Mercurial > repos > earlhaminst > hcluster_sg_parser
comparison hcluster_sg_parser.py @ 4:02d73e6ca869 draft
planemo upload for repository https://github.com/TGAC/earlham-galaxytools/tree/master/tools/hcluster_sg_parser commit e35f2ea026b79daaced9a2a50da02b4881d6154b
| author | earlhaminst |
|---|---|
| date | Fri, 19 Jul 2019 11:44:07 -0400 |
| parents | f9e418125021 |
| children | 07f5b2c5ac10 |
comparison
equal
deleted
inserted
replaced
| 3:f9e418125021 | 4:02d73e6ca869 |
|---|---|
| 15 parser = optparse.OptionParser() | 15 parser = optparse.OptionParser() |
| 16 parser.add_option('-m', '--min', type='int', default=0, help='Minimum number of cluster elements') | 16 parser.add_option('-m', '--min', type='int', default=0, help='Minimum number of cluster elements') |
| 17 parser.add_option('-M', '--max', type='int', default=sys.maxsize, help='Maximum number of cluster elements') | 17 parser.add_option('-M', '--max', type='int', default=sys.maxsize, help='Maximum number of cluster elements') |
| 18 options, args = parser.parse_args() | 18 options, args = parser.parse_args() |
| 19 | 19 |
| 20 with open(args[1], 'w') as discarded_out: | 20 with open(args[2], 'w') as discarded_max_out: |
| 21 with open(args[0]) as fh: | 21 with open(args[1], 'w') as discarded_min_out: |
| 22 for line in fh: | 22 with open(args[0]) as fh: |
| 23 line = line.rstrip() | 23 for line in fh: |
| 24 line_cols = line.split('\t') | 24 line = line.rstrip() |
| 25 cluster_id = line_cols[0] | 25 line_cols = line.split('\t') |
| 26 n_ids = int(line_cols[-2]) | 26 cluster_id = line_cols[0] |
| 27 id_list = line_cols[-1].replace(',', '\n') | 27 n_ids = int(line_cols[-2]) |
| 28 if n_ids >= options.min and n_ids <= options.max: | 28 id_list = line_cols[-1].replace(',', '\n') |
| 29 outfile = cluster_id + '_output.txt' | 29 if n_ids < options.min: |
| 30 with open(outfile, 'w') as f: | 30 discarded_min_out.write(id_list) |
| 31 f.write(id_list) | 31 elif n_ids > options.max: |
| 32 else: | 32 discarded_max_out.write(id_list) |
| 33 discarded_out.write(id_list) | 33 else: |
| 34 outfile = cluster_id + '_output.txt' | |
| 35 with open(outfile, 'w') as f: | |
| 36 f.write(id_list) | |
| 34 | 37 |
| 35 | 38 |
| 36 if __name__ == "__main__": | 39 if __name__ == "__main__": |
| 37 main() | 40 main() |