def test_FGDA_transform():
"""Test transform of FGDA"""
covset = generate_cov(10,3)
labels = np.array([0,1]).repeat(5)
ts = FGDA(metric='riemann')
ts.fit(covset,labels)
ts.transform(covset)
def test_FGDA_transform():
"""Test transform of FGDA."""
covset = generate_cov(10, 3)
labels = np.array([0, 1]).repeat(5)
ts = FGDA(metric='riemann')
ts.fit(covset, labels)
ts.transform(covset)
def test_FGDA_init(tsupdate, metric, get_covmats, get_labels):
n_classes, n_trials, n_channels = 2, 6, 3
labels = get_labels(n_trials, n_classes)
covmats = get_covmats(n_trials, n_channels)
ts = FGDA(metric=metric, tsupdate=tsupdate)
ts.fit(covmats, labels)
Xtr = ts.transform(covmats)
assert Xtr.shape == (n_trials, n_channels, n_channels)
def learn_ts_fgda(X_train, y_train, T=0, NT=1):
classes = [T, NT]
train_fgda = FGDA()
train_fgda.fit(X=X_train, y=y_train)
X_train_fgda = train_fgda.transform(X=X_train)
centroids_train_fgda = [
mean_covariance(X_train_fgda[y_train == l, :, :], metric='riemann')
for l in classes
]
return X_train_fgda, centroids_train_fgda, train_fgda
def test_FGDA_fit():
"""Test Fit of FGDA."""
covset = generate_cov(10, 3)
labels = np.array([0, 1]).repeat(5)
ts = FGDA(metric='riemann')
ts.fit(covset, labels)