step_params = ' ' + measure_fname + ' ' + mdir
absolute_str = ''
if absval:
absolute_str = ' ' + au.abs_str()
step_params += absolute_str
leave_str = ''
if leave > -1:
leave_str = ' excluding subject ' + str(leave)
step_params += leave_str
#checking if this measure has already been done
endstep = au.measure_str() + step_params
stepdone = au.is_done(chkf, endstep)
#add pluses to output dir if it already exists
if stepdone:
while os.path.exists(mdir):
mdir += '+'
else: #work in the last folder used
plus = False
while os.path.exists(mdir):
mdir += '+'
plus = True
if plus:
mdir = mdir[0:-1]
#setting statsdir
pluses = mdir.count('+')
for i in np.arange(pluses):
step_params = ' ' + measure_fname + ' ' + mdir
absolute_str = ''
if absval:
absolute_str = ' ' + au.abs_str()
step_params += absolute_str
leave_str = ''
if leave > -1:
leave_str = ' excluding subject ' + str(leave)
step_params += leave_str
#checking if this measure has already been done
endstep = au.measure_str() + step_params
stepdone = au.is_done(chkf, endstep)
#add pluses to output dir if it already exists
if stepdone:
while os.path.exists (mdir):
mdir += '+'
else: #work in the last folder used
plus = False
while os.path.exists (mdir):
mdir += '+'
plus = True
if plus:
mdir = mdir[0:-1]
#setting statsdir
pluses = mdir.count('+')
for i in np.arange(pluses): statsdir += '+'
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')
def group_distance (measure_function, datadir, groups, groupsizes, chkf, absolute=False, outdir='', foldno='', expname='', exclude_idx=-1, exclude_subj='', exclude_subjclass=''):
olddir = os.getcwd()
if not outdir:
outdir = datadir
ngroups = len(groups)
#matrix of strings of 2000 characters maximum, to save filepaths
gfnames = np.zeros ([ngroups,3], dtype=np.dtype('a2000'))
subject_excluded = False
for g1 in range(ngroups):
g1name = groups[g1]
#mean1fname
gfnames[g1,0] = datadir + os.path.sep + g1name + '_' + au.mean_str()
#var1fname
gfnames[g1,1] = datadir + os.path.sep + g1name + '_' + au.var_str()
#std1fname
gfnames[g1,2] = datadir + os.path.sep + g1name + '_' + au.std_str()
for g2 in range(g1+1, ngroups):
g2name = groups[g2]
gfnames[g2,0] = datadir + os.path.sep + g2name + '_' + au.mean_str()
gfnames[g2,1] = datadir + os.path.sep + g2name + '_' + au.var_str()
gfnames[g2,2] = datadir + os.path.sep + g2name + '_' + au.std_str()
experiment = g1name + '_vs_' + g2name
#check if exclude_subjclass is any of both current groups
eg = -1
if exclude_idx > -1:
if exclude_subjclass == g1name: eg = g2
elif exclude_subjclass == g2name: eg = g1
step = au.measure_str() + ' ' + measure_function.func_name + ' ' + experiment + ' ' + datadir
#remove subject from stats
if eg > -1:
exclude_str = '_' + au.excluded_str() + str(exclude_idx)
step += exclude_str
experiment += exclude_str
if not au.is_done(chkf, step):
if not subject_excluded:
newmeanfname = gfnames[eg,0] + exclude_str
newvarfname = gfnames[eg,1] + exclude_str
newstdfname = gfnames[eg,2] + exclude_str
rstep = au.remove_str() + ' ' + au.subject_str() + ' ' + str(exclude_subj) + ' ' + au.fromstats_str() + ' ' + datadir
if not au.is_done(chkf, rstep):
#(meanfname, varfname, samplesize, subjvolfname, newmeanfname, newvarfname, newstdfname='')
remove_subject_from_stats (gfnames[eg,0], gfnames[eg,1], groupsizes[eg][1], exclude_subj, newmeanfname, newvarfname, newstdfname)
au.checklist_add (chkf, rstep)
gfnames[eg,0] += exclude_str
gfnames[eg,1] += exclude_str
gfnames[eg,2] += exclude_str
groupsizes[eg][1] -= 1
subject_excluded = True
#calculating distance
if not au.is_done(chkf, step):
