def load_data(filename):
ds = mv.gifti_dataset(filename)
ds.sa.pop('intents')
ds.sa['subjects'] = [participant] * ds.shape[0]
ds.fa['node_indices'] = range(n_vertices)
# z-score features across samples
mv.zscore(ds, chunks_attr=None)
return ds
def get_ha_common_data(test_p, mappers, fold_shifted, included, hemi):
train_p = [x for x in participants if x != test_p]
print(
'\nLoading fMRI GIFTI data for HA in test subj space and using {0} as test participant...'.format(test_p))
train_resp = []
for run in included:
avg = []
for participant in train_p:
if run == 4:
resp = mv.gifti_dataset(os.path.join(sam_data_dir, '{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'.format(
participant, tr_fmri[run], run, hemi))).samples[4:-5, :]
else:
resp = mv.gifti_dataset(os.path.join(sam_data_dir, '{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'.format(
participant, tr_fmri[run], run, hemi))).samples[4:-4, :]
mv.zscore(resp, chunks_attr=None)
resp = mappers[participant].forward(resp)
resp = resp[:, cortical_vertices[hemi] == 1]
mv.zscore(resp, chunks_attr=None)
avg.append(resp)
avg = np.mean(avg, axis=0)
mv.zscore(avg, chunks_attr=None)
print('train', run, avg.shape)
train_resp.append(avg)
if fold_shifted == 4:
test_resp = mv.gifti_dataset(os.path.join(sam_data_dir, '{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'.format(
test_p, tr_fmri[fold_shifted], fold_shifted, hemi))).samples[4:-5, :]
else:
test_resp = mv.gifti_dataset(os.path.join(sam_data_dir, '{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'.format(
test_p, tr_fmri[fold_shifted], fold_shifted, hemi))).samples[4:-4, :]
mv.zscore(test_resp, chunks_attr=None)
test_resp = mappers[participant].forward(test_resp)
test_resp = test_resp[:, cortical_vertices[hemi] == 1]
mv.zscore(test_resp, chunks_attr=None)
print('test', fold_shifted, test_resp.shape)
return train_resp, test_resp
def create_dataset(sub_name, main_dir, task_list, hemi):
data_set = []
for task_name in task_list:
for run_num in range(1,6):
ds=[]
gifti_fname = os.path.join(main_dir,'analysis', sub_name,'func', sub_name + '_task-' + task_name + '_run-' + str(run_num) +'_rw-glm.' +hemi+'.coefs.gii')
ds = mv.gifti_dataset(gifti_fname)
# order in sub-rid000001_task-beh_run-5_rw-glm.lh.X.xmat.1D
ds.sa['beh_tax'] = ["bird_eating", "bird_fighting", "bird_running", "bird_swimming",
"insect_eating", "insect_fighting", "insect_running", "insect_swimming",
"primate_eating","primate_fighting","primate_running","primate_swimming",
"reptile_eating","reptile_fighting", "reptile_running", "reptile_swimming",
"ungulate_eating","ungulate_fighting","ungulate_running","ungulate_swimming"]
ds.sa['beh'] = np.tile(['eating','fighting','running','swimming'],5)
ds.sa['tax'] = np.repeat(['bird','insect','primate', 'reptile', 'ungulate'],4)
ds.fa['node_indices'] = range(0,ds.shape[1]) # 0 ~ 400000
data_set.append(ds)
# http://www.pymvpa.org/tutorial_mappers.html
within_ds = mv.vstack(data_set)
return within_ds
def get_ha_testsubj_data(test_p, mappers, fold_shifted, included, hemi):
train_p = [x for x in participants if x != test_p]
print("\n4. hyperalignment test subject data")
print(
'Loading fMRI GIFTI data for HA in test subj space and using {0} as test participant...'
.format(test_p))
train_resp = []
for run in included:
avg = []
for participant in train_p:
# _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
# UNCOMMENT LATER -
# if run == 4:
# resp = mv.gifti_dataset(os.path.join(sam_data_dir, '{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'.format(
# participant, tr_fmri[run], run, hemi))).samples[4:-5, :]
# else:
# resp = mv.gifti_dataset(os.path.join(sam_data_dir, '{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'.format(
# participant, tr_fmri[run], run, hemi))).samples[4:-4, :]
# # _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
# DELETE LATER -
if run == 4:
resp = mv.gifti_dataset(
os.path.join(
sam_data_dir,
'{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'.
format(participant, tr_fmri[run], run,
hemi))).samples[4:-5, :]
else:
resp = mv.gifti_dataset(
os.path.join(
sam_data_dir,
'{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'.
