def get_sourcetarget_split_p300(source, target, ncovs_train):
X_source = source['signals']
y_source = source['labels'].flatten()
covs_source = XdawnCovariances(classes=[2]).fit_transform(
X_source, y_source)
source = {}
source['covs'] = covs_source
source['labels'] = y_source
X_target = target['signals']
y_target = target['labels'].flatten()
if ncovs_train is None:
ncovs_train = np.sum(y_target == 2)
sel = np.arange(len(y_target))
np.random.shuffle(sel)
X_target = X_target[sel]
y_target = y_target[sel]
idx_erps = np.where(y_target == 2)[0][:ncovs_train]
idx_rest = np.where(
y_target == 1)[0][:ncovs_train *
5] # because there's one ERP in every 6 flashes
idx_train = np.concatenate([idx_erps, idx_rest])
idx_test = np.array(
[i for i in range(len(y_target)) if i not in idx_train])
erp = XdawnCovariances(classes=[2])
erp.fit(X_target[idx_train], y_target[idx_train])
target_train = {}
covs_target_train = erp.transform(X_target[idx_train])
y_target_train = y_target[idx_train]
target_train['covs'] = covs_target_train
target_train['labels'] = y_target_train
target_test = {}
covs_target_test = erp.transform(X_target[idx_test])
y_target_test = y_target[idx_test]
target_test['covs'] = covs_target_test
target_test['labels'] = y_target_test
return source, target_train, target_test
subject_dir_list = test_list_np[testing_participant_id]
subject_epoch = np.empty((0, len(channels), epoch_len), float)
for trial_id in range(trial_per_subj):
subject_dir = subject_dir_list[trial_id]
data = generate_epoch('FeedBackEvent', './data/test/'+subject_dir,
channels, fs, lowcut, highcut, epoch_s, epoch_e, bl_s, bl_e)
subject_epoch = np.vstack((subject_epoch, data))
subject_epoch = np.reshape(
subject_epoch, (1, stimulus_per_subj, len(channels), epoch_len))
test_data_list = np.vstack((test_data_list, subject_epoch))
print('Epoched testing data shape: ' + str(test_data_list.shape))
# ########################## apply data preprocessing ############################
y_train = pd.read_csv('data/TrainLabels.csv')['Prediction'].values
XC = XdawnCovariances(nfilter=5)
X_train = XC.fit_transform(np.reshape(
train_data_list, (total_training_participant*stimulus_per_subj, len(channels), epoch_len)), y_train)
X_train = TangentSpace(metric='riemann').fit_transform(X_train)
X_test = XC.transform(np.reshape(
test_data_list, (10*stimulus_per_subj, len(channels), epoch_len)))
X_test = TangentSpace(metric='riemann').transform(X_test)
print('Preprocessed training data shape: ' + str(X_train.shape))
print('Preprocessed testing data shape: ' + str(X_test.shape))
# ############################## save data to disk ###############################
np.save('./data/train_data.npy', train_data_list)
np.save('./data/test_data.npy', test_data_list)
np.save('./data/X_train', X_train)
np.save('./data/X_test', X_test)
