def preprocess_raw_ica_only(sub_id, session):
""" This function removes the ICA component that correlates woth the
EOG channel(s) best.
No filtering or downsampling is applied!
"""
# SETUP AND LOAD FILES ####
# name with subject id & session name
fname = "sub_%d_%s" % (sub_id, session)
# load the raw fif
print '\nLoading raw file'
raw = fiff.Raw(fname + "_tsss_mc.fif", preload=True)
picks = mne.fiff.pick_types(raw.info, meg=True, eeg=False, eog=False,
stim=False, exclude='bads')
# ICA ####
print '\nRun ICA'
ica = ICA(n_components=0.90, n_pca_components=64, max_pca_components=100,
noise_cov=None, random_state=0)
start, stop = None, None
# decompose sources for raw data
ica.decompose_raw(raw, start=start, stop=stop, picks=picks)
corr = lambda x, y: np.array([pearsonr(a, y.ravel()) for a in x])[:, 0]
eog_scores_1 = ica.find_sources_raw(raw, target='EOG001',
score_func=corr)
eog_scores_2 = ica.find_sources_raw(raw, target='EOG002',
score_func=corr)
# get maximum correlation index for EOG
eog_source_idx_1 = np.abs(eog_scores_1).argmax()
eog_source_idx_2 = np.abs(eog_scores_2).argmax()
# We now add the eog artifacts to the ica.exclusion list
if eog_source_idx_1 == eog_source_idx_2:
ica.exclude += [eog_source_idx_1]
elif eog_source_idx_1 != eog_source_idx_2:
ica.exclude += [eog_source_idx_1, eog_source_idx_2]
print eog_source_idx_1, eog_source_idx_2
print ica.exclude
# Restore sensor space data
raw_ica = ica.pick_sources_raw(raw, include=None)
# SAVE FILES ####
raw_ica.save(fname + '_tsss_mc_preproc_ica.fif', overwrite=True)
and target time series
"""
correlation, pval = np.array([pearsonr(a, y) for a in x]).T
return correlation
# As we don't have an ECG channel we use one that correlates a lot with heart
# beats: 'MEG 1531'. To improve detection, we filter the the channel and pass
# it directly to find sources. The method then returns an array of correlation
# scores for each ICA source.
ecg_ch_name = 'MEG 1531'
l_freq, h_freq = 8, 16
ecg = raw[[raw.ch_names.index(ecg_ch_name)], :][0]
ecg = band_pass_filter(ecg, raw.info['sfreq'], l_freq, h_freq)
ecg_scores = ica.find_sources_raw(raw, target=ecg, score_func=score_func)
# get maximum correlation index for ECG
ecg_source_idx = np.abs(ecg_scores).argmax()
title = 'ICA source matching ECG'
ica.plot_sources_raw(raw, ecg_source_idx, title=title, stop=3.0)
# let us have a look which other components resemble the ECG.
# We can do this by reordering the plot by our scores using order
# and generating sort indices for the sources:
ecg_order = np.abs(ecg_scores).argsort()[::-1] # ascending order
ica.plot_sources_raw(raw, ecg_order[:15], start=start_plot, stop=stop_plot)
ica.plot_topomap(ecg_order[:15], colorbar=False)
# This is to illustrate the way ica.find_sources_raw works. Actually, this is # the default score_func. from scipy.stats import pearsonr corr = lambda x, y: np.array([pearsonr(a, y.ravel()) for a in x])[:, 0] # As we don't have an ECG channel we use one that correlates a lot with heart # beats: 'MEG 1531'. To improve detection, we filter the the channel and pass # it directly to find sources. The method then returns an array of correlation # scores for each ICA source. ecg_ch_name = 'MEG 1531' l_freq, h_freq = 8, 16 ecg = raw[[raw.ch_names.index(ecg_ch_name)], :][0] ecg = band_pass_filter(ecg, raw.info['sfreq'], l_freq, h_freq) ecg_scores = ica.find_sources_raw(raw, target=ecg, score_func=corr) # get maximum correlation index for ECG ecg_source_idx = np.abs(ecg_scores).argmax() title = 'ICA source matching ECG' ica.plot_sources_raw(raw, ecg_source_idx, title=title, stop=3.0) # let us have a look which other components resemble the ECG. # We can do this by reordering the plot by our scores using order # and generating sort indices for the sources: ecg_order = np.abs(ecg_scores).argsort()[::-1][:30] # ascending order ica.plot_sources_raw(raw, ecg_order, start=start_plot, stop=stop_plot) # Let's make our ECG component selection more liberal and include sources
# setup reasonable time window for inspection
start_plot, stop_plot = raw.time_as_index([100, 103])
# plot components
ica.plot_sources_raw(raw, start=start_plot, stop=stop_plot)
