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)
# variance explained by the PCA components.
ica = ICA(n_components=0.90,
n_pca_components=None,
max_pca_components=None,
random_state=0)
# Also we decide to use all PCA components before mixing back to sensor space.
# You can again use percentages (float) or set the total number of components
# to be kept directly (int) which allows to control the amount of additional
# denoising.
ica.n_pca_components = 1.0
# decompose sources for raw data using each third sample.
ica.decompose_raw(raw, picks=picks, decim=3)
print(ica)
# plot reasonable time window for inspection
start_plot, stop_plot = 100., 103.
ica.plot_sources_raw(raw, range(30), start=start_plot, stop=stop_plot)
###############################################################################
# Automatically find the ECG component using correlation with ECG signal.
# Defining a customized distance function.
# You can pass any function object that
# takes a n_sources X n_samples vector and, optionally, a second
# n_samples vector, and returns a score vector of length n_sources.
# Let's illustrate this by creating a function that, when passed as
# Instead of the actual number of components here we pass a float value
# between 0 and 1 to select n_components by a percentage of
# explained variance. Also we decide to use 64 PCA components before mixing
# back to sensor space. These include the PCA components supplied to ICA plus
# additional PCA components up to rank 64 of the MEG data.
# This allows to control the trade-off between denoising and preserving signal.
ica = ICA(n_components=0.90, n_pca_components=None, max_pca_components=100,
random_state=0)
# 1 minute exposure should be sufficient for artifact detection.
# However, rejection performance may significantly improve when using
# the entire data range
# decompose sources for raw data using each third sample.
ica.decompose_raw(raw, picks=picks, decim=3)
print ica
# plot reasonable time window for inspection
start_plot, stop_plot = 100., 103.
ica.plot_sources_raw(raw, range(30), start=start_plot, stop=stop_plot)
###############################################################################
# Automatically find the ECG component using correlation with ECG signal.
# 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
# Setup ICA seed decompose data, then access and plot sources.
# Sign and order of components is non deterministic.
# setting the random state to 0 makes the solution reproducible.
# Instead of the actual number of components we pass a float value
# between 0 and 1 to select n_components by a percentage of
# explained variance.
ica = ICA(n_components=0.90, max_pca_components=100, noise_cov=None,
random_state=0)
# For maximum rejection performance we will compute the decomposition on
# the entire time range
# decompose sources for raw data, select n_components by explained variance
ica.decompose_raw(raw, start=None, stop=None, picks=picks)
print ica
sources = ica.get_sources_raw(raw)
# 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.
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')
# explained variance. Also we decide to use 64 PCA components before mixing
# back to sensor space. These include the PCA components supplied to ICA plus
# additional PCA components up to rank 64 of the MEG data.
# This allows to control the trade-off between denoising and preserving signal.
ica = ICA(n_components=0.90, n_pca_components=64, max_pca_components=100,
noise_cov=None, random_state=0)
print ica
# 1 minute exposure should be sufficient for artifact detection.
# However, rejection performance may significantly improve when using
# the entire data range
start, stop = raw.time_as_index([100, 160])
# decompose sources for raw data
ica.decompose_raw(raw, start=start, stop=stop, picks=picks)
print ica
sources = ica.get_sources_raw(raw, start=start, stop=stop)
# 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.
# First, we create a helper function that iteratively applies the pearson
# correlation function to sources and returns an array of r values
# This allows to control the trade-off between denoising and preserving signal.
ica = ICA(n_components=0.90,
n_pca_components=64,
max_pca_components=100,
noise_cov=None,
random_state=0)
print ica
# 1 minute exposure should be sufficient for artifact detection.
# However, rejection performance may significantly improve when using
# the entire data range
start, stop = raw.time_as_index([100, 160])
# decompose sources for raw data
ica.decompose_raw(raw, start=start, stop=stop, picks=picks)
print ica
sources = ica.get_sources_raw(raw, start=start, stop=stop)
# 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.
# First, we create a helper function that iteratively applies the pearson
# correlation function to sources and returns an array of r values