(W, 0)
G = pygsp.graphs.Graph(W)
G2 = build_graph(
sp.coo_matrix(data),
n_pca=n_pca,
decay=None,
knn=k - 1,
random_state=42,
use_pygsp=True,
)
assert G.N == G2.N
np.testing.assert_allclose(G2.W.toarray(), G.W.toarray())
assert isinstance(G2, graphtools.graphs.kNNGraph)
def test_knn_graph_multiplication_symm():
k = 3
n_pca = 20
pca = PCA(n_pca, svd_solver="randomized", random_state=42).fit(data)
data_nu = pca.transform(data)
pdx = squareform(pdist(data_nu, metric="euclidean"))
knn_dist = np.partition(pdx, k, axis=1)[:, :k]
epsilon = np.max(knn_dist, axis=1)
K = np.empty_like(pdx)
for i in range(len(pdx)):
K[i, pdx[i, :] <= epsilon[i]] = 1
K[i, pdx[i, :] > epsilon[i]] = 0
W = K * K.T
np.fill_diagonal(W, 0)
G = pygsp.graphs.Graph(W)
G2 = build_graph(
data,
n_pca=n_pca,
decay=None,
knn=k - 1,
random_state=42,
use_pygsp=True,
kernel_symm="*",
)
assert G.N == G2.N
np.testing.assert_equal(G.dw, G2.dw)
assert (G.W - G2.W).nnz == 0
assert (G2.W - G.W).sum() == 0
assert isinstance(G2, graphtools.graphs.kNNGraph)
def test_knn_graph():
k = 3
n_pca = 20
pca = PCA(n_pca, svd_solver='randomized', random_state=42).fit(data)
data_nu = pca.transform(data)
pdx = squareform(pdist(data_nu, metric='euclidean'))
knn_dist = np.partition(pdx, k, axis=1)[:, :k]
epsilon = np.max(knn_dist, axis=1)
K = np.empty_like(pdx)
for i in range(len(pdx)):
K[i, pdx[i, :] <= epsilon[i]] = 1
K[i, pdx[i, :] > epsilon[i]] = 0
K = K + K.T
W = np.divide(K, 2)
np.fill_diagonal(W, 0)
G = pygsp.graphs.Graph(W)
G2 = build_graph(data, n_pca=n_pca,
decay=None, knn=k, random_state=42,
use_pygsp=True)
assert(G.N == G2.N)
assert(np.all(G.d == G2.d))
assert((G.W != G2.W).nnz == 0)
assert((G2.W != G.W).sum() == 0)
assert(isinstance(G2, graphtools.graphs.kNNGraph))
def test_knn_graph():
k = 3
n_pca = 20
pca = PCA(n_pca, svd_solver="randomized", random_state=42).fit(data)
data_nu = pca.transform(data)
pdx = squareform(pdist(data_nu, metric="euclidean"))
knn_dist = np.partition(pdx, k, axis=1)[:, :k]
epsilon = np.max(knn_dist, axis=1)
K = np.empty_like(pdx)
for i in range(len(pdx)):
K[i, pdx[i, :] <= epsilon[i]] = 1
K[i, pdx[i, :] > epsilon[i]] = 0
K = K + K.T
W = np.divide(K, 2)
np.fill_diagonal(W, 0)
G = pygsp.graphs.Graph(W)
G2 = build_graph(data,
n_pca=n_pca,
decay=None,
knn=k - 1,
random_state=42,
use_pygsp=True)
assert G.N == G2.N
np.testing.assert_equal(G.dw, G2.dw)
assert (G.W - G2.W).nnz == 0
assert (G2.W - G.W).sum() == 0
assert isinstance(G2, graphtools.graphs.kNNGraph)
K2 = G2.build_kernel_to_data(G2.data_nu, knn=k)
K2 = (K2 + K2.T) / 2
assert (G2.K - K2).nnz == 0
assert (G2.build_kernel_to_data(
G2.data_nu, knn=data.shape[0]).nnz == data.shape[0] * data.shape[0])
with assert_warns_message(
UserWarning,
"Cannot set knn ({}) to be greater than "
"n_samples ({}). Setting knn={}".format(data.shape[0] + 1,
data.shape[0],
data.shape[0]),
):
G2.build_kernel_to_data(
Y=G2.data_nu,
knn=data.shape[0] + 1,
)