def test_mnn_graph_matrix_gamma():
X, sample_idx = generate_swiss_roll()
bs = 0.8
gamma = np.array([
[1, bs], # 0
[bs, 1]
]) # 3
k = 10
a = 20
metric = 'euclidean'
beta = 0
samples = np.unique(sample_idx)
K = np.zeros((len(X), len(X)))
K[:] = np.nan
K = pd.DataFrame(K)
for si in samples:
X_i = X[sample_idx == si] # get observations in sample i
for sj in samples:
X_j = X[sample_idx == sj] # get observation in sample j
pdx_ij = cdist(X_i, X_j, metric=metric) # pairwise distances
kdx_ij = np.sort(pdx_ij, axis=1) # get kNN
e_ij = kdx_ij[:, k] # dist to kNN
pdxe_ij = pdx_ij / e_ij[:, np.newaxis] # normalize
k_ij = np.exp(-1 * (pdxe_ij**a)) # apply alpha-decaying kernel
if si == sj:
K.iloc[sample_idx == si, sample_idx == sj] = k_ij * \
(1 - beta) # fill out values in K for NN on diagonal
else:
# fill out values in K for NN on diagonal
K.iloc[sample_idx == si, sample_idx == sj] = k_ij
K = np.array(K)
matrix_gamma = pd.DataFrame(np.zeros((len(sample_idx), len(sample_idx))))
for ix, si in enumerate(set(sample_idx)):
for jx, sj in enumerate(set(sample_idx)):
matrix_gamma.iloc[sample_idx == si, sample_idx == sj] = gamma[ix,
jx]
W = np.array((matrix_gamma * np.minimum(K, K.T)) +
((1 - matrix_gamma) * np.maximum(K, K.T)))
np.fill_diagonal(W, 0)
G = pygsp.graphs.Graph(W)
G2 = graphtools.Graph(X,
knn=k + 1,
decay=a,
beta=1 - beta,
kernel_symm='gamma',
gamma=gamma,
distance=metric,
sample_idx=sample_idx,
thresh=0,
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.MNNGraph)
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_transform_sparse_adaptive_pca():
G = build_graph(data, sparse=True, n_pca=True, random_state=42)
assert np.all(G.data_nu == G.transform(G.data))
with assert_raises_message(
ValueError,
"data of shape ({0}, 1) cannot be transformed to graph built on data of shape ({0}, {1}). Expected shape ({0}, {1})".format(
G.data.shape[0], G.data.shape[1]
),
):
G.transform(sp.csr_matrix(G.data)[:, 0])
with assert_raises_message(
ValueError,
"data of shape ({0}, 15) cannot be transformed to graph built on data of shape ({0}, {1}). Expected shape ({0}, {1})".format(
G.data.shape[0], G.data.shape[1]
),
):
G.transform(sp.csr_matrix(G.data)[:, :15])
G2 = build_graph(
data, sparse=True, n_pca=True, rank_threshold=G.rank_threshold, random_state=42
)
assert np.allclose(G2.data_nu, G2.transform(G2.data))
assert np.allclose(G2.data_nu, G.transform(G.data))
G3 = build_graph(data, sparse=True, n_pca=G2.n_pca, random_state=42)
assert np.allclose(G3.data_nu, G3.transform(G3.data))
assert np.allclose(G3.data_nu, G2.transform(G2.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_inverse_transform_dense_no_pca():
G = build_graph(data, n_pca=None)
np.testing.assert_allclose(
data[:, 5:7], G.inverse_transform(G.data_nu, columns=[5, 6]), atol=1e-12
)
assert np.all(G.data == G.inverse_transform(G.data_nu))
with assert_raises_message(
ValueError,
"data of shape ({0},) cannot be inverse transformed from graph built on reduced data of shape ({0}, {1})".format(
data.shape[0], G.data.shape[1]
),
):
G.inverse_transform(G.data[:, 0])
with assert_raises_message(
ValueError,
"data of shape ({0}, 1, 15) cannot be inverse transformed from graph built on reduced data of shape ({0}, {1})".format(
data.shape[0], data.shape[1]
),
):
G.inverse_transform(G.data[:, None, :15])
with assert_raises_message(
ValueError,
"data of shape ({0}, 15) cannot be inverse transformed from graph built on reduced data of shape ({0}, {1})".format(
data.shape[0], data.shape[1]
),
):
G.inverse_transform(G.data[:, :15])
def test_knnmax():
data = datasets.make_swiss_roll()[0]
k = 5
k_max = 10
a = 0.45
thresh = 0
with warnings.catch_warnings():
warnings.filterwarnings("ignore", "K should be symmetric",
RuntimeWarning)
G = build_graph(
data,
n_pca=None, # n_pca,
decay=a,
knn=k - 1,
knn_max=k_max - 1,
thresh=0,
random_state=42,
kernel_symm=None,
)
assert np.all((G.K > 0).sum(axis=1) == k_max)
pdx = squareform(pdist(data, metric="euclidean"))
knn_dist = np.partition(pdx, k, axis=1)[:, :k]
knn_max_dist = np.max(np.partition(pdx, k_max, axis=1)[:, :k_max], axis=1)
epsilon = np.max(knn_dist, axis=1)
pdx_scale = (pdx.T / epsilon).T
K = np.where(pdx <= knn_max_dist[:, None], np.exp(-1 * pdx_scale**a), 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=None, # n_pca,
decay=a,
knn=k - 1,
knn_max=k_max - 1,
thresh=0,
random_state=42,
use_pygsp=True,
)
assert isinstance(G2, graphtools.graphs.kNNGraph)
assert G.N == G2.N
