def _get_single_subject_data(self, subject, stack_sessions):
"""return data for a single subject"""
all_files = []
raw_fnames = eegbci.load_data(
subject,
runs=self.hand_runs,
verbose='ERROR',
base_url='http://www.physionet.org/pn4/eegmmidb/')
raw_files = [
read_raw_edf(f, preload=True, verbose='ERROR') for f in raw_fnames
]
# strip channel names of "." characters
[raw.rename_channels(lambda x: x.strip('.')) for raw in raw_files]
all_files.extend(raw_files)
raw_feet_fnames = eegbci.load_data(subject,
runs=self.feet_runs,
verbose='ERROR')
raw_feet_files = [
read_raw_edf(f, preload=True, verbose='ERROR')
for f in raw_feet_fnames
]
for raw in raw_feet_files:
events = mne.find_events(raw)
# Event values are added together, previous and current (1,2,3->1,4,5)
events[events[:, 2] != 1, 2] = 2
events[events[:, 2] == 1, 2] = 0
raw.add_events(events)
raw.rename_channels(lambda x: x.strip('.'))
all_files.extend(raw_feet_files)
if stack_sessions:
return [all_files]
else:
return [[all_files]]
def _get_single_subject_data(self, subject, stack_sessions):
"""return data for a single subject"""
all_files = []
raw_fnames = eegbci.load_data(subject,
runs=self.hand_runs,
verbose='ERROR')
raw_files = [
read_raw_edf(f, preload=True, verbose='ERROR') for f in raw_fnames
]
# strip channel names of "." characters
[raw.rename_channels(lambda x: x.strip('.')) for raw in raw_files]
all_files.extend(raw_files)
raw_feet_fnames = eegbci.load_data(subject,
runs=self.feet_runs,
verbose='ERROR')
raw_feet_files = [
read_raw_edf(f, preload=True, verbose='ERROR')
for f in raw_feet_fnames
]
for raw in raw_feet_files:
events = mne.find_events(raw)
events[events[:, 2] == 2, 2] = 2
events[events[:, 2] == 3, 2] = 2
events[events[:, 2] == 1, 2] = 0
raw.add_events(events)
raw.rename_channels(lambda x: x.strip('.'))
all_files.extend(raw_feet_files)
if not stack_sessions:
return [[all_files]]
else:
return [all_files]
def loadthings(subject):
runs = [6, 10, 14]
raw_fnames = eegbci.load_data(subject, runs)
raw = concatenate_raws([read_raw_edf(f, preload=True) for f in raw_fnames])
raw_fnames = eegbci.load_data(subject, runs)
raw = concatenate_raws([read_raw_edf(f, preload=True) for f in raw_fnames])
eegbci.standardize(raw)
#create 10-05 system
montage = make_standard_montage('standard_1005')
raw.set_montage(montage)
raw.filter(7, 13)
events, _ = events_from_annotations(raw, event_id=dict(T1=0, T2=1))
#0: left, 1:right
picks = pick_types(raw.info,
meg=False,
eeg=True,
stim=False,
eog=False,
exclude='bads')
tmin, tmax = -1, 4
epochs = Epochs(raw,
events,
None,
tmin,
tmax,
proj=True,
picks=picks,
baseline=None,
preload=True)
#epochs_train=epochs.copy().crop(0,2)
epochs_train = epochs.copy().crop(0, 2)
labels = epochs.events[:, -1]
# %%
epochs_train_data = epochs_train.get_data()
labels = epochs_train.events[:, -1]
ad = np.array(epochs_train_data)
All_Data = ad.reshape(
64, epochs_train_data.shape[2] * epochs_train_data.shape[0])
labels = labels.reshape(45, 1)
extended = []
for i in range(321):
extended.append(labels)
extended = np.array(extended)
extended = extended.reshape(45, 321)
extended = extended.T
Labels = extended
#np.savetxt("pythondata/extended.csv", extended)
row, column = Labels.shape
Labels = Labels.reshape(1, row * column)
Labels = Labels.T
return All_Data, Labels
def data_path(self, subject, path=None, force_update=False,
update_path=None, verbose=None):
if subject not in self.subject_list:
raise(ValueError("Invalid subject number"))
paths = []
paths += eegbci.load_data(subject, runs=self.feet_runs,
verbose=verbose)
paths += eegbci.load_data(subject, runs=self.hand_runs,
verbose=verbose)
return paths
def get_eeg_data(subject, runs, event_id):
tmin, tmax = -1.0, 4.0
# Get and prepare the raw data
raw_fnames = eegbci.load_data(subject, runs)
raw = concatenate_raws([read_raw_edf(f, preload=True) for f in raw_fnames])
eegbci.standardize(raw)
montage = make_standard_montage('standard_1005')
raw.set_montage(montage)
raw.rename_channels(lambda x: x.strip('.'))
