RecSvd.py 文件源码

def do_calc_svd(self):

        print("?????%d" %(nlp_master.get_dict_len()))
        self.k_value = int(0.1*(nlp_master.get_dict_len()))
        if self.k_value < 300:
            self.k_value = 300
        if self.k_value > 1000:
            self.k_value = 1000
        print("k??%d" %(self.k_value))            

        tfidf = models.TfidfModel(list(nlp_master._id_docs.values()))
        tfidf_corpus = tfidf[list(nlp_master._id_docs.values())]

        # num_topics?????????????? 200–500
        # LSI??
        self.lsi = models.LsiModel(tfidf_corpus, id2word=nlp_master.dictionary, num_topics=self.k_value, chunksize=2000)

        # ??????
        today = datetime.date.today()
        self.dumpfile = "dumpdir/recsvd_dump.%d_%d" %(today.month, today.day)        

        with open(self.dumpfile,'wb', -1) as fp:
            dump_data = []
            dump_data.append(self._user_classifier)
            dump_data.append(self.k_value)
            dump_data.append(self.lsi)
            pickle.dump(dump_data, fp, -1)

        return


    # ???????NULL???
    # ???????site_news?????????????