def test_ICA(epochs):
"""
Test ICA fit, ICA choice comp and ICA apply
"""
ep = [epochs.epo1, epochs.epo2]
icas = prep.ICA_fit(ep, n_components=15, method='fastica', random_state=97)
# check that the number of componenents is similar between the two subjects
for i in range(0, len(icas) - 1):
mne.preprocessing.ICA.get_components(
icas[i]).shape == mne.preprocessing.ICA.get_components(
icas[i + 1]).shape
def test_ICA(epochs):
"""
Test ICA fit, ICA choice comp and ICA apply
"""
ep = [epochs.epo1, epochs.epo2]
icas = prep.ICA_fit(ep,
n_components=15,
method='infomax',
fit_params=dict(extended=True),
random_state=97)
# check that the number of componenents is similar between the two participants
for i in range(0, len(icas) - 1):
mne.preprocessing.ICA.get_components(
icas[i]).shape == mne.preprocessing.ICA.get_components(
icas[i + 1]).shape
# dedicate to hyperscanning, we need to equalize
# the number of epochs between our two participants
mne.epochs.equalize_epoch_counts([epo1, epo2])
# Preprocessing epochs
# Warning: here we directly load epochs data,
# for raw data we highly recommend to perform high-pass filtering
# with prep.filt function before converting raw to epochs
# Computing global AutoReject and Independant Components Analysis
# for each participant
icas = prep.ICA_fit(
[epo1, epo2],
n_components=15,
method="infomax",
fit_params=dict(extended=True),
random_state=42,
)
# Selecting relevant Independant Components for artefact rejection
# on one participant, that will be transpose to the other participant
# and fitting the ICA
cleaned_epochs_ICA = prep.ICA_choice_comp(icas, [epo1, epo2])
plt.close("all")
# Applying local AutoReject for each participant
# rejecting bad epochs, rejecting or interpolating partially bad channels
# removing the same bad channels and epochs across participants
# plotting signal before and after (verbose=True)
cleaned_epochs_AR, dic_AR = prep.AR_local(cleaned_epochs_ICA,