WordAverage by Header Word

mapper.py

#!/usr/bin/env python
import sys

# 標準入力を取得する
for line in sys.stdin:
    line=line.strip()
    words=line.split()

    # 単語の頭文字とその文字数を返す
    for word in words:
        # 標準出力として
        print '%s\t%s' % (word[0], len(word))

reducer.py

#!/usr/bin/env python

from operator import itemgetter
import sys

wordCount = {}
average = 0.0

for line in sys.stdin:
    line = line.strip()

    word, count=line.split('\t', 1)

    try:
        count=int(count)
        wordCount[word]['sum'] = wordCount.get(word['sum'], 0) + count
        wordCount[word]['frequency'] = wordCount.get(word['frequency'], 0) + 1
    except ValueError:
        pass

for word, values in wordCount:
    average = values['sum'] / values['frequency']
    print '%s\t%s' % (word, average)