def pearson_correlation(datadir,
outdir,
usemask=True,
excludef='',
exclude_idx=-1):
slidir = datadir + os.path.sep + au.slices_str()
subjsfile = datadir + os.path.sep + au.subjects_str()
labelsfile = datadir + os.path.sep + au.labels_str()
lst = os.listdir(slidir)
n = au.count_match(lst, au.data_str() + '_' + au.slice_regex())
exclude_log = ''
if exclude_idx > -1:
exclude_log = ' excluding subject ' + str(exclude_idx)
au.log.info('Calculating correlation of ' + slidir + os.path.sep +
au.data_str() + '_' + au.slice_regex() + exclude_log)
for i in range(n):
slino = au.zeropad(i)
dataf = slidir + os.path.sep + au.data_str() + '_' + au.slice_str(
) + '_' + slino + au.ext_str()
maskf = slidir + os.path.sep + au.mask_str() + '_' + au.slice_str(
) + '_' + slino + au.ext_str()
outf = outdir + os.path.sep + au.pearson_str() + '_' + au.slice_str(
) + '_' + slino
if exclude_idx > -1:
outf += '_' + au.excluded_str() + str(exclude_idx) + au.ext_str()
else:
outf += au.ext_str()
if not os.path.isfile(dataf):
au.log.error('Could not find ' + dataf)
continue
if not usemask:
maskf = ''
try:
measure_pearson(dataf, labelsfile, outf, maskf, excludef,
exclude_idx)
except:
au.log.error(
'pearson_correlation: Error measuring correlation on ' + dataf)
au.log.error("Unexpected error: ", sys.exc_info()[0])
exit(1)
def pearson_correlation (datadir, outdir, usemask=True, excludef='', exclude_idx=-1):
slidir = datadir + os.path.sep + au.slices_str()
subjsfile = datadir + os.path.sep + au.subjects_str()
labelsfile = datadir + os.path.sep + au.labels_str()
lst = os.listdir(slidir)
n = au.count_match(lst, au.data_str() + '_' + au.slice_regex())
exclude_log = ''
if exclude_idx > -1:
exclude_log = ' excluding subject ' + str(exclude_idx)
au.log.info ('Calculating correlation of ' + slidir + os.path.sep + au.data_str() + '_' + au.slice_regex() + exclude_log)
for i in range(n):
slino = au.zeropad(i)
dataf = slidir + os.path.sep + au.data_str() + '_' + au.slice_str() + '_' + slino + au.ext_str()
maskf = slidir + os.path.sep + au.mask_str() + '_' + au.slice_str() + '_' + slino + au.ext_str()
outf = outdir + os.path.sep + au.pearson_str() + '_' + au.slice_str() + '_' + slino
if exclude_idx > -1:
outf += '_' + au.excluded_str() + str(exclude_idx) + au.ext_str()
else:
outf += au.ext_str()
if not os.path.isfile(dataf):
au.log.error('Could not find ' + dataf)
continue
if not usemask:
maskf = ''
try:
measure_pearson(dataf, labelsfile, outf, maskf, excludef, exclude_idx)
except:
au.log.error('pearson_correlation: Error measuring correlation on ' + dataf)
au.log.error("Unexpected error: ", sys.exc_info()[0] )
exit(1)
#getting output prefix
prefix = prefixes[m]
m += 1
#saving the feature matrix and labels in a binary file
#setting output file name
ofname = features_str()
if prefix:
ofname = prefix + '_' + ofname
if scale:
ofname = ofname + '.' + scaled_str()
if excluf:
excl_ofname = au.excluded_str() + au.feats_str()
if prefix:
excl_ofname = prefix + '_' + excl_ofname
if scale:
excl_ofname = excl_ofname + '.' + au.scaled_str()
filename = get_filepath(outdir, ofname, otype)
if os.path.exists(filename):
print(filename + ' already exists. Jumping to the next.')
else:
print('Creating ' + filename)
#reading mask volume
if not os.path.exists(maskf):
err = 'Mask file not found: ' + maskf
raise IOError(err)
def save_data (outdir, prefix, dataname, otype, excluding, leave, feats, labels, exclfeats, exclulabels, dmin, dmax, scale, scale_min, scale_max, lthr, uthr, thrp, absolute):
#setting output file name
ofname = au.feats_str()
if leave > -1:
ofname += '.' + au.excluded_str() + str(leave)
if absolute: ofname += '.' + au.abs_str()
if lthr: ofname += '.lthr_' + str(lthr)
if uthr: ofname += '.uthr_' + str(uthr)
if thrp: ofname += '.thrP_' + str(thrp)
if scale: ofname += '.' + au.scaled_str()
if excluding:
excl_ofname = au.excluded_str() + '_' + ofname
exclfilename = get_filepath (outdir, excl_ofname , otype)
if prefix:
ofname = prefix + '_' + ofname
excl_ofname = prefix + '_' + excl_ofname
filename = get_filepath (outdir, ofname, otype)
#writing in a text file the scaling values of this training set
if scale:
write_scalingrange_file (outdir + os.path.sep + ofname + '.scaling_range', dmin, dmax, scale_min, scale_max)
#saving binary file depending on output type
if otype == 'numpybin':
np.save (filename, feats)
if excluding:
np.save (exclfilename, exclfeats)
elif otype == 'octave':
sio.savemat (filename, {au.feats_str(): feats, au.labels_str(): labels})
if excluding:
exclulabels[exclulabels == 0] = -1
sio.savemat (exclfilename, {au.feats_str(): exclfeats, au.labels_str(): exclulabels})
elif otype == 'svmperf':
labels[labels == 0] = -1
ae.write_svmperf_dat(filename, dataname, feats, labels)
if excluding:
exclulabels[exclulabels == 0] = -1
ae.write_svmperf_dat(exclfilename, dataname, exclfeats, exclulabels)
elif otype == 'arff':
featnames = np.arange(nfeats) + 1
ae.write_arff (filename, dataname, featnames, feats, labels)
if excluding:
ae.write_arff (exclfilename, dataname, featnames, exclfeats, exclulabels)
else:
err = 'Output method not recognised!'