raw.filter(7.0, 30.0, fir_design='firwin', skip_by_annotation='edge')
events, _ = events_from_annotations(raw, event_id=event_id)
picks = pick_types(raw.info, meg=False, eeg=True, stim=False, eog=False,
exclude='bads')
epochs = Epochs(raw, events, event_id, tmin, tmax, proj=True, picks=picks,
baseline=None, preload=True)
labels = epochs.events[:, -1]
epochs_data = epochs.get_data()
return raw.info['sfreq'], epochs_data, labels
def get_real_eeg_data(start=0, stop=4, chans=4):
"""Get real EEG data for plotting.
Keyword Args:
start (float): start of the EEG segment, in seconds.
stop (float): end of the EEG segment, in seconds.
chans (int or list): number of channels to extract, or list of channel
indices to be interpreted by MNE's get_data() function.
"""
raw_fnames = eegbci.load_data(1, 2)
raws = [read_raw_edf(f, preload=True) for f in raw_fnames]
raw = concatenate_raws(raws)
fs = raw.info['sfreq']
start = int(fs * start)
stop = int(fs * stop)
if not isinstance(chans, list):
chans = np.arange(chans)
data, t = raw.get_data(picks=chans,
start=start,
stop=stop,
return_times=True)
data = data.T
return data, t, fs
def _load_one_run(self, subject, run, preload=True):
if get_config("MNE_DATASETS_EEGBCI_PATH") is None:
set_config("MNE_DATASETS_EEGBCI_PATH",
osp.join(osp.expanduser("~"), "mne_data"))
raw_fname = eegbci.load_data(subject,
runs=[run],
verbose="ERROR",
base_url=BASE_URL)[0]
raw = read_raw_edf(raw_fname, preload=preload, verbose="ERROR")
raw.rename_channels(lambda x: x.strip("."))
raw.rename_channels(lambda x: x.upper())
# fmt: off
renames = {
"AFZ": "AFz",
"PZ": "Pz",
"FPZ": "Fpz",
"FCZ": "FCz",
"FP1": "Fp1",
"CZ": "Cz",
"OZ": "Oz",
"POZ": "POz",
"IZ": "Iz",
"CPZ": "CPz",
"FP2": "Fp2",
"FZ": "Fz",
}
# fmt: on
raw.rename_channels(renames)
raw.set_montage(mne.channels.make_standard_montage("standard_1005"))
return raw
def raw_clean(montage):
"""Return an `mne.io.Raw` object with no bad channels for use with tests.
This fixture downloads and reads in subject 30, run 2 from the Physionet
BCI2000 (eegbci) open dataset, which contains no bad channels on an initial
pass of :class:`pyprep.NoisyChannels`. Intended for use with tests where
channels are made artificially bad.
File attributes:
- Channels: 64 EEG
- Sample rate: 160 Hz
- Duration: 61 seconds
This is only run once per session to save time downloading.
