def parse_logs(fnames, parse_fn, cache_yaml):
logs = datafile.load_cache_yaml(cache_yaml)
logs = filter(lambda log: 'fname' in log, logs)
processed_fnames = [log['fname'] for log in logs]
# print processed_fnames
for fname in fnames:
if fname in processed_fnames:
print "processed",fname
continue
print fname
date = datafile.get_date_from_fname(fname)
print date
if date is None:
continue
try:
log = {
'fname': fname,
'timestamp': calendar.timegm(date.timetuple()),
'iso_date_str': date.isoformat(),
}
parsed_log = parse_fn(fname)
log.update(parsed_log)
logs.append(log)
except KeyboardInterrupt:
raise
except Exception as E:
logger.debug("Error parsing " + fname + ": " + str(E))
continue
logs.sort(key=lambda l:l['timestamp'])
datafile.write_yaml(logs, cache_yaml)
return logs
def make_subset_groups(peptides, groups_yaml):
identify_subsets(peptides)
groups = find_subset_groups(peptides)
datafile.write_yaml(groups, groups_yaml)
def make_groups(peptides_csv, groups_yaml):
peptides = read_peptides_from_csv(peptides_csv)
identify_overlaps(peptides)
groups = find_groups(peptides)
datafile.write_yaml(groups, groups_yaml)
def make_overlap_groups(peptides, groups_yaml, min_overlap):
identify_overlaps(peptides, min_overlap)
groups = find_overlap_groups(peptides, min_overlap)
datafile.write_yaml(groups, groups_yaml)
def make_groups(peptides_csv, groups_yaml):
peptides = read_peptides_from_csv(peptides_csv)
identify_overlaps(peptides)
groups = find_groups(peptides)
datafile.write_yaml(groups, groups_yaml)