def preprocess_cnt(cnt, final_hz, half_before):
log.info("Resampling...")
cnt = resample_cnt(cnt, 250.0)
log.info("Standardizing...")
cnt = mne_apply(
lambda a: exponential_running_standardize(
a.T, factor_new=1e-3, init_block_size=1000, eps=1e-4
).T,
cnt,
)
if half_before:
cnt = resample_cnt(cnt, final_hz / 2.0)
cnt = resample_cnt(cnt, final_hz)
return cnt
def get_data():
import os
os.sys.path.append('/home/schirrmr/braindecode/code/braindecode/')
from braindecode.datautil.trial_segment import create_signal_target_from_raw_mne
from braindecode.datasets.bbci import BBCIDataset
from braindecode.mne_ext.signalproc import mne_apply, resample_cnt
from braindecode.datautil.signalproc import exponential_running_standardize
subject_id = 4 # 1-14
loader = BBCIDataset(
'/data/schirrmr/schirrmr/HGD-public/reduced/train/{:d}.mat'.format(
subject_id),
load_sensor_names=['C3'])
cnt = loader.load()
cnt = cnt.drop_channels(['STI 014'])
from collections import OrderedDict
marker_def = OrderedDict([('Right Hand', [1]), (
'Left Hand',
[2],
), ('Rest', [3]), ('Feet', [4])])
# Here you can choose a larger sampling rate later
# Right now chosen very small to allow fast initial experiments
cnt = resample_cnt(cnt, new_fs=500)
cnt = mne_apply(
lambda a: exponential_running_standardize(
a.T, factor_new=1e-3, init_block_size=1000, eps=1e-4).T, cnt)
ival = [0, 2000] # ms to cut trial
dataset = create_signal_target_from_raw_mne(cnt, marker_def, ival)
return dataset.X, dataset.y
def load_data(filenames, sensor_names, name_to_start_codes,
name_to_stop_codes, trial_ival, break_ival,
min_break_length_ms, max_break_length_ms, input_time_length,
filename_to_extra_args):
all_sets = []
original_args = locals()
for filename in filenames:
kwargs = deepcopy(original_args)
if filename in filename_to_extra_args:
kwargs.update(filename_to_extra_args[filename])
log.info("Loading {:s}...".format(filename))
cnt = BBCIDataset(filename, load_sensor_names=sensor_names).load()
cnt = cnt.drop_channels(['STI 014'])
log.info("Resampling...")
cnt = resample_cnt(cnt, 100)
log.info("Standardizing...")
cnt = mne_apply(
lambda a: exponential_running_standardize(
a.T, init_block_size=50).T, cnt)
log.info("Transform to set...")
full_set = (create_signal_target_with_breaks_from_mne(
cnt,
kwargs['name_to_start_codes'],
kwargs['trial_ival'],
kwargs['name_to_stop_codes'],
kwargs['min_break_length_ms'],
kwargs['max_break_length_ms'],
kwargs['break_ival'],
prepad_trials_to_n_samples=kwargs['input_time_length'],
))
all_sets.append(full_set)
return all_sets
def load_bbci_data(filename, low_cut_hz):
load_sensor_names = None
loader = BBCIDataset(filename, load_sensor_names=load_sensor_names)
log.info("Loading data...")
cnt = loader.load()
# Cleaning: First find all trials that have absolute microvolt values
# larger than +- 800 inside them and remember them for removal later
log.info("Cutting trials...")
marker_def = OrderedDict([('Right Hand', [1]), ('Left Hand', [2],),
('Rest', [3]), ('Feet', [4])])
clean_ival = [0, 4000]
set_for_cleaning = create_signal_target_from_raw_mne(cnt, marker_def,
clean_ival)
clean_trial_mask = np.max(np.abs(set_for_cleaning.X), axis=(1, 2)) < 800
log.info("Clean trials: {:3d} of {:3d} ({:5.1f}%)".format(
np.sum(clean_trial_mask),
len(set_for_cleaning.X),
np.mean(clean_trial_mask) * 100))
# now pick only sensors with C in their name
# as they cover motor cortex
C_sensors = ['FC5', 'FC1', 'FC2', 'FC6', 'C3', 'C4', 'CP5',
'CP1', 'CP2', 'CP6', 'FC3', 'FCz', 'FC4', 'C5', 'C1', 'C2',
'C6',
'CP3', 'CPz', 'CP4', 'FFC5h', 'FFC3h', 'FFC4h', 'FFC6h',
'FCC5h',
'FCC3h', 'FCC4h', 'FCC6h', 'CCP5h', 'CCP3h', 'CCP4h', 'CCP6h',
'CPP5h',
'CPP3h', 'CPP4h', 'CPP6h', 'FFC1h', 'FFC2h', 'FCC1h', 'FCC2h',
'CCP1h',
'CCP2h', 'CPP1h', 'CPP2h']
cnt = cnt.pick_channels(C_sensors)
# Further preprocessings
log.info("Resampling...")
cnt = resample_cnt(cnt, 250.0)
print("REREFERENCING")
log.info("Highpassing...")
cnt = mne_apply(lambda a: highpass_cnt(a, low_cut_hz, cnt.info['sfreq'], filt_order=3, axis=1),cnt)
log.info("Standardizing...")