"""
mne.set_log_level("WARNING")
# Download and read S030R02.edf from the BCI2000 dataset
edf_fpath = eegbci.load_data(30, 2, update_path=True)[0]
raw = mne.io.read_raw_edf(edf_fpath, preload=True)
eegbci.standardize(raw) # Fix non-standard channel names
# Set a montage for use with RANSAC
raw.set_montage(montage)
return raw
def _load_one_run(self, subject, run, preload=True):
if get_config('MNE_DATASETS_EEGBCI_PATH') is None:
set_config('MNE_DATASETS_EEGBCI_PATH',
osp.join(osp.expanduser("~"), "mne_data"))
raw_fname = eegbci.load_data(subject,
runs=[run],
verbose='ERROR',
base_url=BASE_URL)[0]
raw = read_raw_edf(raw_fname, preload=preload, verbose='ERROR')
raw.rename_channels(lambda x: x.strip('.'))
raw.rename_channels(lambda x: x.upper())
raw.rename_channels({
'AFZ': 'AFz',
'PZ': 'Pz',
'FPZ': 'Fpz',
'FCZ': 'FCz',
'FP1': 'Fp1',
'CZ': 'Cz',
'OZ': 'Oz',
'POZ': 'POz',
'IZ': 'Iz',
'CPZ': 'CPz',
'FP2': 'Fp2',
'FZ': 'Fz'
})
raw.set_montage(mne.channels.make_standard_montage('standard_1005'))
return raw
def _load_one_run(self, subject, run, preload=True):
raw_fname = eegbci.load_data(subject, runs=[run], verbose='ERROR',
base_url=BASE_URL)[0]
raw = read_raw_edf(raw_fname, preload=preload, verbose='ERROR')
raw.rename_channels(lambda x: x.strip('.'))
raw.set_montage(mne.channels.read_montage('standard_1005'))
return raw
def _load_one_run(self, subject, run, preload=True):
raw_fname = eegbci.load_data(subject,
runs=[run],
verbose="ERROR",
base_url=BASE_URL)[0]
raw = read_raw_edf(raw_fname, preload=preload, verbose="ERROR")
raw.rename_channels(lambda x: x.strip("."))
raw.rename_channels(lambda x: x.upper())
# fmt: off
renames = {
"AFZ": "AFz",
"PZ": "Pz",
"FPZ": "Fpz",
"FCZ": "FCz",
"FP1": "Fp1",
"CZ": "Cz",
"OZ": "Oz",
"POZ": "POz",
"IZ": "Iz",
"CPZ": "CPz",
"FP2": "Fp2",
"FZ": "Fz",
}
# fmt: on
raw.rename_channels(renames)
raw.set_montage(mne.channels.make_standard_montage("standard_1005"))
return raw
def get_data():
tmin, tmax = -1., 4.
event_id = dict(hands=2, feet=3)
subject = 1
runs = [6, 10, 14] # motor imagery: hands vs feet
raw_fnames = eegbci.load_data(subject, runs)
raw = concatenate_raws([read_raw_edf(f, preload=True) for f in raw_fnames])
# strip channel names of "." characters
raw.rename_channels(lambda x: x.strip('.'))
# Apply band-pass filter
raw.filter(7., 30., fir_design='firwin', skip_by_annotation='edge')
events, _ = events_from_annotations(raw)
picks = pick_types(raw.info, meg=False, eeg=True, stim=False, eog=False,
exclude='bads')
# Read epochs (train will be done only between 1 and 2s)
# Testing will be done with a running classifier
epochs = Epochs(raw, events, event_id, tmin, tmax, proj=True, picks=picks,
baseline=None, preload=True)
epochs.crop(tmin=1., tmax=None)
labels = epochs.events[:, 2] - 2
return epochs.get_data()[:, :, :256], labels
def load_data ():
ls_run_tot = [] #list of lists, contains lists of Raw files to be concatenated
# e.g. for subjects = [2, 45]
#ls_run_tot = [[S2Raw03,S2Raw07,S2Raw11],
# [S45Raw03,S45Raw07,S45Raw11]]
for subj in subjects:
ls_run = []#Lista dove inseriamo le run
for run in runs:
fname = eegbci.load_data(subj, runs=run)[0] #Prendo le run
raw_run = read_raw_edf(fname, preload=True) #Le carico
len_run = np.sum((raw_run._annotations).duration) #Controllo la durata
if len_run > 123:
raw_run.crop(tmax=124.4) #Taglio la parte finale
ls_run.append(raw_run)
ls_run_tot.append(ls_run)
return ls_run_tot
def load_eeg_bci(targets=4, tmin=0, tlen=3, t_ev=0, t_sub=None, normalizer=zscore, low_f=None, high_f=None,
alignment=True):
paths = [eegbci.load_data(s+1, IMAGERY_FISTS, path=str(TOPLEVEL_EEGBCI), update_path=False) for s in SUBJECTS_EEGBCI]
raws = [mne.io.concatenate_raws([mne.io.read_raw_edf(p, preload=True) for p in path])
for path in tqdm.tqdm(paths, unit='subj', desc='Loading')]
datasets = OrderedDict()
for i, raw in tqdm.tqdm(list(zip(SUBJECTS_EEGBCI, raws)), desc='Preprocessing'):
if raw.info['sfreq'] != 160:
tqdm.tqdm.write('Skipping..., sampling frequency: {}'.format(raw.info['sfreq']))
continue
raw.rename_channels(lambda x: x.strip('.'))
