1#!/usr/local/bin/python3.8
2
3import sys
4import collections
5import utils
6try:
7    import argparse as ap
8    import bz2
9    import random
10except ImportError:
11    sys.stderr.write( "argparse not found" )
12    sys.exit(-1)
13
14def read_params( args ):
15    p = ap.ArgumentParser(description='Convert Usearch ".uc" files in tab-delimited'
16            ' files with the seed as first field followed by the other IDs\n')
17
18    p.add_argument( 'ctxt', nargs='?', default=None, type=str,
19            help=   "the input uc file [stdin if not present]")
20    p.add_argument('txt', nargs='?', default=None, type=str,
21            help=   "the output txt file compresse if fiven with bz2 extension\n"
22                    "[stdout if not present]")
23    p.add_argument('--subsample', metavar="Subsampling rate",
24            default=1.0, type=float )
25    p.add_argument('-n', action='store_true' )
26    p.add_argument('-p', metavar="Prefix for taxon names",
27            default="", type=str )
28    p.add_argument('--sk', action='store_true' )
29
30    return vars( p.parse_args() )
31
32if __name__ == "__main__":
33    args = read_params( sys.argv )
34    uc2cl = collections.defaultdict( set )
35
36    gint = str if args['sk'] else int
37
38    valin = []
39    with utils.openr( args['ctxt'] ) as inp:
40        for l in inp:
41            tset = set([gint(a) for a in l.strip().split('\t')][1:])
42            valin.append(tset)
43    all_t = set()
44    for v in valin:
45        all_t |= v
46
47    res = {}
48    for t in all_t:
49        #if len(t) < args['n']:
50        #    continue
51        res[t] = [int(t in v) for v in valin]
52
53    with utils.openw(args['txt']) as out:
54        mat_res = {}
55        for k1 in res:
56            mat_res[k1] = {}
57            for k2 in res:
58                mat_res[k1][k2] = float(len([1 for x,y in zip(res[k1],res[k2]) if x == 1 and y == 1]))/max(sum(res[k1]),sum(res[k2]))
59
60        keys = sorted(res)
61        out.write( "\t".join( ["x"]+keys ) +"\n" )
62        for k in keys:
63            out.write( "\t".join( [k] + [str(mat_res[k][k2]) for k2 in keys] ) +"\n" )
64
65
66        """
67        n = len(res.values()[0])
68        n_s = int(float(n)*args['subsample'])
69        indok = set(random.sample( list(range(n)), n_s))
70        out.write( "\t".join(['genes']+["g"+str(v) for v in range(n)]) + "\n" )
71
72        for k,v in res.items():
73            out.write( args['p'] + str(k)+"\t"+"\t".join([str(s) for i,s in enumerate(v) if i in indok]) +"\n" )
74        """
75