###############################################################################
# Automatically find the ECG component using correlation with ECG signal
# As we don't have an ECG channel we use one that correlates a lot with heart
# beats: 'MEG 1531'. We can directly pass the name to the find_sources method.
# We select the pearson correlation from scipy stats via string label.
# The function is internally modified to be applicable to 2D arrays and,
# hence, returns product-moment correlation scores for each ICA source.
eog_scores = ica.find_sources_raw(raw, target='EOG 061',
score_func='pearsonr')
# get sources for the entire time range.
sources = ica.get_sources_raw(raw)
# get maximum correlation index for ECG
eog_source_idx = np.abs(eog_scores).argmax()
###############################################################################
# Find ECG event onsets from ICA source
event_id = 999
eog_events = ica_find_eog_events(raw=raw, eog_source=sources[eog_source_idx],
event_id=event_id)
# Read epochs
###############################################################################
# Automatically find the ECG component using correlation with ECG signal
# As we don't have an ECG channel we use one that correlates a lot with heart
# beats: 'MEG 1531'. We can directly pass the name to the find_sources method.
# We select the pearson correlation from scipy stats via string label.
# The function is internally modified to be applicable to 2D arrays and,
# hence, returns product-moment correlation scores for each ICA source.
# pick ECG affected channel
ch_idx = raw.ch_names.index('MEG 1531')
ecg = raw[ch_idx, :][0]
ecg = mne.filter.high_pass_filter(ecg.ravel(), raw.info['sfreq'], 1.0)
ecg_scores = ica.find_sources_raw(raw, target=ecg, score_func='pearsonr')
# get sources for the entire time range.
sources = ica.get_sources_raw(raw)
# get maximum correlation index for ECG
ecg_source_idx = np.abs(ecg_scores).argmax()
# high pass filter source
ecg_source = mne.filter.high_pass_filter(sources[ecg_source_idx],
raw.info['sfreq'], 1.0)
###############################################################################
# Find ECG event onsets from ICA source
event_id = 999
def preprocess_raw(sub_id, session):
""" This function preprocessess data
"""
# SETUP AND LOAD FILES ####
# name with subject id & session name
fname = "sub_%d_%s" % (sub_id, session)
# load the raw fif
print '\nLoading raw file'
raw = fiff.Raw(fname + "_tsss_mc.fif", preload=True)
picks = mne.fiff.pick_types(raw.info, meg=True, eeg=False, eog=False,
stim=False, exclude='bads')
print 'Computing Covariance matrix'
cov = mne.compute_raw_data_covariance(raw, picks=picks, reject=None)
# FILTER ####
# filter raw, lp 128, bp at 50 & 100
raw.filter(None, 128, n_jobs=n_jobs, verbose=True)
# steps = np.arange(50, 151, 50)
# print '\nBand stop filter at %s' % steps
# raw.notch_filter(steps, n_jobs=n_jobs, verbose=True)
# ICA ####
print '\nRun ICA'
ica = ICA(n_components=0.90, n_pca_components=64, max_pca_components=100,
noise_cov=None, random_state=0)
start, stop = None, None
# decompose sources for raw data
ica.decompose_raw(raw, start=start, stop=stop, picks=picks)
corr = lambda x, y: np.array([pearsonr(a, y.ravel()) for a in x])[:, 0]
eog_scores_1 = ica.find_sources_raw(raw, target='EOG001',
score_func=corr)
eog_scores_2 = ica.find_sources_raw(raw, target='EOG002',
score_func=corr)