if low_f or high_f:
raw.filter(low_f, high_f, fir_design='firwin', skip_by_annotation='edge')
events, _ = mne.events_from_annotations(raw, event_id=dict(T1=0, T2=1))
picks = mne.pick_types(raw.info, meg=False, eeg=True, stim=False, eog=False, exclude='bads')
epochs = mne.Epochs(raw, events[:41, ...], tmin=tmin, tmax=tmin + tlen - 1 / raw.info['sfreq'], picks=picks,
baseline=None, reject_by_annotation=False)#.drop_bad()
if targets > 2:
paths = eegbci.load_data(i + 1, BASELINE_EYES_OPEN, path=str(TOPLEVEL_EEGBCI), update_path=False)
raw = mne.io.concatenate_raws([mne.io.read_raw_edf(p, preload=True) for p in paths])
raw.rename_channels(lambda x: x.strip('.'))
if low_f or high_f:
raw.filter(low_f, high_f, fir_design='firwin', skip_by_annotation='edge')
events = np.zeros((events.shape[0] // 2, 3)).astype('int')
events[:, -1] = 2
events[:, 0] = np.linspace(0, raw.info['sfreq'] * (60 - 2 * tlen), num=events.shape[0]).astype(np.int)
picks = mne.pick_types(raw.info, meg=False, eeg=True, stim=False, eog=False, exclude='bads')
eyes_epochs = mne.Epochs(raw, events, tmin=tmin, tmax=tmin + tlen - 1 / raw.info['sfreq'], picks=picks,
baseline=None, reject_by_annotation=False)#.drop_bad()
epochs = mne.concatenate_epochs([eyes_epochs, epochs])
if targets > 3:
paths = eegbci.load_data(i+1, IMAGERY_FEET_V_FISTS, path=str(TOPLEVEL_EEGBCI), update_path=False)
raw = mne.io.concatenate_raws([mne.io.read_raw_edf(p, preload=True) for p in paths])
raw.rename_channels(lambda x: x.strip('.'))
if low_f or high_f:
raw.filter(low_f, high_f, fir_design='firwin', skip_by_annotation='edge')
events, _ = mne.events_from_annotations(raw, event_id=dict(T2=3))
picks = mne.pick_types(raw.info, meg=False, eeg=True, stim=False, eog=False, exclude='bads')
feet_epochs = mne.Epochs(raw, events[:20, ...], tmin=tmin, tmax=tmin + tlen - 1 / raw.info['sfreq'],
picks=picks, baseline=None, reject_by_annotation=False)#.drop_bad()
epochs = mne.concatenate_epochs([epochs, feet_epochs])
datasets[i] = EpochsDataset(epochs, preproccesors=EuclideanAlignment if alignment else [],
normalizer=normalizer, runs=3)
return datasets
def make_filepath(dir_save, subs):
filepaths = []
for i in subs:
load_path = eegbci.load_data(int(i), [4, 6, 8, 10, 12, 14])
filepaths.append(
FilePath(subject='s{}'.format(int(i)),
filetype='edf',
load_path=load_path,
save_path=dir_save))
return filepaths
def _get_single_subject_data(self, subject):
"""return data for a single subject"""
raw_fnames = eegbci.load_data(subject, runs=self.selected_runs)
raw_files = [
read_raw_edf(f, preload=True, verbose=False) for f in raw_fnames
]
# strip channel names of "." characters
[raw.rename_channels(lambda x: x.strip('.')) for raw in raw_files]
return raw_files
def raw():
"""Fixture for physionet EEG subject 4, dataset 1."""
