reducer.py mapper.py -20180411

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Wed Apr 11 22:36:56 2018

@author: vicky
"""

from operator import itemgetter
from itertools import groupby
import sys

def read_mapper_output(file, separator = '\t'):
    for line in file:
        yield line.rstrip().split(separator, 1)

def main(separator = '\t'):
    data = read_mapper_output(sys.stdin, separator = separator)
    for current_word, group in groupby(data, itemgetter(0)):
        try:
            total_count = sum(int(count) for current_word, count in group)
            print("%s%s%d" % (current_word, separator, total_count))
        except:
            pass

if __name__ == "__main__":
    main()

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Wed Apr 11 22:32:09 2018

@author: vicky
"""

import sys
def read_input(file):
    for line in file:
        yield line.split()

def main(separator='\t'):
    data = read_input(sys.stdin)
    for words in data:
        for word in words:
            print "%s%s%d" % (word, separator, 1)

if __name__ == "__main__":
    main()