def volstats (invol, groupname, groupsize, outdir=''):
slicesdir = os.path.dirname(invol)
if not outdir:
outdir = slicesdir
base = os.path.basename(au.remove_ext(invol))
outmeanf = outdir + os.path.sep + base + '_' + au.mean_str()
outvarf = outdir + os.path.sep + base + '_' + au.var_str()
outstdf = outdir + os.path.sep + base + '_' + au.std_str()
outsumsf = outdir + os.path.sep + base + '_' + au.sums_str()
vol = nib.load(invol).get_data()
aff = nib.load(invol).get_affine()
if not os.path.exists(outmeanf):
mean = np.mean(vol, axis=3)
au.save_nibabel(outmeanf, mean, aff)
if not os.path.exists(outstdf):
std = np.std(vol, axis=3)
au.save_nibabel(outstdf, std, aff)
if not os.path.exists(outvarf):
var = np.var(vol, axis=3)
au.save_nibabel(outvarf, var, aff)
if not os.path.exists(outsumsf):
sums = np.sum(vol, axis=3)
au.save_nibabel(outsumsf, sums, aff)
return [outsumsf,outmeanf,outvarf,outstdf]
def volstats(invol, groupname, groupsize, outdir=''):
slicesdir = os.path.dirname(invol)
if not outdir:
outdir = slicesdir
base = os.path.basename(au.remove_ext(invol))
outmeanf = outdir + os.path.sep + base + '_' + au.mean_str()
outvarf = outdir + os.path.sep + base + '_' + au.var_str()
outstdf = outdir + os.path.sep + base + '_' + au.std_str()
outsumsf = outdir + os.path.sep + base + '_' + au.sums_str()
vol = nib.load(invol).get_data()
aff = nib.load(invol).get_affine()
if not os.path.exists(outmeanf):
mean = np.mean(vol, axis=3)
au.save_nibabel(outmeanf, mean, aff)
if not os.path.exists(outstdf):
std = np.std(vol, axis=3)
au.save_nibabel(outstdf, std, aff)
if not os.path.exists(outvarf):
var = np.var(vol, axis=3)
au.save_nibabel(outvarf, var, aff)
if not os.path.exists(outsumsf):
sums = np.sum(vol, axis=3)
au.save_nibabel(outsumsf, sums, aff)
return [outsumsf, outmeanf, outvarf, outstdf]
def do_matlab_svm_bdopt (temporal_filtering=True, global_nuis_correction=True):
wd, xd, dd, labelsf, phenof, dataf, masks, dilmasks, templates, pipe = get_filepaths(temporal_filtering, global_nuis_correction)
au.setup_logger(2, logfname=None)
for fi in range(len(dataf)):
myfile = au.remove_ext(subjsf) + '.mat'
#setting command paths
svm_class = 'svm_perf_classify'
svm_learn = 'svm_perf_learn'
if svmdir:
svm_class = svmdir + os.path.sep + svm_class
svm_learn = svmdir + os.path.sep + svm_learn
train_fname = featsf
test_fname = testf
#creating output filename
if expname:
ofname = os.path.basename(expname)
else:
ofname = au.remove_ext(os.path.basename(train_fname))
modelf = outdir + os.path.sep + ofname + '.model.dat'
predsf = outdir + os.path.sep + ofname + '.preds.txt'
logf = outdir + os.path.sep + ofname + '.log.txt'
resf = outdir + os.path.sep + ofname + '.results.txt'
if redoing:
if os.path.exists(resf):
au.log.info('The results already are in ' + resf)
return 0
modelf = au.add_pluses_if_exist(modelf)
predsf = au.add_pluses_if_exist(predsf)
logf = au.add_pluses_if_exist(logf)
def do_darya_localizations ():
import scipy.io as sio
sys.path.append('/home/alexandre/Dropbox/Documents/work/visualize_volume')
import visualize_volume as vis
import aizkolari_utils as au
au.setup_logger()
locd = '/home/alexandre/Dropbox/ELM 2013/ELM-2013-Darya/localization'
wd, xd, dd, labelsf, phenof, dataf, masks, dilmasks, templates, pipe = get_filepaths()
maskf = dilmasks[0]
mask, hdr, aff = au.get_nii_data(maskf)
indices = np.array(np.where(mask > 0))
tmpltf = templates[0]
tmplt, _, _ = au.get_nii_data(tmpltf)
flist = os.listdir(locd)
flist = au.find(flist, '.mat')
flist.sort()
for f in flist:
data = sio.loadmat(os.path.join(locd, f))
name = au.remove_ext(f)
if f.find('cobre') >= 0:
p = data['pearson'].squeeze()
locs = p > 0
lidx = indices[:, locs].squeeze()
if f.find('reho') >= 0:
preho = p.copy()
elif f.find('alff') >= 0:
palff = p.copy()
else:
locs = data[name].squeeze()
locs -= 1
if f.find('pearson') >= 0:
if f.find('reho') >= 0:
lidx = indices[:, preho > 0]
elif f.find('alff') >= 0:
lidx = indices[:, palff > 0]
lidx = lidx[:, locs]
else:
lidx = indices[:, locs].squeeze()
locvol = np.zeros_like(mask, dtype=np.float)
locvol[tuple(lidx)] = 1
#save nifti volume
au.save_nibabel (os.path.join(locd, name + '.nii.gz'), locvol, aff, hdr)
#save image
fig = vis.show_many_slices(tmplt, locvol, volaxis=1, vol2_colormap=plt.cm.autumn, figtitle=name)
aizc.save_fig_to_png(fig, os.path.join(locd, name + '.png'))
if os.access (os.path.join(xd,'innercrop'), os.X_OK):
au.exec_command (os.path.join(xd,'innercrop') + ' -o white ' + fig2name + ' ' + fig2name)
return 0
ilst = args.input.strip().split()
odir = args.outdir.strip()
threshs = args.threshs.strip().split()
maskf = args.mask.strip()
ext = args.ext.strip()
au.setup_logger(args.verbosity)
mask = nib.load(maskf).get_data()
for i in ilst:
im = nib.load(i)
ivol = im.get_data()
ifnom = au.remove_ext(os.path.basename(imf))
if mask.shape != ivol.shape:
au.log.error ("Mask file " + maskf + " and input " + i + " do not have the same shape. Skipping...")