au.log.error(err)
sys.exit(-1)
return [filename, exclfilename]
#read the measure argument and start processing
if measure == 'pea':
#measure pearson correlation for each population slice
step = au.measureperslice_str() + step_params
if not au.is_done(chkf, step):
pear.pearson_correlation(outdir, mdir, usemask, excluf, leave)
au.checklist_add(chkf, step)
#merge all correlation slice measures
step = au.postmerging_str() + step_params
if not au.is_done(chkf, step):
pearegex = au.pearson_str() + '_' + au.slice_str() + '*'
peameasf = mdir + os.path.sep + au.pearson_str()
if leave > -1:
pearegex += '_' + au.excluded_str() + str(leave) + '*'
peameasf += '_' + au.excluded_str() + str(
leave) + '_' + au.pearson_str()
post.merge_slices(mdir, pearegex, peameasf, mdir)
if absval:
post.change_to_absolute_values(peameasf)
au.checklist_add(chkf, step)
#BHATTACHARYYA AND T-TEST
elif measure == 'bat' or measure == 'ttest':
if not os.path.exists(statsdir):
os.mkdir(statsdir)
# getting output prefix
prefix = prefixes[m]
m += 1
# saving the feature matrix and labels in a binary file
# setting output file name
ofname = features_str()
if prefix:
ofname = prefix + "_" + ofname
if scale:
ofname = ofname + "." + scaled_str()
if excluf:
excl_ofname = au.excluded_str() + au.feats_str()
if prefix:
excl_ofname = prefix + "_" + excl_ofname
if scale:
excl_ofname = excl_ofname + "." + au.scaled_str()
filename = get_filepath(outdir, ofname, otype)
if os.path.exists(filename):
print(filename + " already exists. Jumping to the next.")
else:
print("Creating " + filename)
# reading mask volume
if not os.path.exists(maskf):
err = "Mask file not found: " + maskf
raise IOError(err)
#read the measure argument and start processing
if measure == 'pea':
#measure pearson correlation for each population slice
step = au.measureperslice_str() + step_params
if not au.is_done(chkf, step):
pear.pearson_correlation (outdir, mdir, usemask, excluf, leave)
au.checklist_add(chkf, step)
#merge all correlation slice measures
step = au.postmerging_str() + step_params
if not au.is_done(chkf, step):
pearegex = au.pearson_str() + '_' + au.slice_str() + '*'
peameasf = mdir + os.path.sep + au.pearson_str()
if leave > -1:
pearegex += '_' + au.excluded_str() + str(leave) + '*'
peameasf += '_' + au.excluded_str() + str(leave) + '_' + au.pearson_str()
post.merge_slices (mdir, pearegex, peameasf, mdir)
if absval:
post.change_to_absolute_values(peameasf)
au.checklist_add(chkf, step)
#BHATTACHARYYA AND T-TEST
elif measure == 'bat' or measure == 'ttest':
if not os.path.exists (statsdir):
os.mkdir(statsdir)
print('Creating ' + filename)
if otype == 'numpybin':
np.save(filename, feats)
elif otype == 'octave':
sio.savemat(filename, {au.feats_str(): feats, au.labels_str(): labels})
elif otype == 'svmperf':
labels[labels == 0] = -1
ae.write_svmperf_dat(filename, dataname, feats, labels)
if excluf:
exclulabels[exclulabels == 0] = -1
exclfilename = set_filename(
outdir, prefix + '_' + au.excluded_str() + au.feats_str(),
otype)
ae.write_svmperf_dat(exclfilename, dataname, exclfeats,
exclulabels)
elif otype == 'arff':
featnames = np.arange(nfeats) + 1
ae.write_arff(filename, dataname, featnames, feats, labels)
else:
err = 'Output method not recognised!'
raise IOError(err)
return filename
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
filename = set_filename (outdir, prefix + '_' + au.features_str(), otype)
print ('Creating ' + filename)
if otype == 'numpybin':
np.save (filename, feats)
elif otype == 'octave':
sio.savemat (filename, {au.feats_str(): feats, au.labels_str(): labels})
elif otype == 'svmperf':
labels[labels == 0] = -1
ae.write_svmperf_dat(filename, dataname, feats, labels)
if excluf:
exclulabels[exclulabels == 0] = -1
exclfilename = set_filename(outdir, prefix + '_' + au.excluded_str() + au.feats_str(), otype)
ae.write_svmperf_dat(exclfilename, dataname, exclfeats, exclulabels)
elif otype == 'arff':
featnames = np.arange(nfeats) + 1
ae.write_arff (filename, dataname, featnames, feats, labels)
else:
err = 'Output method not recognised!'
raise IOError(err)
return filename
#-------------------------------------------------------------------------------
## END EXTRACT FEATSET
#-------------------------------------------------------------------------------
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