mne.set_log_level("WARNING")
# load in subject 1, run 1 dataset
edf_fpath = eegbci.load_data(4, 1, update_path=True)[0]
# using sample EEG data (https://physionet.org/content/eegmmidb/1.0.0/)
raw = mne.io.read_raw_edf(edf_fpath, preload=True)
# The eegbci data has non-standard channel names. We need to rename them:
eegbci.standardize(raw)
return raw
def data_path(self,
subject,
path=None,
force_update=False,
update_path=None,
verbose=None):
if subject not in self.subject_list:
raise (ValueError("Invalid subject number"))
paths = eegbci.load_data(subject,
runs=[1, 2] + self.hand_runs + self.feet_runs,
base_url=BASE_URL)
return paths
def get_raw(subject, runs=[6, 10, 14]):
raw_fnames = eegbci.load_data(subject, runs)
raw_files = [
read_raw_edf(f, preload=True, stim_channel='auto') for f in raw_fnames
]
raw = concatenate_raws(raw_files)
raw.rename_channels(lambda x: x.strip('.'))
raw.pick_channels(ch_names)
raw.filter(low_freq,
high_freq,
fir_design='firwin',
skip_by_annotation='edge')
return raw
def raw():
"""Fixture for physionet EEG subject 4, dataset 1."""
mne.set_log_level("WARNING")
# load in subject 1, run 1 dataset
edf_fpath = eegbci.load_data(4, 1, update_path=True)[0]
# using sample EEG data (https://physionet.org/content/eegmmidb/1.0.0/)
raw = mne.io.read_raw_edf(edf_fpath, preload=True)
raw.rename_channels(lambda s: s.strip("."))
raw.rename_channels(
lambda s: s.replace("c", "C").replace("o", "O").replace("f", "F").
replace("t", "T").replace("Tp", "TP").replace("Cp", "CP"))
return raw
def get_classification_dataset(subject=1, typeInt=4):
#TypeInt:
#Task 1 (open and close left or right fist)
#Task 2 (imagine opening and closing left or right fist)
#Task 3 (open and close both fists or both feet)
#Task 4 (imagine opening and closing both fists or both feet)
assert (typeInt >= 1)
assert (typeInt <= 4)
from mne.io import concatenate_raws, read_raw_edf
from mne.datasets import eegbci
tmin, tmax = -1., 4.
runs = [3, 7, 11]
runs = [r + typeInt - 1 for r in runs]
print("loading subject {} with runs {}".format(subject, runs))
if typeInt <= 1:
event_id = dict(left=2, right=3)
else:
event_id = dict(hands=2, feet=3)
raw_fnames = eegbci.load_data(subject, runs)
raws = [read_raw_edf(f, preload=True) for f in raw_fnames]
raw = concatenate_raws(raws)
raw.filter(7., 30., fir_design='firwin', skip_by_annotation='edge')
eegbci.standardize(raw) # set channel names
montage = mne.channels.make_standard_montage('standard_1005')
raw.set_montage(montage)
raw.rename_channels(lambda x: x.strip('.'))
events, _ = mne.events_from_annotations(raw, event_id=dict(T1=2, T2=3))
picks = mne.pick_types(raw.info,
meg=False,
eeg=True,
stim=False,
eog=False,
exclude='bads')
# Read epochs (train will be done only between 1 and 2s)
# Testing will be done with a running classifier
epochs = mne.Epochs(raw,
events,
event_id,
tmin,
tmax,
proj=True,
picks=picks,
baseline=None,
preload=True)
return (epochs)
def data_path(self,
subject,
path=None,
force_update=False,
update_path=None,
verbose=None):
if subject not in self.subject_list:
raise (ValueError("Invalid subject number"))
sign = "EEGBCI"
get_dataset_path(sign, None)
paths = eegbci.load_data(subject,
runs=[1, 2] + self.hand_runs + self.feet_runs,
verbose=verbose)
return paths
def load_nme_data(self):
raw_fnames = eegbci.load_data(1, self.RUNS)
raw_files = []
raw_files.extend([
read_raw_edf(f, preload=True, stim_channel='auto')
for f in raw_fnames
])
raw = concatenate_raws(raw_files)
raw.rename_channels(lambda x: x.strip('.'))
