|
0
|
1 import csv, os, sys, argparse
|
|
|
2
|
|
|
3 from bl.vl.kb import KnowledgeBase as KB
|
|
|
4 import bl.vl.utils.ome_utils as vlu
|
|
|
5 from bl.vl.utils import LOG_LEVELS, get_logger
|
|
|
6
|
|
|
7
|
|
|
8 def make_parser():
|
|
|
9 parser = argparse.ArgumentParser(description='Retrieve all enrollments')
|
|
|
10 parser.add_argument('--logfile', type=str, help='log file (default=stderr)')
|
|
|
11 parser.add_argument('--loglevel', type=str, choices = LOG_LEVELS,
|
|
|
12 help='logger level', default='INFO')
|
|
|
13 parser.add_argument('--host', type=str, help='omero hostname')
|
|
|
14 parser.add_argument('--user', type=str, help='omero user')
|
|
|
15 parser.add_argument('--passwd', type=str, help='omero password')
|
|
|
16 parser.add_argument('--ofile', type=str, help='output file path',
|
|
|
17 required=True)
|
|
|
18 return parser
|
|
|
19
|
|
|
20
|
|
|
21 def main(argv):
|
|
|
22 parser = make_parser()
|
|
|
23 args = parser.parse_args(argv)
|
|
|
24
|
|
|
25 # This is a temporary hack!!!
|
|
|
26 to_be_ignored = ['IMMUNOCHIP_DISCARDED', 'CASI_MS_CSM_TMP',
|
|
|
27 'CASI_MS_CSM_CODES']
|
|
|
28
|
|
|
29 logger = get_logger('all_enrollments', level=args.loglevel,
|
|
|
30 filename=args.logfile)
|
|
|
31
|
|
|
32 try:
|
|
|
33 host = args.host or vlu.ome_host()
|
|
|
34 user = args.user or vlu.ome_user()
|
|
|
35 passwd = args.passwd or vlu.ome_passwd()
|
|
|
36 except ValueError, ve:
|
|
|
37 logger.critical(ve)
|
|
|
38 sys.exit(ve)
|
|
|
39
|
|
|
40 try:
|
|
|
41 out_file_path = args.ofile
|
|
|
42 except IndexError:
|
|
|
43 logger.error('Mandatory field missing.')
|
|
|
44 parser.print_help()
|
|
|
45 sys.exit(2)
|
|
|
46
|
|
|
47 # Create the KnowledgeBase object
|
|
|
48 kb = KB(driver='omero')(host, user, passwd)
|
|
|
49
|
|
|
50 # Retrieve all studies from omero
|
|
|
51 studies = kb.get_objects(kb.Study)
|
|
|
52 studies = [s for s in studies if s.label not in to_be_ignored]
|
|
|
53 logger.info('Retrieved %d studies from database' % len(studies))
|
|
|
54
|
|
|
55 csv_header = ['individual_uuid']
|
|
|
56 enrolls_map = {}
|
|
|
57
|
|
|
58 # For each study, retrieve all enrollments
|
|
|
59 for s in studies:
|
|
|
60 logger.info('Retrieving enrollments for study %s' % s.label)
|
|
|
61 enrolls = kb.get_enrolled(s)
|
|
|
62 logger.info('%s enrollments retrieved' % len(enrolls))
|
|
|
63 if len(enrolls) > 0:
|
|
|
64 logger.debug('Building lookup dictionary....')
|
|
|
65 for e in enrolls:
|
|
|
66 enrolls_map.setdefault(e.individual.omero_id, {})['individual_uuid'] = e.individual.id
|
|
|
67 enrolls_map[e.individual.omero_id].setdefault('studies', {})
|
|
|
68 enrolls_map[e.individual.omero_id]['studies'].setdefault(s.label,[])
|
|
|
69 enrolls_map[e.individual.omero_id]['studies'][s.label].append(e.studyCode)
|
|
|
70 label = "{0} #{1}".format(s.label,len(enrolls_map[e.individual.omero_id]['studies'][s.label]))
|
|
|
71 enrolls_map[e.individual.omero_id][label] = e.studyCode
|
|
|
72 if label not in csv_header:
|
|
|
73 csv_header.append(label) # Add study label to CSV header
|
|
|
74 else:
|
|
|
75 logger.debug('No enrollments found, skip study %s' % s.label)
|
|
|
76
|
|
|
77 # Write to CSV file
|
|
|
78 logger.debug('Writing CSV file %s' % out_file_path)
|
|
|
79 with open(out_file_path, 'w') as f:
|
|
|
80 writer = csv.DictWriter(f, csv_header,
|
|
|
81 delimiter='\t', quotechar='"',
|
|
|
82 restval = 'None')
|
|
|
83 writer.writeheader()
|
|
|
84 for k, v in enrolls_map.iteritems():
|
|
|
85 v.pop("studies",{})
|
|
|
86 writer.writerow(v)
|
|
|
87
|
|
|
88 if __name__ == '__main__':
|
|
|
89 main(sys.argv[1:])
|
