reducer.py

# reducer.py
# input data looks like
# (1,2)    1
# (2,3)    1
# (1,3)    1
# (1,3)    1

# need to count each group and sum the totals.

#!/usr/bin/python
threshhold = 8
import sys
from collections import defaultdict
cnts = defaultdict(int)
for line in sys.stdin:
  line = line.strip()
  k,v = line.split('\t')
  (item1,item2)=k.split(',')
  cnts[(int(item1),int(item2))] += 1


for key,val in cnts.items():
  if val >= threshhold:
    print '%s\t%s' % (key,val)