Hinweise zur Verwendung von MeCab aus Python

#!/usr/bin/env python
# -*- coding:utf-8 -*-

import MeCab
m = MeCab.Tagger()

print m.parse("Wenn ein Hund geht, trifft er einen Stock.")

$ ./mecab.py
Hund Nomen,Allgemeines,*,*,*,*,Hund,Hund,Hund
Auch Assistent,Hilfe,*,*,*,*,Ebenfalls,Mo.,Mo.
Verb gehen,Unabhängigkeit,*,*,Fünf-Dan / Ka-Linie,Angenommene Form,gehen,Arche,Arche
Ba Assistent,Verbindungsassistent,*,*,*,*,Wenn,Ba,Ba
Stick Nomen,Allgemeines,*,*,*,*,Stange,Bogen,Baud
Hilfs,Fallassistent,Allgemeines,*,*,*,Zu,D.,D.
Hit Verb,Unabhängigkeit,*,*,Fünf Schritte, La Linie,Grundform,Schlagen,Atal,Atal
.. Symbol,Phrase,*,*,*,*,。,。,。
EOS

#!/usr/bin/env python
# -*- coding:utf-8 -*-

import sys
param = sys.argv
infile = param[1]

f = open(infile)
line = f.readline() 

import MeCab
m = MeCab.Tagger()

while line:
	res = m.parseToNode(line)

	while res:
		print res.feature
		#Substantiv,Allgemeines,*,*,*,*,Hund,Hund,Hund

		res = res.next

	line = f.readline()

#!/usr/bin/env python
# -*- coding:utf-8 -*-

import sys
param = sys.argv
infile = param[1]

f = open(infile)
line = f.readline() 

import MeCab
m = MeCab.Tagger()

from collections import defaultdict
frequency = defaultdict(int)

while line:
	res = m.parseToNode(line)

	while res:
		# print res.feature
		#Substantiv,Allgemeines,*,*,*,*,Hund,Hund,Hund
		
		arr = res.feature.split(",")
		class_1 = arr[0]
		frequency[class_1] += 1
		
		res = res.next

	line = f.readline()

# print frequency
# defaultdict(<type 'int'>, {'...

for k, v in frequency.iteritems():
    print k, v

$ ./mecab_morph_count.py input.txt
Verb 4
BOS/EOS 8
Nomen 9
Hilfs 7
Hilfsverb 1

#MeCab-Instanz
m = MeCab.Tagger(' -d /usr/local/Cellar/mecab/0.996/lib/mecab/dic/mecab-ipadic-neologd')

m = MeCab.Tagger('-r my_mecabrc')

Recommended Posts