word2vec.py 文件源码

def features(self, q1, q2):
        q1 = str(q1).lower().split()
        q2 = str(q2).lower().split()
        q1 = [w for w in q1 if w not in stopwords]
        q2 = [w for w in q2 if w not in stopwords]

        wmd = min(self.model.wmdistance(q1, q2), 10)
        wmd_norm = min(self.model_norm.wmdistance(q1, q2), 10)

        q1vec = self.sent2vec(q1)
        q2vec = self.sent2vec(q2)

        if q1vec is not None and q2vec is not None:
            cos = cosine(q1vec, q2vec)
            city = cityblock(q1vec, q2vec)
            jacc = jaccard(q1vec, q2vec)
            canb = canberra(q1vec, q2vec)
            eucl = euclidean(q1vec, q2vec)
            mink = minkowski(q1vec, q2vec, 3)
            bray = braycurtis(q1vec, q2vec)

            q1_skew = skew(q1vec)
            q2_skew = skew(q2vec)
            q1_kurt = kurtosis(q1vec)
            q2_kurt = kurtosis(q2vec)

        else:
            cos = -1
            city = -1
            jacc = -1
            canb = -1
            eucl = -1
            mink = -1
            bray = -1

            q1_skew = 0
            q2_skew = 0
            q1_kurt = 0
            q2_kurt = 0

        return wmd, wmd_norm, cos, city, jacc, canb, eucl, mink, bray, q1_skew, q2_skew, q1_kurt, q2_kurt