models.py 文件源码

def fit_embeddings(self, documents):
        """
        Train word embeddings of the classification model, using the same parameter values for classification on Gensim ``Word2Vec``.
        Similar to use a pre-trained model.
        :param documents:
        """
        params = self.get_params()
        del params['pre_trained']
        del params['bucket']
        # Word2Vec has not softmax
        if params['loss'] == 'softmax':
            params['loss'] = 'hs'
        LabeledWord2Vec.init_loss(LabeledWord2Vec(), params, params['loss'])
        del params['loss']
        w2v = Word2Vec(sentences=documents, **params)
        self._classifier = LabeledWord2Vec.load_from(w2v)