Python PunktSentenceTokenizer.sentences_from_text方法代码示例

# 需要导入模块: from nltk.tokenize import PunktSentenceTokenizer [as 别名]
# 或者: from nltk.tokenize.PunktSentenceTokenizer import sentences_from_text [as 别名]
from nltk.tokenize import PunktSentenceTokenizer
from nltk.collocations import *
from nltk.tokenize import word_tokenize
from nltk.util import ngrams

txt = "I was in the room in Los Angeles in 1988, about 200 feet from Michael Dukakis, when Bernard Shaw asked him what he'd do if his wife were raped. Now that really was a sucker punch of a question. I was on the other side of the arena, in Cleveland, when Donald Trump bared his teeth (metaphorically speaking) at Megyn Kelly."

pst = PunktSentenceTokenizer()
sents = pst.sentences_from_text(txt.encode('utf-8').replace('\n',''))
print sents
bigrams = ngrams(word_tokenize(sents[1].replace('.','')),2)
print bigrams

# 需要导入模块: from nltk.tokenize import PunktSentenceTokenizer [as 别名]
# 或者: from nltk.tokenize.PunktSentenceTokenizer import sentences_from_text [as 别名]
pst = PunktSentenceTokenizer()
files =[]
words = []
##allow to take a directory
for i in sys.argv:
  match = re.match(".*\.txt$", i)
  if match:
    files.append(i)

print 'file_name' + '\t' + 'politcal_stance'

for f in files:
  with open(f,"rb") as class_file:
    if sys.argv[1] == '--sents':
      data = class_file.read().replace('\n', '')
      sents = pst.sentences_from_text(data)
      for sent in sents:
        sent_words = nltk.word_tokenize(sent)
        for word in sent_words:
          words.append(word)
      feats = dict([(word, True) for word in words])

    else:
      for line in class_file:
        line_words = nltk.word_tokenize(line)
        for word in line_words:
          words.append(word)
      feats = dict([(word, True) for word in words])

    print f + '\t' + classifier.classify(feats)

# 需要导入模块: from nltk.tokenize import PunktSentenceTokenizer [as 别名]
# 或者: from nltk.tokenize.PunktSentenceTokenizer import sentences_from_text [as 别名]
def sentence_parser( input_str ):

    sentences_tokenize = PunktSentenceTokenizer()
    for sentence in sentences_tokenize.sentences_from_text( input_str ):
        if sentence.strip() != u'':
            yield sentence