format(participant, tr_fmri[run], run,
hemi))).samples[4:-4, :]
# _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
mv.zscore(resp, chunks_attr=None)
resp = mappers[participant].forward(resp)
mv.zscore(resp, chunks_attr=None)
resp = mappers[test_p].reverse(resp)
# _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
# DELETE LATER -
# resp = resp[:, cortical_vertices[hemi] == 1]
resp = resp[:, selected_node]
# _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
mv.zscore(resp, chunks_attr=None)
avg.append(resp)
avg = np.mean(avg, axis=0)
mv.zscore(avg, chunks_attr=None)
print('train', run, avg.shape)
train_resp.append(avg)
# if fold_shifted == 4:
# test_resp = mv.gifti_dataset(os.path.join(sam_data_dir, '{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'.format(
# test_p, tr_fmri[fold_shifted], fold_shifted, hemi))).samples[4:-5, cortical_vertices[hemi] == 1]
# else:
# test_resp = mv.gifti_dataset(os.path.join(sam_data_dir, '{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'.format(
# test_p, tr_fmri[fold_shifted], fold_shifted, hemi))).samples[4:-4, cortical_vertices[hemi] == 1]
if fold_shifted == 4:
test_resp = mv.gifti_dataset(
os.path.join(
sam_data_dir,
'{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'.format(
test_p, tr_fmri[fold_shifted], fold_shifted,
hemi))).samples[4:-5, selected_node]
else:
test_resp = mv.gifti_dataset(
os.path.join(
sam_data_dir,
'{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'.format(
test_p, tr_fmri[fold_shifted], fold_shifted,
hemi))).samples[4:-4, selected_node]
mv.zscore(test_resp, chunks_attr=None)
print('test', fold_shifted, test_resp.shape)
return train_resp, test_resp
prefix = data_path + 'sub-rid' + sub
suffix = hemi + '.coefs.gii'
fn = prefix + '*' + suffix
files = sorted(glob.glob(fn))
# labels for our gifti_dataset
taxonomy = np.repeat(['bird', 'insect', 'primate', 'reptile', 'unduate'], 4)
behavior = np.tile(['eating', 'fighting', 'running', 'swimming'], 5)
conditions = [' '.join((beh, tax)) for beh, tax in zip(behavior, taxonomy)]
# load in all of the data into the dataframe
targets = range(1, 21)
ds = None
for x in range(len(files)):
chunks = [x + 1] * 20
d = mv.gifti_dataset(files[x], chunks=chunks, targets=targets)
d.sa['conditions'] = conditions
d.sa['taxonomy'] = taxonomy
d.sa['behavior'] = behavior
if ds is None:
ds = d
else:
ds = mv.vstack((ds, d))
ds.fa['node_indices'] = range(ds.shape[1])
# zscore all of our samples
mv.zscore(ds, chunks_attr='chunks', dtype='float32')
# load in surgace and get searchlight query
radius = 10
surface = mv.surf.read(join(data_path, '{0}.pial.gii'.format(hemi)))
# this is an arbitrary radius and distance metric!
query = mv.SurfaceQueryEngine(surface, radius, distance_metric='dijkstra')
print('made our sls')
all_slres = []
for sub in subjs:
# get all our data files for this subj
ds = None
prefix = data_path + 'sub-rid' + sub
suffix = hemi + '.coefs.gii'
fn = prefix + '*' + suffix
files = sorted(glob.glob(fn))
for x in range(len(files)):
if x < 5:
chunks = [x + 1] * 20
else:
chunks = [x - 5 + 1] * 20
d = mv.gifti_dataset(files[x], chunks=chunks, targets=conditions)
d.sa['conditions'] = conditions
if ds is None:
ds = d
else:
ds = mv.vstack((ds, d))
ds.fa['node_indices'] = range(ds.shape[1])
ds.samples = zscore(ds.samples, axis=1)
mtgs = mean_group_sample(['conditions'])
mtds = mtgs(ds)
slres = sl(mtds)
slres.samples = np.nan_to_num(slres.samples)
all_slres.append(slres.samples)
# all_slres has all (190, 40962) RDMs for each subject
# now we need ISCs
qe = mv.SurfaceQueryEngine(surf, 20.0, distance_metric='dijkstra')
print("Finished creating surface-based searchlight query engine")
# Optional load hyperalignment mappers
if hyperalign:
mappers1 = mv.h5load(join(mvpa_dir, 'search_hyper_mappers_life_mask_nofsel_{0}_leftout_1.hdf5'.format(hemi)))
mappers2 = mv.h5load(join(mvpa_dir, 'search_hyper_mappers_life_mask_nofsel_{0}_leftout_2.hdf5'.format(hemi)))
