Created
November 11, 2009 11:33
-
-
Save yono/231879 to your computer and use it in GitHub Desktop.
指定されたファイル中の文章を解析して 単語とその出現頻度を返す
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# -*- coding:utf-8 -*- | |
""" | |
feature_vector.py | |
指定されたファイル中の文章を解析して | |
単語とその出現頻度を返す | |
使い方(コマンドラインから) | |
% python feature_vector.py file | |
使い方 2(Pythonスクリプト中で) | |
import feature_vector | |
text = '単語とその出現頻度を返す' | |
result = feature_vector.analyse(text) | |
""" | |
import MeCab | |
def analyse(text): | |
mecab = MeCab.Tagger() ## MeCab のインスタンス作成 | |
feature_vector = {} ## 結果を納める辞書 | |
node = mecab.parseToNode(text) ## 解析を実行 | |
while node: | |
print node.surface, node.feature ## それぞれ単語とその情報(品詞など) | |
surface = node.surface.decode('utf-8') | |
feature_vector[surface] = feature_vector.get(surface, 0) + 1 # 辞書に単語を追加 | |
node = node.next | |
return feature_vector | |
if __name__ == '__main__': | |
import sys | |
filename = sys.argv[1] | |
file = open(filename).read() | |
feature_vector = analyse(file) | |
for word,freq in feature_vector.items(): | |
print "%s\t%d" % (word,freq) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment