epochs = Epochs(raw_filter, events, event_id, tmin - w_size, tmax + w_size,
proj=False, baseline=None, preload=True)
epochs.drop_bad()
y = le.fit_transform(epochs.events[:, 2])
# Roll covariance, csp and lda over time
for t, w_time in enumerate(centered_w_times):
# Center the min and max of the window
w_tmin = w_time - w_size / 2.
w_tmax = w_time + w_size / 2.
# Crop data into time-window of interest
X = epochs.copy().crop(w_tmin, w_tmax).get_data()
# Save mean scores over folds for each frequency and time window
tf_scores[freq, t] = np.mean(cross_val_score(estimator=clf, X=X, y=y,
scoring='roc_auc', cv=cv,
n_jobs=1), axis=0)
###############################################################################
# Plot time-frequency results
# Set up time frequency object
av_tfr = AverageTFR(create_info(['freq'], sfreq), tf_scores[np.newaxis, :],
centered_w_times, freqs[1:], 1)
chance = np.mean(y) # set chance level to white in the plot
av_tfr.plot([0], vmin=chance, title="Time-Frequency Decoding Scores",
cmap=plt.cm.Reds)
# Roll covariance, csp and lda over time
for t, w_time in enumerate(centered_w_times):
# Center the min and max of the window
w_tmin = w_time - w_size / 2.
w_tmax = w_time + w_size / 2.
# Crop data into time-window of interest
X = epochs.copy().crop(w_tmin, w_tmax).get_data()
# Save mean scores over folds for each frequency and time window
scores[freq, t] = np.mean(cross_val_score(estimator=clf,
X=X,
y=y,
cv=cv,
n_jobs=1),
axis=0)
###############################################################################
# Plot results
# Set up time frequency object
av_tfr = AverageTFR(create_info(['freq'], sfreq), scores[np.newaxis, :],
centered_w_times, freqs[1:], 1)
chance = np.mean(y) # set chance level to white in the plot
av_tfr.plot([0],
vmin=chance,
title="Time-Frequency Decoding Scores",
cmap=plt.cm.Reds)
c.info['subject_info'] = 'P14'
c.info['cond'] = conds[ix_c]
calc_wpli_over_time(c)
dats = list()
for c in conds:
dat = np.load(
op.join(study_path, 'results', 'wpli', 'P14_{}_wpli.npz'.format(c)))
dats.append(dat)
info = dat['info'].item()
for ix_c, c in enumerate(conds):
tfr = AverageTFR(info, dats[ix_c]['con'][1, :, :, :], dat['times'],
dat['freqs'], 1)
tfr.plot(picks=[83], vmin=-1, vmax=1, cmap='viridis', title=c)
# TF ROI
if ref == 'avg':
rois = {
'HP_r': np.array(raw.ch_names)[picks[:4]],
'HP_l': np.array(raw.ch_names)[picks[4:]]
} # :4
elif ref == 'bip':
rois = {
'HP_l': np.array(raw.ch_names)[picks[:2]],
'HP_r': np.array(raw.ch_names)[picks[2:]]
}
roi_fig, axes = plt.subplots(len(rois), len(conds), sharey=True, sharex=True)
roi_pows = {'HP_l': list(), 'HP_r': list()}