in subsample.py [0:0]
def sub(filename,out, size):
qids = {}
with open(filename,'r') as f:
for l in f:
l = l.strip().split('\t')[0]
qids[l]= 0
sample = list(qids)[:size]
with open(filename,'r') as f:
with open(out,'w') as w:
for l in f:
qid = l.strip().split('\t')[0]
if qid in sample:
w.write(l)