def test_prepare_mvpa_data():
processed_data, labels = io.prepare_mvpa_data(dir, extension, mask_file, epoch_file)
expected_processed_data = np.load(os.path.join(os.path.dirname(__file__),
'data/expected_processed_data.npy'))
assert len(processed_data) == len(expected_processed_data), \
'numbers of epochs do not match in test_prepare_mvpa_data'
for idx in range(len(processed_data)):
assert np.allclose(processed_data[idx], expected_processed_data[idx]), \
'raw data do not match'
assert np.array_equal(labels, expected_labels), \
'the labels do not match in test_prepare_mvpa_data'
def test_prepare_mvpa_data():
processed_data, labels = io.prepare_mvpa_data(dir, extension, mask_file,
epoch_file)
expected_processed_data = np.load(
os.path.join(os.path.dirname(__file__),
'data/expected_processed_data.npy'))
assert len(processed_data) == len(expected_processed_data), \
'numbers of epochs do not match in test_prepare_mvpa_data'
for idx in range(len(processed_data)):
assert np.allclose(processed_data[idx], expected_processed_data[idx]), \
'raw data do not match'
assert np.array_equal(labels, expected_labels), \
'the labels do not match in test_prepare_mvpa_data'
#from sklearn.externals import joblib
format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s'
# if want to output log to a file instead of outputting log to the console,
# replace "stream=sys.stdout" with "filename='fcma.log'"
logging.basicConfig(level=logging.INFO, format=format, stream=sys.stdout)
logger = logging.getLogger(__name__)
# python mvpa_classification.py face_scene bet.nii.gz face_scene/visual_top_mask.nii.gz face_scene/fs_epoch_labels.npy
if __name__ == '__main__':
data_dir = sys.argv[1]
extension = sys.argv[2]
mask_file = sys.argv[3]
epoch_file = sys.argv[4]
processed_data, labels = io.prepare_mvpa_data(data_dir, extension, mask_file, epoch_file)
# transpose data to facilitate training and prediction
processed_data = processed_data.T
# no shrinking, set C=10
clf = svm.SVC(kernel='rbf', shrinking=False, C=10)
training_data = processed_data[0:204]
test_data = processed_data[204:]
clf.fit(training_data, labels[0:204])
# joblib can be used for saving and loading models
#joblib.dump(clf, 'model/logistic.pkl')
#clf = joblib.load('model/svm.pkl')
print(clf.predict(test_data))
print(clf.decision_function(test_data))
print(np.asanyarray(labels[204:]))
# python mvpa_classification.py face_scene bet.nii.gz face_scene/visual_top_mask.nii.gz face_scene/fs_epoch_labels.npy
if __name__ == '__main__':
data_dir = sys.argv[1]
extension = sys.argv[2]
mask_file = sys.argv[3]
epoch_file = sys.argv[4]
epoch_list = np.load(epoch_file)
num_subjects = len(epoch_list)
num_epochs_per_subj = epoch_list[0].shape[1]
logger.info(
'doing MVPA training and classification on %d subjects, each of which has %d epochs'
% (num_subjects, num_epochs_per_subj))
processed_data, labels = io.prepare_mvpa_data(data_dir, extension,
mask_file, epoch_file)
# transpose data to facilitate training and prediction
processed_data = processed_data.T
clf = svm.SVC(kernel='linear', shrinking=False, C=1)
# doing leave-one-subject-out cross validation
for i in range(num_subjects):
leave_start = i * num_epochs_per_subj
leave_end = (i + 1) * num_epochs_per_subj
training_data = np.concatenate(
(processed_data[0:leave_start], processed_data[leave_end:]),
axis=0)
test_data = processed_data[leave_start:leave_end]
training_labels = np.concatenate(
(labels[0:leave_start], labels[leave_end:]), axis=0)
