Mapper

def mapper():

	for line in sys.stdin:

		data = line.strip.split("")

		for i in data:
			cleaned_data = i.translate(string.maketrans("",""), string.punctuation).lower()
			print "{0}\t{t}".format(cleaned_data,1)

			mapper()

Reduce stage -> reducer

import sys

def reducer():
	word_count = 0
	old_key = None

	for line in sys.stdin:
		data = line.strip().split("\t")

		if len(data) != 2:
			continue

		if old_key and old_key != this_key: 
			print"{0}\t{1}".format(old_key, word_count)
			word_count = 0

		old_key = this_key
		word_count += float(count)

	if old_key != None:
		print "{0}\t{1}".format(old_key, word_count)

#! /bin/bash

cat ../../data/aliceInWorderland.txt | python word_count_mapper.py | sort | python word_count_reducer.py