def test_kernel(ker, rndstate, get_covmats):
"""Test Kernel build"""
n_matrices, n_channels = 12, 3
cov = get_covmats(n_matrices, n_channels)
K = ker(cov, cov)
assert is_spsd(K)
assert K.shape == (n_matrices, n_matrices)
def test_erp_covariances_classes(rndstate, get_labels):
n_matrices, n_channels, n_times, n_classes = 4, 3, 100, 2
x = rndstate.randn(n_matrices, n_channels, n_times)
labels = get_labels(n_matrices, n_classes)
cov = ERPCovariances(classes=[0])
covmats = cov.fit_transform(x, labels)
assert covmats.shape == (n_matrices, 2 * n_channels, 2 * n_channels)
assert is_spsd(covmats)
def test_xdawn_covariances_applyfilters(rndstate, get_labels):
n_classes, nfilter = 2, 2
n_matrices, n_channels, n_times = 4, 6, 100
x = rndstate.randn(n_matrices, n_channels, n_times)
labels = get_labels(n_matrices, n_classes)
cov = XdawnCovariances(nfilter=nfilter, applyfilters=False)
covmats = cov.fit_transform(x, labels)
covsize = n_classes * nfilter + n_channels
assert covmats.shape == (n_matrices, covsize, covsize)
assert is_spsd(covmats)
def test_erp_covariances(estimator, svd, rndstate, get_labels):
"""Test fit ERPCovariances"""
n_classes, n_matrices, n_channels, n_times = 2, 4, 3, 100
x = rndstate.randn(n_matrices, n_channels, n_times)
labels = get_labels(n_matrices, n_classes)
cov = ERPCovariances(estimator=estimator, svd=svd)
covmats = cov.fit_transform(x, labels)
if svd is None:
covsize = (n_classes + 1) * n_channels
else:
covsize = n_classes * svd + n_channels
assert cov.get_params() == dict(classes=None, estimator=estimator, svd=svd)
assert covmats.shape == (n_matrices, covsize, covsize)
assert is_spsd(covmats)
def test_cosp_covariances(rndstate):
"""Test fit CospCovariances"""
n_matrices, n_channels, n_times = 2, 3, 1000
x = rndstate.randn(n_matrices, n_channels, n_times)
cov = CospCovariances()
cov.fit(x)
covmats = cov.transform(x)
assert cov.get_params() == dict(window=128,
overlap=0.75,
fmin=None,
fmax=None,
fs=None)
n_freqs = 65
assert covmats.shape == (n_matrices, n_channels, n_channels, n_freqs)
assert is_spsd(covmats.transpose(0, 3, 1, 2))
def test_coherences(coh, rndstate):
"""Test fit Coherences"""
n_matrices, n_channels, n_times = 2, 5, 200
x = rndstate.randn(n_matrices, n_channels, n_times)
cov = Coherences(coh=coh)
cov.fit(x)
covmats = cov.fit_transform(x)
assert cov.get_params() == dict(window=128,
overlap=0.75,
fmin=None,
fmax=None,
fs=None,
coh=coh)
n_freqs = 65
assert covmats.shape == (n_matrices, n_channels, n_channels, n_freqs)
if coh in ["ordinary", "instantaneous"]:
assert is_spsd(covmats.transpose(0, 3, 1, 2))
def test_xdawn_covariances_nfilter(nfilter, rndstate, get_labels):
"""Test fit XdawnCovariances"""
n_classes, n_matrices, n_channels, n_times = 2, 4, 8, 100
x = rndstate.randn(n_matrices, n_channels, n_times)
labels = get_labels(n_matrices, n_classes)
cov = XdawnCovariances(nfilter=nfilter)
covmats = cov.fit_transform(x, labels)
assert cov.get_params() == dict(
nfilter=nfilter,
applyfilters=True,
classes=None,
estimator="scm",
xdawn_estimator="scm",
baseline_cov=None,
)
covsize = 2 * (n_classes * nfilter)
assert covmats.shape == (n_matrices, covsize, covsize)
assert is_spsd(covmats)