assert np.all(G.dw == G2.dw)
assert (G.W - G2.W).nnz == 0
def test_inverse_transform_dense_no_pca():
G = build_graph(data, n_pca=None)
np.testing.assert_allclose(data[:, 5:7],
G.inverse_transform(G.data_nu, columns=[5, 6]),
atol=1e-12)
assert np.all(G.data == G.inverse_transform(G.data_nu))
assert_raises(ValueError, G.inverse_transform, G.data[:, 0])
assert_raises(ValueError, G.inverse_transform, G.data[:, None, :15])
assert_raises(ValueError, G.inverse_transform, G.data[:, :15])
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,
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.csr_matrix(data_small),
thresh=thresh,
graphtype='exact',
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))
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_transform_sparse_pca():
G = build_graph(data, sparse=True, n_pca=20)
assert np.all(G.data_nu == G.transform(G.data))
with assert_raises_message(
ValueError,
"data of shape ({0}, 1) cannot be transformed to graph built on data of shape ({0}, {1}). Expected shape ({0}, {1})".format(
G.data.shape[0], G.data.shape[1]
),
):
G.transform(sp.csr_matrix(G.data)[:, 0])
with assert_raises_message(
ValueError,
"data of shape ({0}, 15) cannot be transformed to graph built on data of shape ({0}, {1}). Expected shape ({0}, {1})".format(
G.data.shape[0], G.data.shape[1]
),
):
G.transform(sp.csr_matrix(G.data)[:, :15])
def test_transform_sparse_adaptive_pca():
G = build_graph(data, sparse=True, n_pca=True, random_state=42)
assert np.all(G.data_nu == G.transform(G.data))
assert_raises(ValueError, G.transform, sp.csr_matrix(G.data)[:, 0])
assert_raises(ValueError, G.transform, sp.csr_matrix(G.data)[:, :15])
G2 = build_graph(data,
sparse=True,
n_pca=True,
rank_threshold=G.rank_threshold,
random_state=42)
assert np.allclose(G2.data_nu, G2.transform(G2.data))
assert np.allclose(G2.data_nu, G.transform(G.data))
G3 = build_graph(data, sparse=True, n_pca=G2.n_pca, random_state=42)
assert np.allclose(G3.data_nu, G3.transform(G3.data))
assert np.allclose(G3.data_nu, G2.transform(G2.data))
def test_mnn_with_non_zero_indexed_sample_idx():
X, sample_idx = generate_swiss_roll()
G = build_graph(X,
sample_idx=sample_idx,
kernel_symm='gamma',
gamma=0.5,
n_pca=None,
use_pygsp=True)
sample_idx += 1
G2 = build_graph(X,
sample_idx=sample_idx,
kernel_symm='gamma',
gamma=0.5,
n_pca=None,
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.MNNGraph)
def test_transform_dense_no_pca():
G = build_graph(data, n_pca=None)
assert np.all(G.data_nu == G.transform(G.data))
with assert_raises_message(
ValueError,
"data of shape ({0},) cannot be transformed to graph built on data of shape ({0}, {1})".format(
data.shape[0], data.shape[1]
),
):
G.transform(G.data[:, 0])
with assert_raises_message(
ValueError,
"data of shape ({0}, 1, 15) cannot be transformed to graph built on data of shape ({0}, {1})".format(
data.shape[0], data.shape[1]
),
):
G.transform(G.data[:, None, :15])
with assert_raises_message(
ValueError,
"data of shape ({0}, 15) cannot be transformed to graph built on data of shape ({0}, {1})".format(
data.shape[0], data.shape[1]
),
):
G.transform(G.data[:, :15])
def test_mnn_with_string_sample_idx():
X, sample_idx = generate_swiss_roll()
G = build_graph(
X,
sample_idx=sample_idx,
kernel_symm="mnn",
theta=0.5,
n_pca=None,
use_pygsp=True,
)
sample_idx = np.where(sample_idx == 0, "a", "b")
G2 = build_graph(
X,
sample_idx=sample_idx,
kernel_symm="mnn",
theta=0.5,
n_pca=None,
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.MNNGraph)
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,
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,
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.lil_matrix(K),
n_pca=None,
precomputed='affinity',
thresh=thresh,
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.dok_matrix(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_transform_dense_no_pca():
G = build_graph(data, n_pca=None)
assert np.all(G.data_nu == G.transform(G.data))
assert_raises(ValueError, G.transform, G.data[:, 0])
assert_raises(ValueError, G.transform, G.data[:, None, :15])
assert_raises(ValueError, G.transform, G.data[:, :15])
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_transform_sparse_pca():
G = build_graph(data, sparse=True, n_pca=20)
assert np.all(G.data_nu == G.transform(G.data))
assert_raises(ValueError, G.transform, sp.csr_matrix(G.data)[:, 0])
assert_raises(ValueError, G.transform, sp.csr_matrix(G.data)[:, :15])
