ldaseqmodel.py 文件源码

def compute_lda_lhood(self):
        """
        compute the likelihood bound
        """
        num_topics = self.lda.num_topics
        gamma_sum = np.sum(self.gamma)

        # to be used in DIM
        # sigma_l = 0
        # sigma_d = 0 

        lhood = gammaln(np.sum(self.lda.alpha)) - gammaln(gamma_sum)
        self.lhood[num_topics] = lhood

        # influence_term = 0
        digsum = digamma(gamma_sum)

        model = "DTM"
        for k in range(0, num_topics):
            # below code only to be used in DIM mode
            # if ldapost.doc_weight is not None and (model == "DIM" or model == "fixed"):
            #     influence_topic = ldapost.doc_weight[k]
            #     influence_term = - ((influence_topic * influence_topic + sigma_l * sigma_l) / 2.0 / (sigma_d * sigma_d))

            e_log_theta_k = digamma(self.gamma[k]) - digsum
            lhood_term = (self.lda.alpha[k] - self.gamma[k]) * e_log_theta_k + gammaln(self.gamma[k]) - gammaln(self.lda.alpha[k])
            # TODO: check why there's an IF
            n = 0
            for word_id, count in self.doc:
                if self.phi[n][k] > 0:
                    lhood_term += count * self.phi[n][k] * (e_log_theta_k + self.lda.topics[word_id][k] - self.log_phi[n][k])
                n += 1
            self.lhood[k] = lhood_term
            lhood += lhood_term
            # in case of DIM add influence term
            # lhood += influence_term

        return lhood