doc2veckeras.py 文件源码

def predict(self,X):
        self.sents_test=X
        self.sents_all=self.sents_train + self.sents_test

        if self.sents_shuffle :
            s_indexs=range(len(self.sents_all))
            random.shuffle(s_indexs)
            s_invers_indexs=range(len(s_indexs))
            for n in range(len(s_indexs)):
                s_invers_indexs[s_indexs[n]]=n
            sents_all=[self.sents_all[n] for n in s_indexs]
        else:
            sents_all=self.sents_all
        all_docs = list(LabeledListSentence(self.sents_all))

        self.doc2vec_set(all_docs)
        #print 'size',self.doc2vec.vector_size

        self.X_train= [self.doc2vec.infer_vector(s) for s in self.sents_train]
        self.X_test= [self.doc2vec.infer_vector(s) for s in self.sents_test]
        self.logistic =LogisticRegressionCV(class_weight='balanced')#,n_jobs=-1)
        self.logistic.fit(self.X_train,self.Y_train)
        Y_test_predict=self.logistic.predict(self.X_test)
        return Y_test_predict