thesaurus.py 文件源码

def synonyms_by_synset(self, synset_name, topn=3):
    ssid = self.id_table[synset_name]
    doc = self.doc_matrix[ssid]
    found_indices = set([ssid])
    synonyms = []
    for _ in range(topn):
      min_index = 0
      min_val = 10
      for i in range(self.doc_matrix.shape[0]):
        cos_dist = cosine(self.doc_matrix[i], doc)
        if i not in found_indices and cos_dist < min_val:
          min_index = i
          min_val = cos_dist
      found_indices.add(min_index)
      synonyms.append((self.definitions[min_index], min_val))
    return synonyms