view bin/uniq_merge.py @ 159:c3c3dd60b8a8

demo of slurm usage using cdx2tsv.py
author Henry S. Thompson <ht@inf.ed.ac.uk>
date Wed, 06 Jul 2022 18:07:34 +0100
parents f5e2211b50bd
children
line wrap: on
line source

#!/usr/bin/env python3
# Merge counts by key from the output of "uniq -c" (or sus) and sort in descending order
# An alternative to sus when the scale is too big for the initial sort, or if uniq -c already does a lot
#  of the work
# Usage: ... | uniq -c | uniq-merge.py
import sys
from collections import defaultdict
s=defaultdict(int)
for l in sys.stdin:
 (i,d)=l.split(maxsplit=1)
 s[d]+=int(i)
for (d,n) in sorted(s.items(),key=lambda j:j[1],reverse=True):
 sys.stdout.write('%5d\t%s'%(n,d))