def test_knn_graph_anisotropy():
k = 3
a = 13
n_pca = 20
anisotropy = 0.9
thresh = 1e-4
data_small = data[np.random.choice(len(data), len(data) // 2, replace=False)]
pca = PCA(n_pca, svd_solver="randomized", random_state=42).fit(data_small)
data_small_nu = pca.transform(data_small)
pdx = squareform(pdist(data_small_nu, metric="euclidean"))
knn_dist = np.partition(pdx, k, axis=1)[:, :k]
epsilon = np.max(knn_dist, axis=1)
weighted_pdx = (pdx.T / epsilon).T
K = np.exp(-1 * weighted_pdx ** a)
K[K < thresh] = 0
K = K + K.T
K = np.divide(K, 2)
d = K.sum(1)
W = K / (np.outer(d, d) ** anisotropy)
np.fill_diagonal(W, 0)
G = pygsp.graphs.Graph(W)
G2 = build_graph(
data_small,
n_pca=n_pca,
thresh=thresh,
decay=a,
knn=k - 1,
random_state=42,
use_pygsp=True,
anisotropy=anisotropy,
)
assert isinstance(G2, graphtools.graphs.kNNGraph)
assert G.N == G2.N
np.testing.assert_allclose(G.dw, G2.dw, atol=1e-14, rtol=1e-14)
np.testing.assert_allclose((G2.W - G.W).data, 0, atol=1e-14, rtol=1e-14)
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_fixed_bandwidth():
k = None
decay = 5
bandwidth = 10
bandwidth_scale = 1.3
n_pca = 20
thresh = 1e-4
pca = PCA(n_pca, svd_solver="randomized", random_state=42).fit(data)
data_nu = pca.transform(data)
pdx = squareform(pdist(data_nu, metric="euclidean"))
K = np.exp(-1 * np.power(pdx / (bandwidth * bandwidth_scale), decay))
K[K < thresh] = 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=decay,
bandwidth=bandwidth,
bandwidth_scale=bandwidth_scale,
knn=k,
random_state=42,
thresh=thresh,
search_multiplier=2,
use_pygsp=True,
)
assert isinstance(G2, graphtools.graphs.kNNGraph)
np.testing.assert_array_equal(G.N, G2.N)
np.testing.assert_array_equal(G.d, G2.d)
np.testing.assert_allclose((G.W - G2.W).data,
np.zeros_like((G.W - G2.W).data),
atol=1e-14)
bandwidth = np.random.gamma(20, 0.5, len(data))
K = np.exp(-1 * (pdx.T / (bandwidth * bandwidth_scale)).T**decay)
K[K < thresh] = 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=decay,
bandwidth=bandwidth,
bandwidth_scale=bandwidth_scale,
knn=k,
random_state=42,
thresh=thresh,
use_pygsp=True,
)
assert isinstance(G2, graphtools.graphs.kNNGraph)
np.testing.assert_array_equal(G.N, G2.N)
np.testing.assert_allclose(G.dw, G2.dw, atol=1e-14)
np.testing.assert_allclose((G.W - G2.W).data,
np.zeros_like((G.W - G2.W).data),
atol=1e-14)
def test_exact_graph_callable_bandwidth():
decay = 2
knn = 5
def bandwidth(x):
return 2
n_pca = 20
thresh = 1e-4
pca = PCA(n_pca, svd_solver="randomized", random_state=42).fit(data)
data_nu = pca.transform(data)
pdx = squareform(pdist(data_nu, metric="euclidean"))
K = np.exp(-1 * (pdx / bandwidth(pdx))**decay)
K[K < thresh] = 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,
knn=knn - 1,
decay=decay,
bandwidth=bandwidth,
random_state=42,
thresh=thresh,
use_pygsp=True,
)
assert isinstance(G2, graphtools.graphs.TraditionalGraph)
assert G.N == G2.N
np.testing.assert_equal(G.dw, G2.dw)
assert (G2.W != G.W).sum() == 0
assert (G.W != G2.W).nnz == 0
def bandwidth(x):
return np.percentile(x, 10, axis=1)
K = np.exp(-1 * (pdx / bandwidth(pdx))**decay)