self.raw = raw
self.data = raw.get_data()
self.times = self.raw[-1, :][-1] * 1000
def data_path(self,
subject,
path=None,
force_update=False,
update_path=None,
verbose=None):
if subject not in self.subject_list:
raise (ValueError("Invalid subject number"))
if get_config('MNE_DATASETS_EEGBCI_PATH') is None:
set_config('MNE_DATASETS_EEGBCI_PATH',
osp.join(osp.expanduser("~"), "mne_data"))
paths = eegbci.load_data(subject,
runs=[1, 2] + self.hand_runs + self.feet_runs,
verbose=verbose)
return paths
def load_subject(id_num, runs):
'''
Loads raw EEG recordings for one subject and at least one run of
experiments.
Arguments:
id_num: int, the subject's ID number
runs: int or list of ints -- which experiment(s) to read data from
Returns:
MNE Raw object
'''
edf_files = load_data(id_num, runs)
if len(edf_files) > 1:
raw_objects = [read_raw_edf(file, preload=True) for file in edf_files]
mne_raw = concatenate_raws(raw_objects, preload=True)
else:
mne_raw = read_raw_edf(edf_files[0], preload=True)
return mne_raw
def _load_one_run(self, subject, run, preload=True):
if get_config('MNE_DATASETS_EEGBCI_PATH') is None:
set_config('MNE_DATASETS_EEGBCI_PATH',
osp.join(osp.expanduser("~"), "mne_data"))
raw_fname = eegbci.load_data(subject,
runs=[run],
verbose='ERROR',
base_url=BASE_URL)[0]
raw = read_raw_edf(raw_fname, preload=preload, verbose='ERROR')
raw.rename_channels(lambda x: x.strip('.'))
raw.rename_channels(lambda x: x.upper())
raw.rename_channels({
'AFZ': 'AFz',
'PZ': 'Pz',
'FPZ': 'Fpz',
'FCZ': 'FCz',
'FP1': 'Fp1',
'CZ': 'Cz',
'OZ': 'Oz',
'POZ': 'POz',
'IZ': 'Iz',
'CPZ': 'CPz',
'FP2': 'Fp2',
'FZ': 'Fz'
})
raw.set_montage(mne.channels.make_standard_montage('standard_1005'))
# creat simulate stim channel
# mne >= 0.18
events, _ = mne.events_from_annotations(raw)
stim_channel = np.zeros((1, raw.n_times))
for event in events:
stim_channel[0, event[0]] = event[2]
info = mne.create_info(['STI 014'],
raw.info['sfreq'],
ch_types=['stim'])
raw = raw.add_channels([mne.io.RawArray(stim_channel, info)],
force_update_info=True)
return raw
def _load_one_run(self, subject, run, preload=True, verbose=None):
raw_fname = eegbci.load_data(subject, runs=[run], base_url=BASE_URL)[0]
raw = read_raw_edf(raw_fname, preload=preload)
raw.rename_channels(lambda x: x.strip('.'))
montage = make_standard_montage('standard_1005')
# 0.19.2 can not guarante channel name case insensitive
montage.ch_names = [ch_name.upper() for ch_name in montage.ch_names]
raw = upper_ch_names(raw)
raw.set_montage(montage)
# creat simulate stim channel
# mne >= 0.18
events, _ = mne.events_from_annotations(raw)
stim_channel = np.zeros((1, raw.n_times))
for event in events:
stim_channel[0, event[0]] = event[2]
info = mne.create_info(['STI 014'],
raw.info['sfreq'],
ch_types=['stim'])
raw = raw.add_channels([RawArray(stim_channel, info)],
force_update_info=True)
return raw
def raw():
"""Return an `mne.io.Raw` object for use with unit tests.