cnt = mne_apply(lambda a: exponential_running_standardize(a.T, factor_new=1e-3,init_block_size=1000,eps=1e-4).T,cnt)
# Trial interval, start at -500 already, since improved decoding for networks
ival = [-500, 4000]
dataset = create_signal_target_from_raw_mne(cnt, marker_def, ival)
dataset.X = dataset.X[clean_trial_mask]
dataset.y = dataset.y[clean_trial_mask]
return dataset.X, dataset.y
def load(self):
cnt = self.set_loaders[0].load()
for loader in self.set_loaders[1:]:
next_cnt = loader.load()
# always sample down to lowest common denominator
if next_cnt.fs > cnt.fs:
log.warning("Next set has larger sampling rate ({:d}) "
"than before ({:d}), resampling next set".format(
next_cnt.fs, cnt.fs))
next_cnt = resample_cnt(next_cnt, cnt.fs)
if next_cnt.fs < cnt.fs:
log.warning("Next set has smaller sampling rate ({:d}) "
"than before ({:d}), resampling set so far".format(
next_cnt.fs, cnt.fs))
cnt = resample_cnt(cnt, next_cnt.fs)
cnt = concatenate_raws_with_events(cnt, next_cnt)
return cnt
def load_bbci_data(filename, low_cut_hz, debug=False):
load_sensor_names = None
if debug:
load_sensor_names = ['C3', 'C4', 'C2']
loader = BBCIDataset(filename, load_sensor_names=load_sensor_names)
log.info("Loading data...")
cnt = loader.load()
log.info("Cutting trials...")
marker_def = OrderedDict([('Right Hand', [1]), (
'Left Hand',
[2],
), ('Rest', [3]), ('Feet', [4])])
clean_ival = [0, 4000]
set_for_cleaning = create_signal_target_from_raw_mne(
cnt, marker_def, clean_ival)
clean_trial_mask = np.max(np.abs(set_for_cleaning.X), axis=(1, 2)) < 800
log.info("Clean trials: {:3d} of {:3d} ({:5.1f}%)".format(
np.sum(clean_trial_mask), len(set_for_cleaning.X),
np.mean(clean_trial_mask) * 100))
# lets convert to millivolt for numerical stability of next operations
C_sensors = [
'FC5', 'FC1', 'FC2', 'FC6', 'C3', 'C4', 'CP5', 'CP1', 'CP2', 'CP6',
'FC3', 'FCz', 'FC4', 'C5', 'C1', 'C2', 'C6', 'CP3', 'CPz', 'CP4',
'FFC5h', 'FFC3h', 'FFC4h', 'FFC6h', 'FCC5h', 'FCC3h', 'FCC4h', 'FCC6h',
'CCP5h', 'CCP3h', 'CCP4h', 'CCP6h', 'CPP5h', 'CPP3h', 'CPP4h', 'CPP6h',
'FFC1h', 'FFC2h', 'FCC1h', 'FCC2h', 'CCP1h', 'CCP2h', 'CPP1h', 'CPP2h'
]
if debug:
C_sensors = load_sensor_names
cnt = cnt.pick_channels(C_sensors)
cnt = mne_apply(lambda a: a * 1e6, cnt)
log.info("Resampling...")
cnt = resample_cnt(cnt, 250.0)
log.info("Highpassing...")
cnt = mne_apply(
lambda a: highpass_cnt(
a, low_cut_hz, cnt.info['sfreq'], filt_order=3, axis=1), cnt)
log.info("Standardizing...")
cnt = mne_apply(
lambda a: exponential_running_standardize(
a.T, factor_new=1e-3, init_block_size=1000, eps=1e-4).T, cnt)
ival = [-500, 4000]
dataset = create_signal_target_from_raw_mne(cnt, marker_def, ival)
return dataset
def import_EEGData_test(start=0, end=9, dir='../data_HGD/test/'):
X, y = [], []
for i in range(start, end):
dataFile = str(dir + str(i + 1) + '.mat')
print("File:", dataFile, " loading...")
cnt = BBCIDataset(filename=dataFile, load_sensor_names=None).load()
marker_def = OrderedDict([('Right Hand', [1]), (
'Left Hand',
[2],
), ('Rest', [3]), ('Feet', [4])])
clean_ival = [0, 4000]
set_for_cleaning = create_signal_target_from_raw_mne(
cnt, marker_def, clean_ival)
clean_trial_mask = np.max(np.abs(set_for_cleaning.X),
axis=(1, 2)) < 800
C_sensors = [
'FC5', 'FC1', 'FC2', 'FC6', 'C3', 'C4', 'CP5', 'CP1', 'CP2', 'CP6',
'FC3', 'FCz', 'FC4', 'C5', 'C1', 'C2', 'C6', 'CP3', 'CPz', 'CP4',
'FFC5h', 'FFC3h', 'FFC4h', 'FFC6h', 'FCC5h', 'FCC3h', 'FCC4h',
'FCC6h', 'CCP5h', 'CCP3h', 'CCP4h', 'CCP6h', 'CPP5h', 'CPP3h',
'CPP4h', 'CPP6h', 'FFC1h', 'FFC2h', 'FCC1h', 'FCC2h', 'CCP1h',
'CCP2h', 'CPP1h', 'CPP2h'
]
cnt = cnt.pick_channels(C_sensors)
cnt = resample_cnt(cnt, 250.0)
cnt = mne_apply(
lambda a: exponential_running_standardize(
a.T, factor_new=1e-3, init_block_size=1000, eps=1e-4).T, cnt)
ival = [-500, 4000]
dataset = create_signal_target_from_raw_mne(cnt, marker_def, ival)
dataset.X = dataset.X[clean_trial_mask]
dataset.X = dataset.X[:, :, np.newaxis, :]
dataset.y = dataset.y[clean_trial_mask]
dataset.y = dataset.y[:, np.newaxis]
X.extend(dataset.X)
y.extend(dataset.y)
X = data_in_one(np.array(X))
y = np.array(y)
print("X:", X.shape)
print("y:", y.shape)
dataset = EEGDataset(X, y)
return dataset
def resample(cnt, fs):
return resample_cnt(cnt, fs)
