def __init__(self):
import konlpy
from konlpy import tag
print("Initialize Hannanum from konlpy ({})".format(
konlpy.__version__),
file=sys.stderr)
self._mdl = tag.Hannanum()
def tagger_load(self):
name = self.tagger_name
if name == 'Okt':
self.tagger = tag.Okt()
elif name == 'Kkma':
self.tagger = tag.Kkma()
elif name == 'Komoran':
self.tagger = tag.Komoran()
else:
self.tagger = tag.Hannanum()
print("load tagger")
def parse_into_nouns(articles):
articles = utils.preprocess(articles)
model = tag.Hannanum()
result = []
for sentence in articles:
words = []
for word in model.nouns(sentence):
for p in punctuation:
word = word.replace(p, '')
if word not in ignore_words:
try:
int(word)
except ValueError:
words.append(word)
if len(words) > 0:
result.append(words)
return result
def __init__(self, tagger, useful_tags, delimiters, min_token_length,
stopwords, **kwargs):
if tagger == 'twitter':
self.tagger = taggers.Twitter()
self.tagger_options = {
'norm': bool(kwargs.get('norm', True)),
'stem': bool(kwargs.get('stem', True)),
}
elif tagger == 'komoran':
self.tagger = taggers.Komoran()
self.tagger_options = {
'flatten': bool(kwargs.get('flatten', True)),
}
elif tagger == 'hannanum':
self.tagger = taggers.Hannanum()
self.tagger_options = {
'ntags': int(kwargs.get('ntags', 9)),
'flatten': bool(kwargs.get('flatten', True)),
}
elif tagger == 'kkma':
self.tagger = taggers.Kkma()
self.tagger_options = {
'flatten': bool(kwargs.get('flatten', True)),
}
# 윈도에선 mecab을 지원하지 않으니 이하 생략하도록 한다.
# elif tagger == 'mecab':
# self.tagger = taggers.Mecab()
# self.tagger_options = {
# 'flatten': bool(kwargs.get('flatten', True)),
# }
else:
raise LexRankError(
"available taggers are: twitter, komoran, hannanum, kkma")
self.useful_tags = useful_tags
self.delimiters = delimiters
self.stopwords = stopwords
self.min_token_length = min_token_length
self.splitter = self.splitterer()
self.pos = lambda text: self.tagger.pos(text, **self.tagger_options)
def __init__(self, pre_trained=True, analyzer='Hannanum'):
self.pre_trained = pre_trained
if analyzer == 'Hannanum':
self.analyzer = tag.Hannanum()
elif analyzer == 'Kkma':
self.analyzer = tag.Kkma()
elif analyzer == 'Komoran':
self.analyzer = tag.Komoran()
elif analyzer == 'Mecab':
self.analyzer = tag.Mecab()
elif analyzer == 'Okt':
self.analyzer = tag.Okt()
else:
if pre_trained == False:
pass
else:
print('Enter a valid KoNLPy analyzer name.\n\tavailable: Hannanum, Kkma, Komoran, Mecab, Okt')
self.WordExtractor = WordExtractor(min_frequency=0)
self.noun_extractor = LRNounExtractor(verbose=False)
self.word_score = {}