K[K < thresh] = 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,
knn=knn - 1,
decay=decay,
bandwidth=bandwidth,
random_state=42,
thresh=thresh,
use_pygsp=True,
)
assert isinstance(G2, graphtools.graphs.TraditionalGraph)
assert G.N == G2.N
np.testing.assert_allclose(G.dw, G2.dw)
np.testing.assert_allclose((G2.W - G.W).data, 0, atol=1e-14)
def test_exact_graph_fixed_bandwidth():
decay = 2
knn = None
bandwidth = 2
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"))
K = np.exp(-1 * (pdx / bandwidth)**decay)
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,
graphtype="exact",
knn=knn,
decay=decay,
bandwidth=bandwidth,
random_state=42,
thresh=0,
use_pygsp=True,
)
assert isinstance(G2, graphtools.graphs.TraditionalGraph)
assert G.N == G2.N
np.testing.assert_allclose(G.dw, G2.dw)
np.testing.assert_allclose((G2.W - G.W).data, 0, atol=1e-14)
bandwidth = np.random.gamma(5, 0.5, len(data))
K = np.exp(-1 * (pdx.T / bandwidth).T**decay)
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,
graphtype="exact",
knn=knn,
decay=decay,
bandwidth=bandwidth,
random_state=42,
thresh=0,
use_pygsp=True,
)
assert isinstance(G2, graphtools.graphs.TraditionalGraph)
assert G.N == G2.N
np.testing.assert_allclose(G.dw, G2.dw)
np.testing.assert_allclose((G2.W - G.W).data, 0, atol=1e-14)
def test_knn_interpolate():
G = build_graph(data, decay=None)
assert_raises(ValueError, G.interpolate, data)
pca_data = PCA(2).fit_transform(data)
transitions = G.extend_to_data(data)
assert(np.all(G.interpolate(pca_data, Y=data) ==
G.interpolate(pca_data, transitions=transitions)))
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,
)
def test_exact_interpolate():
G = build_graph(data, decay=10, thresh=0)
with assert_raises_message(
ValueError, "Either `transitions` or `Y` must be provided."):
G.interpolate(data)
pca_data = PCA(2).fit_transform(data)
transitions = G.extend_to_data(data)
assert np.all(
G.interpolate(pca_data, Y=data) == G.interpolate(
pca_data, transitions=transitions))
def test_knn_interpolate():
G = build_graph(data, decay=None)
with assert_raises_message(
ValueError, "Either `transitions` or `Y` must be provided."):
G.interpolate(data)
pca_data = PCA(2).fit_transform(data)
transitions = G.extend_to_data(data)
np.testing.assert_equal(
G.interpolate(pca_data, Y=data),
G.interpolate(pca_data, transitions=transitions),
)
def test_exact_graph_anisotropy():
k = 3
a = 13
n_pca = 20
anisotropy = 0.9
data_small = data[np.random.choice(len(data),
len(data) // 2,
replace=False)]
pca = PCA(n_pca, svd_solver="randomized", random_state=42).fit(data_small)
data_small_nu = pca.transform(data_small)
pdx = squareform(pdist(data_small_nu, metric="euclidean"))
knn_dist = np.partition(pdx, k, axis=1)[:, :k]
epsilon = np.max(knn_dist, axis=1)
weighted_pdx = (pdx.T / epsilon).T
K = np.exp(-1 * weighted_pdx**a)
K = K + K.T
K = np.divide(K, 2)
d = K.sum(1)
W = K / (np.outer(d, d)**anisotropy)
np.fill_diagonal(W, 0)
G = pygsp.graphs.Graph(W)
G2 = build_graph(
data_small,
thresh=0,
n_pca=n_pca,
decay=a,
knn=k - 1,
random_state=42,
use_pygsp=True,
anisotropy=anisotropy,
)
assert isinstance(G2, graphtools.graphs.TraditionalGraph)
