ranker.py 文件源码

def token_similarity(self, words ,rwords):
        words = set(words)
        rwords = set(rwords)
        word_vec = np.zeros(self.word_dim)
        rword_vec = np.zeros(self.word_dim)
        word_count = 0
        rword_count = 0
        for word in words:
            if self.word_vec.has_key(word) and word not in self.stopwords:
                word_vec += self.word_vec[word]
                word_count += 1
        for word in rwords:
            if self.word_vec.has_key(word):
                rword_vec += self.word_vec[word]
                rword_count += 1
        if word_count > 0:
            word_vec = word_vec / word_count
        if rword_count > 0:
            rword_vec = rword_vec / rword_count
        if word_count>0 and rword_count>0:
            return cosine(word_vec, rword_vec)
        else:
            return 1