728x90
from konlpy.tag import Okt
from collections import Counter
from konlpy.corpus import kolaw
from konlpy.corpus import kobill
import codecs
okt = Okt()
f = codecs.open('testtext.txt','r', encoding ='utf8')
text = f.read()
print(text)
# kolaw.open('./testtext.txt').read()[:30]
print("okt.morphs(text)")
print(okt.morphs(text))
print("okt.nouns(text)")
print(okt.nouns(text))
print("okt.phrases(text)")
print(okt.phrases(text))
# pos : 품사부착
# norm – If True, normalize tokens.
# stem – If True, stem tokens.
# join – If True, returns joined sets of morph and tag.
print("okt.pos(text)")
print(okt.pos(text))
print("okt.pos(text, norm=True)")
print(okt.pos(text, norm=True))
print("okt.pos(text, norm=True, stem=True)")
print(okt.pos(text, norm=True, stem=True))
# counter
print("Counter(okt.morphs(text) )")
print(Counter(okt.morphs(text) ))
from konlpy.tag import Okt
from collections import Counter
from konlpy.corpus import kolaw
from konlpy.corpus import kobill
import codecs
import pytagcloud
from Ipython.display import image
okt = Okt()
f = codecs.open('testtext.txt','r', encoding ='utf8')
text = f.read()
print(text)
# kolaw.open('./testtext.txt').read()[:30]
# print("okt.morphs(text)")
# print(okt.morphs(text))
print("okt.nouns(text)")
print(okt.nouns(text))
# print("okt.phrases(text)")
# print(okt.phrases(text))
# pos : 품사부착
# norm – If True, normalize tokens.
# stem – If True, stem tokens.
# join – If True, returns joined sets of morph and tag.
# print("okt.pos(text)")
# print(okt.pos(text))
# print("okt.pos(text, norm=True)")
# print(okt.pos(text, norm=True))
# print("okt.pos(text, norm=True, stem=True)")
# print(okt.pos(text, norm=True, stem=True))
# counter
print("Counter(okt.morphs(text) )")
count=Counter(okt.morphs(text) )
# count
print(count.most_common(10))
taglist = pytagcloud.make_tags(tag2,maxsize=80)
taglist