def test_precomputed_interpolate():
with assert_raises_message(ValueError,
"Cannot extend kernel on precomputed graph"):
G = build_graph(squareform(pdist(data)),
n_pca=None,
precomputed="distance")
G.build_kernel_to_data(data)
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_sample_idx_and_precomputed():
build_graph(
squareform(pdist(data)),
n_pca=None,
sample_idx=np.arange(10),
precomputed="distance",
decay=10,
)
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_precomputed_with_pca():
with assert_warns_message(
RuntimeWarning,
"n_pca cannot be given on a precomputed graph. Setting n_pca=None",
):
build_graph(squareform(pdist(data)),
precomputed="distance",
n_pca=20,
decay=10)
def test_sample_idx_and_precomputed():
with assert_raises_message(
ValueError,
"MNNGraph does not support precomputed values. Use `graphtype='exact'` and `sample_idx=None` or `precomputed=None`",
):
build_graph(
squareform(pdist(data)),
n_pca=None,
sample_idx=np.arange(10),
precomputed="distance",
decay=10,
)
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_truncated_exact_graph_no_pca():
k = 3
a = 13
n_pca = None
thresh = 1e-4
data_small = data[np.random.choice(len(data),
len(data) // 10,
replace=False)]
pdx = squareform(pdist(data_small, 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(
sp.csr_matrix(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)
def test_sparse_alpha_knn_graph():
data = datasets.make_swiss_roll()[0]
k = 5
a = 0.45
thresh = 0.01
pdx = squareform(pdist(data, metric='euclidean'))
knn_dist = np.partition(pdx, k, axis=1)[:, :k]
epsilon = np.max(knn_dist, axis=1)
pdx = (pdx.T / epsilon).T
K = np.exp(-1 * pdx**a)
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=None, # n_pca,
decay=a, knn=k, thresh=thresh,
random_state=42, use_pygsp=True)
assert(np.abs(G.W - G2.W).max() < thresh)
assert(G.N == G2.N)
assert(isinstance(G2, graphtools.graphs.kNNGraph))
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, 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_precomputed_interpolate():
G = build_graph(squareform(pdist(data)),
n_pca=None,
precomputed='distance')
G.build_kernel_to_data(data)
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))
def test_precomputed_with_pca():
build_graph(squareform(pdist(data)),
precomputed='distance',
n_pca=20,
decay=10)
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_precomputed_with_pca():
build_graph(squareform(pdist(data)), precomputed="distance", n_pca=20)
def test_exact_graph():
k = 3
a = 13
n_pca = 20
bandwidth_scale = 1.3
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) * bandwidth_scale
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 - 1,
random_state=42,
bandwidth_scale=bandwidth_scale,
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",
bandwidth_scale=bandwidth_scale,
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(
sp.coo_matrix(K),
n_pca=None,
precomputed="affinity",
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",
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_invalid_precomputed():
build_graph(squareform(pdist(data)),
n_pca=None,
precomputed='hello world',
decay=10)
def test_truncated_exact_graph_sparse():
k = 3
a = 13
n_pca = 20
thresh = 1e-4
data_small = data[np.random.choice(len(data),
len(data) // 2,
replace=False)]
pca = TruncatedSVD(n_pca, 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(
sp.coo_matrix(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_allclose(G2.W.toarray(), G.W.toarray())
assert isinstance(G2, graphtools.graphs.TraditionalGraph)
G2 = build_graph(
sp.bsr_matrix(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(
sp.lil_matrix(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(
sp.dok_matrix(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)