This fixture downloads and reads in subject 4, run 1 from the Physionet
BCI2000 (eegbci) open dataset. This recording is quite noisy and is thus a
good candidate for testing the PREP pipeline.
File attributes:
- Channels: 64 EEG
- Sample rate: 160 Hz
- Duration: 61 seconds
This is only run once per session to save time downloading.
"""
mne.set_log_level("WARNING")
# Download and read S004R01.edf from the BCI2000 dataset
edf_fpath = eegbci.load_data(4, 1, update_path=True)[0]
raw = mne.io.read_raw_edf(edf_fpath, preload=True)
eegbci.standardize(raw) # Fix non-standard channel names
return raw
from mne import Epochs, pick_types, events_from_annotations
from mne.channels import read_layout
from mne.io import concatenate_raws, read_raw_edf
from mne.datasets import eegbci
from mne.decoding import CSP
from smica import ICA
import pickle
tmin, tmax = -1., 4.
subject = 1
runs = [6, 10, 14] # motor imagery: hands vs feet
raw_fnames = eegbci.load_data(subject, runs)
raw = concatenate_raws([read_raw_edf(f, preload=True) for f in raw_fnames])
# strip channel names of "." characters
raw.rename_channels(lambda x: x.strip('.'))
# Apply band-pass filter
raw.filter(7., 30., fir_design='firwin', skip_by_annotation='edge')
events, _ = events_from_annotations(raw)
picks = pick_types(raw.info,
meg=False,
eeg=True,
stim=False,
eog=False,
from mne.event import find_events
from pyriemann.stats import PermutationTest
from pyriemann.estimation import Covariances
###############################################################################
## Set parameters and read data
# avoid classification of evoked responses by using epochs that start 1s after
# cue onset.
tmin, tmax = 1., 3.
event_id = dict(hands=2, feet=3)
subject = 1
runs = [6, 10, 14] # motor imagery: hands vs feet
raw_files = [read_raw_edf(f, preload=True,verbose=False) for f in eegbci.load_data(subject, runs) ]
raw = concatenate_raws(raw_files)
# strip channel names
raw.info['ch_names'] = [chn.strip('.') for chn in raw.info['ch_names']]
# Apply band-pass filter
raw.filter(7., 35., method='iir')
events = find_events(raw, shortest_event=0, stim_channel='STI 014')
picks = pick_types(raw.info, meg=False, eeg=True, stim=False, eog=False,
exclude='bads')
# Read epochs (train will be done only between 1 and 2s)
# Testing will be done with a running classifier
epochs = Epochs(raw, events, event_id, tmin, tmax, proj=True, picks=picks,
fs_dir = fetch_fsaverage(verbose=True)
subjects_dir = op.dirname(fs_dir)
# The files live in:
subject = 'fsaverage'
trans = op.join(fs_dir, 'bem', 'fsaverage-trans.fif')
src = op.join(fs_dir, 'bem', 'fsaverage-ico-5-src.fif')
bem = op.join(fs_dir, 'bem', 'fsaverage-5120-5120-5120-bem-sol.fif')
##############################################################################
# Load the data
# -------------
#
# We use here EEG data from the BCI dataset.
raw_fname, = eegbci.load_data(subject=1, runs=[6])
raw = mne.io.read_raw_edf(raw_fname, preload=True)
# Clean channel names to be able to use a standard 1005 montage
ch_names = [c.replace('.', '') for c in raw.ch_names]
raw.rename_channels({old: new for old, new in zip(raw.ch_names, ch_names)})
# Read and set the EEG electrode locations
montage = mne.channels.read_montage('standard_1005',
ch_names=raw.ch_names,
transform=True)
raw.set_montage(montage)
raw.set_eeg_reference(projection=True) # needed for inverse modeling
# Check that the locations of EEG electrodes is correct with respect to MRI
fs_dir = fetch_fsaverage(verbose=True)
subjects_dir = op.dirname(fs_dir)
# The files live in:
subject = 'fsaverage'
trans = op.join(fs_dir, 'bem', 'fsaverage-trans.fif')
src = op.join(fs_dir, 'bem', 'fsaverage-ico-5-src.fif')
bem = op.join(fs_dir, 'bem', 'fsaverage-5120-5120-5120-bem-sol.fif')
