Word2VecFromParsedCorpus.py 文件源码

def add_phrases(self, corpus):
        '''
        Parameters
        ----------
        corpus: Corpus for phrase augmentation

        Returns
        -------
        New ParsedCorpus containing unigrams in corpus and new phrases
        '''
        assert isinstance(corpus, ParsedCorpus)
        self.phrases = [Phrases(CorpusAdapterForGensim.get_sentences(corpus), delimiter=' ')]

        for i in range(1, self.max_tokens_per_phrase):
            self.phrases.append(Phrases(self.phrases[-1][CorpusAdapterForGensim.get_sentences(corpus)]))

        return self