Mercurial > repos > galaxyp > percolator

comparison nested_collection.py @ 4:154147805a33 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/percolator commit 9db2c1bb610ff3a6940f0a037c0fccf337692c36
author galaxyp
date Fri, 28 Apr 2017 12:25:36 -0400
parents abed51712ed0
children 07107a686ce9
comparison
equal deleted inserted replaced
3:abed51712ed0 4:154147805a33
18 if pool_ids: 18 if pool_ids:
19 filegroups = OrderedDict([(p_id, get_filename_index_with_identifier( 19 filegroups = OrderedDict([(p_id, get_filename_index_with_identifier(
20 realnames, p_id)) for p_id in pool_ids]) 20 realnames, p_id)) for p_id in pool_ids])
21 else: 21 else:
22 filegroups = {1: range(len(realnames))} 22 filegroups = {1: range(len(realnames))}
23 batch = [] 23 batch, in_pool_indices = [], []
24 for pool_id, grouped_indices in filegroups.items(): 24 for pool_id, grouped_indices in filegroups.items():
25 if pool_id == 1: 25 if pool_id == 1:
26 pool_id = 'pool0' 26 pool_id = 'pool0'
27 for index in grouped_indices: 27 for in_pool_index, total_index in enumerate(grouped_indices):
28 batch.append(index) 28 batch.append(total_index)
29 in_pool_indices.append(in_pool_index)
29 if batchsize and len(batch) == int(batchsize): 30 if batchsize and len(batch) == int(batchsize):
30 yield pool_id, batch 31 yield pool_id, batch, in_pool_indices
31 batch = [] 32 batch, in_pool_indices = [], []
32 if len(batch) > 0: 33 if len(batch) > 0:
33 yield pool_id, batch 34 yield pool_id, batch, in_pool_indices
34 batch = [] 35 batch, in_pool_indices = [], []
35 36
36 37
37 def main(): 38 def main():
38 parser = argparse.ArgumentParser() 39 parser = argparse.ArgumentParser()
39 parser.add_argument('--batchsize', dest='batchsize', default=False) 40 parser.add_argument('--batchsize', dest='batchsize', default=False)
40 parser.add_argument('--real-names', dest='realnames', nargs='+') 41 parser.add_argument('--real-names', dest='realnames', nargs='+')
41 parser.add_argument('--galaxy-files', dest='galaxyfiles', nargs='+') 42 parser.add_argument('--galaxy-files', dest='galaxyfiles', nargs='+')
42 parser.add_argument('--pool-ids', dest='poolids', nargs='+', default=False) 43 parser.add_argument('--pool-ids', dest='poolids', nargs='+', default=False)
43 args = parser.parse_args() 44 args = parser.parse_args()
44 for batchcount, (pool_id, batch) in enumerate(get_batches_of_galaxyfiles( 45 batches = [x for x in get_batches_of_galaxyfiles(args.realnames, args.batchsize, args.poolids)]
45 args.realnames, args.batchsize, args.poolids)): 46 batchdigits = len(str(len(batches)))
46 for fncount, batchfile in enumerate([args.galaxyfiles[index] for index in batch]): 47 if args.poolids:
47 dsetname = '{}_batch{}___inputfn{}.data'.format(pool_id, batchcount, fncount) 48 pooldigits = {pid: [] for pid in args.poolids}
49 for batchdata in batches:
50 pooldigits[batchdata[0]].append(len(batchdata[1]))
51 pooldigits = {pid: len(str(sum(batchlengths))) for pid, batchlengths in pooldigits.items()}
52 else:
53 pooldigits = {'pool0': len(str(len(args.galaxyfiles)))}
54 for batchcount, (pool_id, batch, in_pool_indices) in enumerate(batches):
55 for fnindex, in_pool_index in zip(batch, in_pool_indices):
56 dsetname = '{pid}_batch{bi:0{bd}d}___inputfn{fi:0{pd}d}_{real}.data'.format(pid=pool_id, bi=batchcount, bd=batchdigits, fi=in_pool_index, pd=pooldigits[pool_id], real=args.realnames[fnindex])
48 print('producing', dsetname) 57 print('producing', dsetname)
49 os.symlink(batchfile, dsetname) 58 os.symlink(args.galaxyfiles[fnindex], dsetname)
50 59
51 if __name__ == '__main__': 60 if __name__ == '__main__':
52 main() 61 main()