Pythonで単語の数え上げとかするならCounterを使うと便利なはなし ref: http://qiita.com/hatchinee/items/a904c1f8d732a4686c9d

file0.txt

data = ['aaa', 'bbb', 'ccc', 'aaa', 'ddd']

word_and_counts = {}
for word in data:
    if word_and_counts.has_key(word):
        word_and_counts[word] += 1
    else:
        word_and_counts[word] = 1
for w, c in sorted(word_and_counts.iteritems(), key=lambda x: x[1], reverse=True):
    print w, c  # =>
                #   aaa 2
                #   bbb 1
                #   ccc 1
                #   ddd 1

file1.txt

from collections import Counter

data = ['aaa', 'bbb', 'ccc', 'aaa', 'ddd']
counter = Counter(data)
for word, cnt in counter.most_common():
    print word, cnt # =>
                    #   aaa 2
                    #   bbb 1
                    #   ccc 1
                    #   ddd 1

file2.txt

from collections import Counter

dataA = ['aaa', 'bbb', 'ccc', 'aaa', 'ddd']
dataB = ['aaa', 'bbb', 'bbb', 'bbb', 'abc']

counterA = Counter(dataA)
counterB = Counter(dataB)

counter = counterA + counterB  # 頻度を足し合わせられる
counterA.subtract(counterB)  # 要素の差をとる（破壊的メソッド）
counter.most_common(3)  # 上位3要素の取得（上記の例のように、引数nの省略を省略すればすべての要素を降順で取得）
# 他にもいくつか

file3.txt

# -*- coding: utf-8 -*-

from collections import Counter
import codecs
import json

import MeCab


# バッドノウハウ感あるけど、出力結果をリダイレクトしたいし
import sys
reload(sys)
sys.setdefaultencoding("utf-8")

# codecsはunicodeを返す
# 一行目に余計な記述があってだるいしテストコードだし面倒なので事前に消しておこう
_tweetfile = codecs.open('./data/js/tweets/2013_09.js', 'r', 'sjis')
tweets = json.load(_tweetfile)
# Mecabはstr型しか受け付けないのでエンコード
texts = (tw['text'].encode('utf-8') for tw in tweets)

tagger = MeCab.Tagger('-Ochasen')
counter = Counter()
for text in texts:
    nodes = tagger.parseToNode(text)
    while nodes:
        if nodes.feature.split(',')[0] == '名詞':
            word = nodes.surface.decode('utf-8')
            counter[word] += 1
        nodes = nodes.next
for word, cnt in counter.most_common():
    print word, cnt