mean1fname = au.add_extension_if_needed (gfnames[g1,0], au.ext_str())
mean2fname = au.add_extension_if_needed (gfnames[g2,0], au.ext_str())
var1fname = au.add_extension_if_needed (gfnames[g1,1], au.ext_str())
var2fname = au.add_extension_if_needed (gfnames[g2,1], au.ext_str())
std1fname = au.add_extension_if_needed (gfnames[g1,2], au.ext_str())
std2fname = au.add_extension_if_needed (gfnames[g2,2], au.ext_str())
outfname = measure_function (mean1fname, mean2fname, var1fname, var2fname, std1fname, std2fname, groupsizes[g1][1], groupsizes[g2][1], experiment, outdir, exclude_idx)
if absolute:
change_to_absolute_values (outfname)
au.checklist_add (chkf, step)
return outfname
def group_distance(measure_function,
datadir,
groups,
groupsizes,
chkf,
absolute=False,
outdir='',
foldno='',
expname='',
exclude_idx=-1,
exclude_subj='',
exclude_subjclass=''):
olddir = os.getcwd()
if not outdir:
outdir = datadir
ngroups = len(groups)
#matrix of strings of 2000 characters maximum, to save filepaths
gfnames = np.zeros([ngroups, 3], dtype=np.dtype('a2000'))
subject_excluded = False
for g1 in range(ngroups):
g1name = groups[g1]
#mean1fname
gfnames[g1, 0] = datadir + os.path.sep + g1name + '_' + au.mean_str()
#var1fname
gfnames[g1, 1] = datadir + os.path.sep + g1name + '_' + au.var_str()
#std1fname
gfnames[g1, 2] = datadir + os.path.sep + g1name + '_' + au.std_str()
for g2 in range(g1 + 1, ngroups):
g2name = groups[g2]
gfnames[g2,
0] = datadir + os.path.sep + g2name + '_' + au.mean_str()
gfnames[g2,
1] = datadir + os.path.sep + g2name + '_' + au.var_str()
gfnames[g2,
2] = datadir + os.path.sep + g2name + '_' + au.std_str()
experiment = g1name + '_vs_' + g2name
#check if exclude_subjclass is any of both current groups
eg = -1
if exclude_idx > -1:
if exclude_subjclass == g1name: eg = g2
elif exclude_subjclass == g2name: eg = g1
step = au.measure_str(
) + ' ' + measure_function.func_name + ' ' + experiment + ' ' + datadir
#remove subject from stats
if eg > -1:
exclude_str = '_' + au.excluded_str() + str(exclude_idx)
step += exclude_str
experiment += exclude_str
if not au.is_done(chkf, step):
if not subject_excluded:
newmeanfname = gfnames[eg, 0] + exclude_str
newvarfname = gfnames[eg, 1] + exclude_str
newstdfname = gfnames[eg, 2] + exclude_str
rstep = au.remove_str() + ' ' + au.subject_str(
) + ' ' + str(exclude_subj) + ' ' + au.fromstats_str(
) + ' ' + datadir
if not au.is_done(chkf, rstep):
#(meanfname, varfname, samplesize, subjvolfname, newmeanfname, newvarfname, newstdfname='')
remove_subject_from_stats(gfnames[eg,
0], gfnames[eg,
1],
groupsizes[eg][1],
exclude_subj,
newmeanfname,
newvarfname, newstdfname)
au.checklist_add(chkf, rstep)
gfnames[eg, 0] += exclude_str
gfnames[eg, 1] += exclude_str
gfnames[eg, 2] += exclude_str
groupsizes[eg][1] -= 1
subject_excluded = True
#calculating distance
if not au.is_done(chkf, step):
mean1fname = au.add_extension_if_needed(
gfnames[g1, 0], au.ext_str())
mean2fname = au.add_extension_if_needed(
gfnames[g2, 0], au.ext_str())
var1fname = au.add_extension_if_needed(gfnames[g1, 1],
au.ext_str())
var2fname = au.add_extension_if_needed(gfnames[g2, 1],
au.ext_str())
std1fname = au.add_extension_if_needed(gfnames[g1, 2],
au.ext_str())
std2fname = au.add_extension_if_needed(gfnames[g2, 2],
au.ext_str())
outfname = measure_function(mean1fname, mean2fname, var1fname,
var2fname, std1fname, std2fname,
groupsizes[g1][1],
groupsizes[g2][1], experiment,
outdir, exclude_idx)
if absolute:
change_to_absolute_values(outfname)
au.checklist_add(chkf, step)
return outfname