Ejemplo n.º 1
0
 def __init__(self, max_document_length,
              min_frequency=0, vocabulary=None,
              tokenizer_fn=None):
     self.max_document_length = max_document_length
     self.min_frequency = min_frequency
     if vocabulary:
         self.vocabulary_ = vocabulary
     else:
         self.vocabulary_ = CategoricalVocabulary()
     if tokenizer_fn:
         self._tokenizer = tokenizer_fn
     else:
         self._tokenizer = tokenizer