# get maximum correlation index for EOG
eog_source_idx_1 = np.abs(eog_scores_1).argmax()
eog_source_idx_2 = np.abs(eog_scores_2).argmax()
# We now add the eog artifacts to the ica.exclusion list
if eog_source_idx_1 == eog_source_idx_2:
ica.exclude += [eog_source_idx_1]
elif eog_source_idx_1 != eog_source_idx_2:
ica.exclude += [eog_source_idx_1, eog_source_idx_2]
print eog_source_idx_1, eog_source_idx_2
print ica.exclude
# Restore sensor space data
raw_ica = ica.pick_sources_raw(raw, include=None)
# EPOCHS ####
events = mne.find_events(raw_ica, stim_channel="STI101")
events_classic = []
events_interupt = []
for i in range(len(events)):
if i > 0:
if events[i, 2] == 1 and events[i - 1, 2] == 1:
events_classic.append(i)
elif events[i, 2] == 1 and events[i - 1, 2] == 2:
events_interupt.append(i)
picks = mne.fiff.pick_types(raw_ica.info, meg=True, eeg=False, eog=False,
emg=True, stim=False, exclude='bads')
reject = dict(grad=4000e-13)
epochs = mne.Epochs(raw_ica, events[events_classic], event_id, tmin, tmax,
proj=True, picks=picks, baseline=baseline,
preload=False, reject=reject)
# SAVE FILES ####
raw_ica.save(fname + '_tsss_mc_ica.fif', overwrite=True)
cov.save((fname + '_tsss_mc_cov.fif'))
epochs.save(fname + '_tsss_mc_ica_epochs.fif')
###############################################################################
# Automatically find the ECG component using correlation with ECG signal
# As we don't have an ECG channel we use one that correlates a lot with heart
# beats: 'MEG 1531'. We can directly pass the name to the find_sources method.
# We select the pearson correlation from scipy stats via string label.
# The function is internally modified to be applicable to 2D arrays and,
# hence, returns product-moment correlation scores for each ICA source.
# pick ECG affected channel
ch_idx = raw.ch_names.index('MEG 1531')
ecg = raw[ch_idx, :][0]
ecg = mne.filter.high_pass_filter(ecg.ravel(), raw.info['sfreq'], 1.0)
ecg_scores = ica.find_sources_raw(raw, target=ecg, score_func='pearsonr')
# get sources for the entire time range.
sources = ica.get_sources_raw(raw)
# get maximum correlation index for ECG
ecg_source_idx = np.abs(ecg_scores).argmax()
# high pass filter source
ecg_source = mne.filter.high_pass_filter(sources[ecg_source_idx],
raw.info['sfreq'], 1.0)
###############################################################################
# Find ECG event onsets from ICA source
event_id = 999
# First, we create a helper function that iteratively applies the pearson
# correlation function to sources and returns an array of r values
# This is to illustrate the way ica.find_sources_raw works. Actually, this is
# the default score_func.
from scipy.stats import pearsonr
corr = lambda x, y: np.array([pearsonr(a, y.ravel()) for a in x])[:, 0]
# As we don't have an ECG channel we use one that correlates a lot with heart
# beats: 'MEG 1531'. We can directly pass the name to the find_sources method.
# In our example, the find_sources method returns and array of correlation
# scores for each ICA source.
ecg_scores = ica.find_sources_raw(raw, target='MEG 1531', score_func=corr)
# get sources
sources = ica.get_sources_raw(raw, start=start_plot, stop=stop_plot)
# get times
times = raw.time_as_index(np.arange(stop_plot - start_plot))
# get maximum correlation index for ECG
ecg_source_idx = np.abs(ecg_scores).argmax()
pl.figure()
pl.plot(times, sources[ecg_source_idx])
pl.title('ICA source matching ECG')
pl.show()