assert G.N == G2.N
np.testing.assert_equal(G.dw, G2.dw)
assert (G2.W != G.W).sum() == 0
assert (G.W != G2.W).nnz == 0
with assert_raises_message(ValueError,
"Expected 0 <= anisotropy <= 1. Got -1"):
build_graph(
data_small,
thresh=0,
n_pca=n_pca,
decay=a,
knn=k - 1,
random_state=42,
use_pygsp=True,
anisotropy=-1,
)
with assert_raises_message(ValueError,
"Expected 0 <= anisotropy <= 1. Got 2"):
build_graph(
data_small,
thresh=0,
n_pca=n_pca,
decay=a,
knn=k - 1,
random_state=42,
use_pygsp=True,
anisotropy=2,
)
with assert_raises_message(ValueError,
"Expected 0 <= anisotropy <= 1. Got invalid"):
build_graph(
data_small,
thresh=0,
n_pca=n_pca,
decay=a,
knn=k - 1,
random_state=42,
use_pygsp=True,
anisotropy="invalid",
)
def test_truncated_exact_graph():
k = 3
a = 13
n_pca = 20
thresh = 1e-4
data_small = data[np.random.choice(len(data),
len(data) // 2,
replace=False)]
pca = PCA(n_pca, svd_solver="randomized", random_state=42).fit(data_small)
data_small_nu = pca.transform(data_small)
pdx = squareform(pdist(data_small_nu, metric="euclidean"))
knn_dist = np.partition(pdx, k, axis=1)[:, :k]
epsilon = np.max(knn_dist, axis=1)
weighted_pdx = (pdx.T / epsilon).T
K = np.exp(-1 * weighted_pdx**a)
K[K < thresh] = 0
W = K + K.T
W = np.divide(W, 2)
np.fill_diagonal(W, 0)
G = pygsp.graphs.Graph(W)
G2 = build_graph(
data_small,
thresh=thresh,
graphtype="exact",
n_pca=n_pca,
decay=a,
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.TraditionalGraph)
G2 = build_graph(
pdx,
n_pca=None,
precomputed="distance",
thresh=thresh,
decay=a,
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.TraditionalGraph)
G2 = build_graph(
K,
n_pca=None,
precomputed="affinity",
thresh=thresh,
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.TraditionalGraph)
G2 = build_graph(W,
n_pca=None,
precomputed="adjacency",
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.TraditionalGraph)
def test_exact_graph():
k = 3
a = 13
n_pca = 20
data_small = data[np.random.choice(len(data),
len(data) // 2,
replace=False)]
pca = PCA(n_pca, svd_solver='randomized', random_state=42).fit(data_small)
data_small_nu = pca.transform(data_small)
pdx = squareform(pdist(data_small_nu, metric='euclidean'))
knn_dist = np.partition(pdx, k, axis=1)[:, :k]
epsilon = np.max(knn_dist, axis=1)
weighted_pdx = (pdx.T / epsilon).T
K = np.exp(-1 * weighted_pdx**a)
W = K + K.T
W = np.divide(W, 2)
np.fill_diagonal(W, 0)
G = pygsp.graphs.Graph(W)
G2 = build_graph(data_small,
thresh=0,
n_pca=n_pca,
decay=a,
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.TraditionalGraph))
G2 = build_graph(pdx,
n_pca=None,
precomputed='distance',
decay=a,
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.TraditionalGraph))
G2 = build_graph(sp.coo_matrix(K),
n_pca=None,
precomputed='affinity',
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.TraditionalGraph))
G2 = build_graph(K,
n_pca=None,
precomputed='affinity',
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.TraditionalGraph))
G2 = build_graph(W,
n_pca=None,
precomputed='adjacency',
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.TraditionalGraph))