mappers3 = mv.h5load(join(mvpa_dir, 'search_hyper_mappers_life_mask_nofsel_{0}_leftout_3.hdf5'.format(hemi)))
mappers4 = mv.h5load(join(mvpa_dir, 'search_hyper_mappers_life_mask_nofsel_{0}_leftout_4.hdf5'.format(hemi)))
mappers = [mappers1, mappers2, mappers3, mappers4]
print("Loaded hyperalignment mappers")
for participant in participants:
# Load in functional data
ds1 = mv.gifti_dataset(join(sam_data_dir, '{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'.format(participant, tr[1], 1, hemi)))
ds2 = mv.gifti_dataset(join(sam_data_dir, '{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'.format(participant, tr[2], 2, hemi)))
ds3 = mv.gifti_dataset(join(sam_data_dir, '{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'.format(participant, tr[3], 3, hemi)))
ds4 = mv.gifti_dataset(join(sam_data_dir, '{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'.format(participant, tr[4], 4, hemi)))
# Exclude medial wall
medial_wall = np.where(np.sum(ds1.samples == 0, axis=0) == tr[1])[0].tolist()
cortical_vertices = np.where(np.sum(ds1.samples == 0, axis=0) < tr[1])[0].tolist()
assert len(medial_wall) == n_medial[hemi]
assert len(medial_wall) + len(cortical_vertices) == n_vertices
for i, ds in enumerate([ds1, ds2, ds3, ds4]):
print(i)
ds.samples = ds.samples[]
if i < 2:
ses = 0
join(
mvpa_dir,
'search_hyper_mappers_life_mask_nofsel_{0}_leftout_{1}.hdf5'
.format(hemi, run)))
for participant in participants:
# print(ds.sa['intents'])
# to_avg = mean_group_feature()
# averaged_response = to_avg(ds)
print(
"loading data for run {0}, hemisphere {1}, participant {2}...".
format(run, hemi, participant))
ds = mv.gifti_dataset(
join(
sam_data_dir,
'{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'.
format(participant, tr[run], run, hemi)))
mv.zscore(ds, chunks_attr=None)
if hyperalign:
ds = mappers[participant].forward(ds)
mv.zscore(ds, chunks_attr=None)
ds.fa['node_indices'] = range(ds.shape[1])
# n_samples = ds.samples.shape[0]
#
# # Exclude medial wall
# print(np.where(np.sum(ds.samples == 0, axis=0) == n_samples))
n_samples = ds.samples.shape[0]
medial_wall = np.where(
data_dir,
'{0}-leftout{1}_singlealpha/{2}/{3}/weights.npy'.format(
t, run, p, h)))
# put medial wall back in
med_wall_ind = np.where(cortical_vertices[h] == 0)[0]
wt = np.zeros((wt_missing_medial.shape[0],
wt_missing_medial.shape[1] + med_wall_ind.shape[0]),
dtype=wt_missing_medial.dtype)
wt[:, cortical_vertices[h] == 1] = wt_missing_medial
Pstim = get_stim_for_test_fold(run)
if run == 4:
Presp = mv.gifti_dataset(
os.path.join(
sam_data_dir,
'{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'.
format(p, tr[run], run, h))).samples[4:-14, :]
else:
Presp = mv.gifti_dataset(
os.path.join(
sam_data_dir,
'{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'.
format(p, tr[run], run, h))).samples[4:-7, :]
mv.zscore(Presp, chunks_attr=None)
forward_resp = mappers[p].forward(Presp)
mv.zscore(forward_resp, chunks_attr=None)
print("Loaded stim and resp data. Doing prediction...")
pred = np.dot(Pstim, wt)
for hemi in hemispheres:
runlist = []
for run in runs:
avg_stack = np.empty((4, 40962))
triu_corrs = []
plist = []
for participant in participants:
# filenames = []
# filenames = glob.glob(os.path.join(result_dir, align, 'visual', 'bg_actions_agents', 'leftout_run_' + str(run), '*', h,
# 'kernel-weights_' + '*' + '_model-visual_align-' + align + '_feature-' + model + '_foldshifted-' + str(run) + '_hemi_' + h + '.npy'))
if align == 'aa':
if run == 4:
resp = mv.gifti_dataset(
os.path.join(
sam_data_dir,
'{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'
.format(participant, tr_fmri[run], run,
hemi))).samples[4:-5, :]
else:
resp = mv.gifti_dataset(
os.path.join(
sam_data_dir,
'{0}_task-life_acq-{1}vol_run-0{2}.{3}.tproject.gii'
.format(participant, tr_fmri[run], run,
hemi))).samples[4:-4, :]
resp = resp[:, cortical_vertices[hemi] == 1]
mv.zscore(resp, chunks_attr=None)
plist.append(resp)
# np.shape(plist) (18, 403, 37471)