continue
for t in threshs:
au.log.info ("Thresholding " + i + " with " + str(t) + " robust lower bound.")
out = au.threshold_robust_range (ivol, t)
if odir:
of = odir
else:
of = os.path.dirname(i)
of += os.path.sep + ifnom + "_" + str(t) + "thrP" + ext
#setting command paths
svm_class = 'svm_perf_classify'
svm_learn = 'svm_perf_learn'
if svmdir:
svm_class = svmdir + os.path.sep + svm_class
svm_learn = svmdir + os.path.sep + svm_learn
train_fname = featsf
test_fname = testf
#creating output filename
if expname:
ofname = os.path.basename(expname)
else:
ofname = au.remove_ext(os.path.basename(train_fname))
modelf = outdir + os.path.sep + ofname + '.model.dat'
predsf = outdir + os.path.sep + ofname + '.preds.txt'
logf = outdir + os.path.sep + ofname + '.log.txt'
resf = outdir + os.path.sep + ofname + '.results.txt'
if redoing:
if os.path.exists(resf):
au.log.info('The results already are in ' + resf)
return 0
modelf = au.add_pluses_if_exist (modelf)
predsf = au.add_pluses_if_exist (predsf)
logf = au.add_pluses_if_exist (logf)
def slice_and_merge (subsfname, labelsfname, checkfname, outdir='', maskfname='', outbase=''):
check_data (subsfname, labelsfname, outdir, maskfname, outbase)
nsubs = au.file_len(subsfname)
nlabs = au.file_len(labelsfname)
if not outdir:
outdir = os.getcwd()
slicesdir = outdir + os.path.sep + au.slices_str()
tempdir = outdir + os.path.sep + au.temp_str()
tmpdirlst = os.listdir(tempdir)
fpath = ''
olddir = os.getcwd()
if not au.is_done (checkfname, au.preslicingdata_str()):
#slicing subjects
au.log.info ('Slicing all subjects: takes a while')
subsfile = open(subsfname, 'r')
for line in subsfile:
fpath = line.strip()
isfile = os.path.basename(fpath)
osfile = tempdir + os.path.sep + isfile
#test if file has been sliced
fdim3 = au.fslval(fpath, 'dim3')
regex = au.remove_ext(isfile) + '*'
nslices = au.count_match (tmpdirlst, regex)
if fdim3 != nslices:
#if not, then slice it in tempdir
au.log.debug('Slicing ' + isfile)
os.chdir (tempdir)
shutil.copy (fpath, tempdir)
au.fslslice (osfile)
os.remove(osfile)
os.chdir (olddir)
else:
au.log.debug(isfile + ' previously sliced')
subsfile.close()
au.checklist_add (checkfname, au.preslicingdata_str())
if not au.is_done (checkfname, au.premergingdata_str()):
#merging each slice
if not outbase:
outbase = au.data_str()
if not fpath:
subsfile = open(subsfname, 'r')
for line in subsfile:
fpath = line.strip()
break
au.log.info ('Merging all subject slices: takes a while')
nslices = int(au.fslval(fpath,'dim3'))
for slice in range(nslices):
slicezp = au.zeropad(slice)
mergeout = outbase + '_slice_' + slicezp
outdata = slicesdir + os.path.sep + mergeout
#check if data file exists
if not au.imtest(outdata):
#if not, then create it, merging all the corresponding slices
au.log.debug('Merging slice ' + slicezp)
imglob = ''
subsfile = open(subsfname, 'r')
for line in subsfile:
fpath = line.strip()
isfile = au.remove_ext(os.path.basename(fpath)).strip()
isfile = tempdir + os.path.sep + isfile + '_slice_' + slicezp
imglob += isfile + ' '
os.system('fslmerge -t ' + outdata + ' ' + imglob)
for f in imglob.split():
au.imrm(f)
else:
au.log.debug('Slice ' + slicezp + ' previously done')
au.checklist_add (checkfname, au.premergingdata_str())
#slicing mask
if maskfname:
if os.path.exists(maskfname) and not au.is_done (checkfname, au.preslicingmask_str()):
au.log.info('Slicing mask ' + maskfname)
au.imcp (maskfname, slicesdir + os.path.sep + au.mask_str())
os.chdir (slicesdir)
au.fslslice (au.mask_str())
au.imrm (au.mask_str())
au.checklist_add (checkfname, au.preslicingmask_str())
os.chdir (olddir)
au.log.debug('Done preprocessing')
