def main():
tagger = Tagger()
wakati_tagger = Tagger('-Owakati')
text = '私はご飯を食べます。'
result = wakati_tagger.parse(text)
print('result1(parse + wakati):')
print(result)
print(type(result))
print()
result = tagger.parse(text)
print('result2(parse):')
print(result)
print(type(result))
print()
result = wakati_tagger(text)
print('result3(_call_+wakati):')
print(result)
print(type(result))
print(inspect.getmembers(result[0]))
print(type(result[0]))
print()
result = tagger(text)
print('result4(_call_):')
print(result)
print(type(result))
print(inspect.getmembers(result[0]))
print(type(result[0]))
print()
print('DONE')
def main():
tagger = Tagger()
neologd_tagger = Tagger('-d /usr/lib/x86_64-linux-gnu/mecab/dic/mecab-unidic-neologd')
text = '私は、渋谷ストリームでランチを食べる。'
print('unidic:')
print(tagger.parse(text))
print()
print('unidic-neologd:')
print(neologd_tagger.parse(text))
print('DONE')
class Tokenizer():
def __init__(self):
self.tagger = Tagger("-Owakati")
def tokenize(self, text):
tokens = self.tagger.parse(text).split(" ")
return tokens
def main():
text = 'softbank'
tagger = Tagger()
gtagger = GenericTagger()
print('Tagger:')
print(tagger.parse(text))
for word in tagger(text):
print(word.surface)
print(word.feature)
print()
print('GenericTagger:')
print(gtagger.parse(text))
for word in gtagger(text):
print(word.surface)
print(word.feature)
print()
print('DONE')
def test_wakati(text, wakati):
tagger = Tagger('-Owakati')
assert tagger.parse(text) == wakati
text = 'でないと'
filter_text = text.replace(' ','');
filter_text = text.replace('?','');
filter_text = text.replace('!','');
filter_text = text.replace('...','');
filter_text = text.replace('(','');
filter_text = text.replace(')','');
text_binary = np.zeros(len(filter_text)) # 1 si des mots ont été trouvés à cet emplacement, sinon 0
text_kana = text #Texte qui sera traduit en kana
tagger.parse(text)
# => '麩 菓子 は 、 麩 を 主材 料 と し た 日本 の 菓子 。'
def data_preparation(csv):
regles = []
explications = []
for l in csv:
l.strip()
ligne = l.split(';')
if 'null' not in ligne:
regles.append(ligne[0])
explications.append(ligne[1])
return regles, explications
#!/usr/bin/env python
from fugashi import Tagger
tt = Tagger('-Owakati')
from collections import Counter
wc = Counter()
for line in open('wagahai.txt'):
for word in tt.parse(line.strip()).split(' '):
wc[word] += 1
