reader.py 文件源码

def get(self, text=["medical"]):
    if type(text) == str:
      text = text.lower()
      text = TreebankWordTokenizer().tokenize(text)

    try:
      data = np.array(map(self.vocab.get, text))
      return self.onehot(data), data
    except:
      unknowns = []
      for word in text:
        if self.vocab.get(word) == None:
          unknowns.append(word)
      raise Exception(" [!] unknown words: %s" % ",".join(unknowns))