def get_subjects_sessions_dictionary(input_subjects,
cache,
resultdir,
prefix,
dbfile,
useSentinal,
shuffle=False):
import random
_temp = OpenSubjectDatabase(cache, ['all'], prefix, dbfile)
if "all" in input_subjects:
input_subjects = _temp.getAllSubjects()
if useSentinal:
print("=" * 80)
print("Using Sentinal Files to Limit Jobs Run")
_all_subjects = set(input_subjects)
_processed_subjects = set(
get_processed_subjects(resultdir, input_subjects))
subjects = list(_all_subjects - _processed_subjects
) #NOTE - in set operation notation removes values
else:
subjects = input_subjects
if shuffle:
random.shuffle(
subjects) # randomly shuffle to get max cluster efficiency
subject_sessions_dictionary = dict()
for subject in subjects:
subject_sessions_dictionary[subject] = _temp.getSessionsFromSubject(
subject)
return subjects, subject_sessions_dictionary
def get_subjects(subjects, cache, prefix, dbfile, shuffle=True):
import random
_temp = OpenSubjectDatabase(cache, ['all'], prefix, dbfile)
if "all" in subjects:
subjects = _temp.getAllSubjects()
if shuffle:
random.shuffle(subjects) # randomly shuffle to get max
return subjects
def get_subjects(argv, cache, prefix, dbfile, shuffle=True):
import random
_temp = OpenSubjectDatabase(cache, ['all'], prefix, dbfile)
subjects = argv["--subject"] #.split(',')
if "all" in subjects:
subjects = _temp.getAllSubjects()
if shuffle:
random.shuffle(subjects) # randomly shuffle to get max
return subjects
def get_subjects_sessions_dictionary(input_subjects, cache, resultdir, prefix, dbfile, useSentinal, shuffle=False):
import random
_temp = OpenSubjectDatabase(cache, ['all'], prefix, dbfile)
if "all" in input_subjects:
input_subjects = _temp.getAllSubjects();
if useSentinal:
print("="*80)
print("Using Sentinal Files to Limit Jobs Run")
_all_subjects = set(input_subjects )
_processed_subjects = set( get_processed_subjects( resultdir, input_subjects ) )
subjects = list( _all_subjects - _processed_subjects ) #NOTE - in set operation notation removes values
else:
subjects = input_subjects
if shuffle:
random.shuffle(subjects) # randomly shuffle to get max cluster efficiency
subject_sessions_dictionary = dict()
for subject in subjects:
subject_sessions_dictionary[subject]=_temp.getSessionsFromSubject(subject)
return subjects,subject_sessions_dictionary
