hmp.txt or hmp.txt.gz to plink ped format - use R gist to get map format

convert_hmp_plink_ped.py

#!/usr/bin/python

import sys
import csv
import array

def main():
    #if len(sys.argv) < 2:
    #    print 'give me a filename'
    #    sys.exit(1)

    fname = 'AmesUSInbreds_AllZeaGBSv1.0_imputed_20130508_chr1.hmp.txt'

    names = []
    datarows = []
    with open(fname) as f:

        header = f.readline().strip().split('\t')
        header = header[:1] + header[11:] # strip out headers we don't need
        for i, row in enumerate(f):
            row = row.strip()
            tabcount = j = 0
            for j in xrange(len(row)):
                if row[j] == '\t':
                    if tabcount == 0:
                        name = row[:j]
                    elif tabcount == 10:
                        break
                    tabcount += 1
            datarow = array.array('b', row[j+1::2])

            names.append(name)
            datarows.append(datarow)
    print len(names), 'names'
    print len(datarows), 'data'
    print len(header), 'columns'
    expanding = dict(N='N N', X='N N', A='A A', C='C C', G='G G',
                     T='T T', K='G T', M='A C', R='A G', S='C G',
                     W='A T', Y='C T')
    def convert(c):
        c = chr(c)
        return expanding.get(c, c)

    with open(fname + '.converted.ped', 'wb') as out:
        owrite = out.write
        for i in xrange(len(header)):
            owrite(header[i] + '\t' + names[i] + '\t')
            owrite('\t'.join(convert(r[i]) for r in datarows))
            owrite('\n')
    print 'done'

if __name__ == '__main__':
    main()

A little gist to convert GBS hapmap.txt to plink ped files

Seems to work ok. No complaints - affiliated public gist will make the .map file