def test_sample_gaussian_spd():
"""Test Riemannian Gaussian sampling."""
n_matrices, n_dim, sigma = 50, 16, 2.
mean = np.eye(n_dim)
X = sample_gaussian_spd(n_matrices, mean, sigma, random_state=42)
assert X.shape == (n_matrices, n_dim, n_dim) # X shape mismatch
assert is_spd(X) # X is an array of SPD matrices
def test_hankel_covariances_delays(rndstate):
n_matrices, n_channels, n_times = 2, 3, 100
x = rndstate.randn(n_matrices, n_channels, n_times)
cov = HankelCovariances(delays=[1, 2])
cov.fit(x)
covmats = cov.fit_transform(x)
assert covmats.shape == (n_matrices, 3 * n_channels, 3 * n_channels)
assert is_spd(covmats)
def test_hankel_covariances(rndstate):
"""Test Hankel Covariances"""
n_matrices, n_channels, n_times = 2, 3, 100
x = rndstate.randn(n_matrices, n_channels, n_times)
cov = HankelCovariances()
cov.fit(x)
covmats = cov.fit_transform(x)
assert cov.get_params() == dict(estimator="scm", delays=4)
assert covmats.shape == (n_matrices, 4 * n_channels, 4 * n_channels)
assert is_spd(covmats)
def test_shrinkage(shrinkage, rndstate):
"""Test Shrinkage"""
n_matrices, n_channels, n_times = 2, 3, 100
x = rndstate.randn(n_matrices, n_channels, n_times)
covmats = Covariances().fit_transform(x)
sh = Shrinkage(shrinkage=shrinkage)
covmats = sh.fit(covmats).transform(covmats)
assert sh.get_params() == dict(shrinkage=shrinkage)
assert covmats.shape == (n_matrices, n_channels, n_channels)
assert is_spd(covmats)
def test_block_covariances_blocks(block_size, rndstate):
"""Test BlockCovariances fit"""
n_matrices, n_channels, n_times = 2, 12, 100
x = rndstate.randn(n_matrices, n_channels, n_times)
cov = BlockCovariances(block_size=block_size)
cov.fit(x)
covmats = cov.fit_transform(x)
assert cov.get_params() == dict(block_size=block_size, estimator='scm')
assert covmats.shape == (n_matrices, n_channels, n_channels)
assert is_spd(covmats)
def test_covariances(estimator, rndstate):
"""Test Covariances"""
n_matrices, n_channels, n_times = 2, 3, 100
x = rndstate.randn(n_matrices, n_channels, n_times)
cov = Covariances(estimator=estimator)
cov.fit(x)
covmats = cov.fit_transform(x)
assert cov.get_params() == dict(estimator=estimator)
assert covmats.shape == (n_matrices, n_channels, n_channels)
assert is_spd(covmats)
def test_generate_random_spd_matrix():
"""Test function for sampling outliers"""
n_matrices, n_dim, sigma = 100, 8, 1.
mean = generate_random_spd_matrix(n_dim)
X = make_outliers(n_matrices=n_matrices,
mean=mean,
sigma=sigma,
outlier_coeff=10,
random_state=None)
assert X.shape == (n_matrices, n_dim, n_dim) # X shape mismatch
assert is_spd(X) # X is an array of SPD matrices
def test_gaussian_blobs():
"""Test function for sampling Gaussian blobs."""
n_matrices, n_dim = 50, 8
X, y = make_gaussian_blobs(n_matrices=n_matrices,
n_dim=n_dim,
class_sep=2.0,
class_disp=1.0,
return_centers=False,
random_state=None)
assert X.shape == (2 * n_matrices, n_dim, n_dim) # X shape mismatch
assert is_spd(X) # X is an array of SPD matrices
assert y.shape == (2 * n_matrices, ) # y shape mismatch
assert np.unique(y).shape == (2, ) # Unexpected number of classes
assert sum(y == 0) == n_matrices # Unexpected number of samples in class 0
assert sum(y == 1) == n_matrices # Unexpected number of samples in class 1
_, _, centers = make_gaussian_blobs(n_matrices=1,
n_dim=n_dim,
class_sep=2.0,
class_disp=1.0,
return_centers=True,
random_state=None)
assert centers.shape == (2, n_dim, n_dim) # centers shape mismatch
def test_generate_random_spd_matrix():
"""Test generating random SPD matrix"""
n_dim = 16
X = generate_random_spd_matrix(n_dim, random_state=None)
assert X.shape == (n_dim, n_dim) # X shape mismatch
assert is_spd(X) # X is a SPD matrix