##############################################################################
# Load the data
# -------------
#
# We use here EEG data from the BCI dataset.
raw_fname, = eegbci.load_data(subject=1, runs=[6])
raw = mne.io.read_raw_edf(raw_fname, preload=True)
# Clean channel names to be able to use a standard 1005 montage
ch_names = [c.replace('.', '') for c in raw.ch_names]
raw.rename_channels({old: new for old, new in zip(raw.ch_names, ch_names)})
# Read and set the EEG electrode locations
montage = mne.channels.read_montage('standard_1005', ch_names=raw.ch_names,
transform=True)
raw.set_montage(montage)
raw.set_eeg_reference(projection=True) # needed for inverse modeling
# Check that the locations of EEG electrodes is correct with respect to MRI
from pyriemann.stats import PermutationTestTwoWay, PermutationTest
from pyriemann.estimation import Covariances
###############################################################################
## Set parameters and read data
# avoid classification of evoked responses by using epochs that start 1s after
# cue onset.
tmin, tmax = -2., 6.
event_id = dict(hands=2, feet=3)
subject = 1
runs = [6, 10, 14] # motor imagery: hands vs feet
raw_files = [
read_raw_edf(f, preload=True, verbose=False)
for f in eegbci.load_data(subject, runs)
]
raw = concatenate_raws(raw_files)
# strip channel names
raw.info['ch_names'] = [chn.strip('.') for chn in raw.info['ch_names']]
events = find_events(raw, shortest_event=0, stim_channel='STI 014')
picks = pick_types(raw.info,
meg=False,
eeg=True,
stim=False,
eog=False,
exclude='bads')
raw.filter(7., 35., method='iir', picks=picks)
from pyriemann.stats import PermutationTest
from pyriemann.estimation import CospCovariances
###############################################################################
# Set parameters and read data
# avoid classification of evoked responses by using epochs that start 1s after
# cue onset.
tmin, tmax = 1., 3.
event_id = dict(hands=2, feet=3)
subject = 1
runs = [6, 10, 14] # motor imagery: hands vs feet
raw_files = [read_raw_edf(f, preload=True, verbose=False)
for f in eegbci.load_data(subject, runs)]
raw = concatenate_raws(raw_files)
events = find_events(raw, shortest_event=0, stim_channel='STI 014')
picks = pick_types(raw.info, meg=False, eeg=True, stim=False, eog=False,
exclude='bads')
# Read epochs (train will be done only between 1 and 2s)
# Testing will be done with a running classifier
epochs = Epochs(raw, events, event_id, tmin, tmax, proj=True, picks=picks,
baseline=None, preload=True, add_eeg_ref=False, verbose=False)
labels = epochs.events[:, -1] - 2
# get epochs
epochs_data = epochs.get_data()
from mne.datasets import eegbci
from mne.decoding import CSP
print(__doc__)
# #############################################################################
# # Set parameters and read data
# avoid classification of evoked responses by using epochs that start 1s after
# cue onset.
tmin, tmax = -1., 4.
event_id = dict(hands=2, feet=3)
subject = 1
runs = [6, 10, 14] # motor imagery: hands vs feet
raw_fnames = eegbci.load_data(subject, runs)
raw_files = [read_raw_edf(f, preload=True) for f in raw_fnames]
raw = concatenate_raws(raw_files)
# strip channel names of "." characters
raw.rename_channels(lambda x: x.strip('.'))
# Apply band-pass filter
raw.filter(7., 30., method='iir')
events = find_events(raw, shortest_event=0, stim_channel='STI 014')
picks = pick_types(raw.info, meg=False, eeg=True, stim=False, eog=False,
exclude='bads')
# Read epochs (train will be done only between 1 and 2s)
