def __init__(self, n_components=4, reg=None, log=None,
transform_into='csp_space', norm_trace=False, name="CSP"):
super(CSP, self).__init__(name)
self.n_components = n_components
self.reg = reg
self.log = log
self.transform_into = transform_into
self.norm_trace = norm_trace
self.model = mne_CSP(n_components, reg, log, 'epoch', transform_into, norm_trace)
s_id[s],
npp_params,
clean=False,
physical=True,
downsample=False)
data_size = y_train.shape[0]
shuffle_index = utils.shuffle_data(data_size)
x_train = x_train[shuffle_index]
x_train = np.squeeze(x_train)
y_train = y_train[shuffle_index]
print(x_train.shape)
csp = mne_CSP(n_components=6,
transform_into='average_power',
log=False,
cov_est='epoch')
# build model
lr = LogisticRegression(solver='sag', max_iter=200, C=0.01)
model = Pipeline([('csp_power', csp), ('LR', lr)])
model.fit(x_train, y_train)
# Test Model
y_pred = np.argmax(model.predict_proba(np.squeeze(x_test)), axis=1)
bca = utils.bca(y_test, y_pred)
acc = np.sum(y_pred == y_test).astype(np.float32) / len(y_pred)
print('{}: acc-{} bca-{}'.format(data_name, acc, bca))
acc_mean += acc
bca_mean += bca