Mercurial > repos > bgruening > column_arrange_by_header

comparison column_arrange.py @ 1:6c6d26ff01ff draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/column_arrange_by_header commit b6e0b2de32ddb91085235397728623a35ad13f42
author bgruening
date Fri, 15 Feb 2019 07:45:03 -0500
parents f18f67056946
children
comparison
equal deleted inserted replaced
0:f18f67056946 1:6c6d26ff01ff
1 #!/usr/bin/env python 1 #!/usr/bin/env python
2 import pandas as pd 2
3 import argparse 3 import argparse
4 4
5 parser = argparse.ArgumentParser() 5 parser = argparse.ArgumentParser()
6 parser.add_argument('-i', '--input', help='Tabular Input File Name') 6 parser.add_argument('-i', '--input', help='Tabular Input File Name')
7 parser.add_argument('-o','--output', help='Tabular Output File') 7 parser.add_argument('-o','--output', help='Tabular Output File')
8 parser.add_argument('-c', '--columns', nargs='+', help='Column Headers to Sort By') 8 parser.add_argument(
9 '-c', '--columns', nargs='+', help='Column Headers to Sort By'
10 )
11 parser.add_argument(
12 '-d', '--discard', action='store_true',
13 help='Discard remaining columns'
14 )
15
9 args=parser.parse_args() 16 args=parser.parse_args()
10 17
11 cols = args.columns 18 with open(args.input) as data:
12 table = pd.read_csv(args.input, sep='\t') 19 hdr = next(data)
13 blist = list(table.columns) 20 columns = hdr.rstrip('\n').split('\t')
14 for token in cols: 21 idx = [columns.index(name) for name in args.columns]
15 blist.remove(token) 22 if not args.discard:
16 sorted_table = table[args.columns + blist] 23 idx += [i for i in range(len(columns)) if i not in idx]
17 # write without index, seperated by tabs 24 rearranged_cols = [columns[i] for i in idx]
18 sorted_table.to_csv(args.output, sep='\t', index=False) 25 with open(args.output, 'w') as out:
26 out.write('\t'.join(rearranged_cols) + '\n')
27 for line in data:
28 columns = line.rstrip('\n').split('\t')
29 rearranged_cols = [columns[i] for i in idx]
30 out.write('\t'.join(rearranged_cols) + '\n')