similarityWord2Vec.py 文件源码

def test2(self):
        topWords = self.getTopTfIdfTerms("Jerusalem")
        for word in topWords:
            #print word, idfIndex[word] if word in idfIndex else 1.5
            try:
                print self.model.most_similar(positive=[word], topn=10)
            except:
                print "word not in vocabulary"


#print model.accuracy(r"C:\Users\David\workspace\Wiki\gitWiki\questions-words.txt")

#model = word2vec.Word2Vec(sentences)
#model = word2vec.Word2Vec.load_word2vec_format("C:\Users\David\workspace\Wiki\gitWiki\text8-queen", binary=False)
#model = gensim.models.Word2Vec.load_word2vec_format('/tmp/vectors.txt', binary=False)