Frequency analysis of text files

freq_noun.py

import MeCab
import sys
import re
import collections

cmd, infile = sys.argv
with open(infile) as f:
    text = f.read()
f.close()

m = MeCab.Tagger ('-Ochasen')
 
node = m.parseToNode(text)
words=[]
while node:
    hinshi = node.feature.split(",")[0]
    if hinshi in ["名詞"]:
        origin = node.feature.split(",")[6]
        words.append(origin)
    node = node.next
c = collections.Counter(words)
print(c.most_common(40))