fold_shifted, included,
hemi)
elif align == 'ha_testsubj':
train_resp, test_resp = get_ha_testsubj_data(
test_p, mappers, fold_shifted, included, hemi)
alphas = np.logspace(0, 3, 20)
nboots = len(included)
chunklen = 15
nchunks = 15
wt, corrs, alphas, bootstrap_corrs, valinds = hyper_ridge.bootstrap_ridge(
train_stim,
train_resp,
test_stim,
test_resp,
alphas,
nboots,
single_alpha=True,
nuisance_regressor=True)
print('\nFinished training ridge regression')
print('\n\nwt: {0}'.format(wt))
print('\n\n corrs: {0}'.format(corrs))
print('\n\nalphas: {0}'.format(alphas))
print('\n\nbootstrap_corrs: {0}'.format(bootstrap_corrs))
print('\n\nvalinds: {0}'.format(valinds))
print('\n\nWriting to file...')
directory = os.path.join(
'/dartfs/rc/lab/D/DBIC/DBIC/f0042x1/life-encoding/results/ridge-models',
load_data(
os.path.join(
sam_data_dir,
'{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'.
format(test_p, tr[3], 3, hemi))).samples[4:-7, :])
mv.zscore(test_resp, chunks_attr=None)
print(test_resp.shape)
run = 2
balphas = np.logspace(-3, 3, 100)
nboots = 15
chunklen = 15
nchunks = 25
# print('\n\nRidge regression with alphas: {0}, nboots: {1}\n'.format(balphas, nboots))
wt, corrs, alphas, bootstrap_corrs, valinds = hyper_ridge.bootstrap_ridge(
train_stim, train_resp, test_stim, test_resp, balphas, nboots,
chunklen, nchunks)
# rr_model = Ridge(alpha=1.0)
# rr_model.fit(w2v, fmri[:,i])
print('\nFinished training ridge regression')
print('\n\nwt: {0}'.format(wt))
print('\n\ncorrs: {0}'.format(corrs))
print('\n\nalphas: {0}'.format(alphas))
# print('\n\nbootstrap_corrs: {0}'.format(bootstrap_corrs))
# print('\n\nvalinds: {0}'.format(valinds))
print('\n\nWriting to file...')
directory = os.path.join(ridge_dir,
'avg-{}-slh-CV'.format(stimfile[:-4]),
test_p, hemi)