Word Count MapReduce

wordcount_mapreduce.py

# wordcount
import string
from functools import reduce

str = """\
How much ground would a groundhog hog, \
if a groundhog could hog ground? \
A gfoundhog would hog all the ground he could hog, \
if a groundhog could hog ground. \
"""

# 1. partition
word_list = str.translate(string.punctuation).split(' ')

# 2. map
word_map  = map(lambda x: (x, 1), word_list)

# 3. group by
group_by_word = {}
for word, value in word_map:
  try:
    group_by_word[word].append(value)
  except:
    group_by_word[word] = [value]

# 4. reduce
word_count = {}
for key, key_list in group_by_word.items():
  word_count[key] = reduce(lambda x, y : x+y, key_list)

print(word_count)