labeling an unlabeled instance in Weka(java code) -
i beginner in java , weka tool, want use logitboost algorithm decisionstump weak learner in java code, don't know how work. create vector 6 feature(without label feature) , want feed logitboost labeling , probability of assignment. labels 1 or -1 , train/test data in arff file.this code, algorithm return 0 ! thanks
double candidate_similarity(ha_nodes ha , weightmatrix[][] wm , logitboost lgb ,arraylist<attribute> atts){ logitboost lgb = new logitboost(); lgb.buildclassifier(newdata);//newdata arff file labeled data evaluation eval = new evaluation(newdata); eval.crossvalidatemodel(lgb, newdata, 10, new random(1)); try { feature_vector[0] = ip_sim(main.a_new.dip, ha.candidate.dip_cand); feature_vector[1] = ip_sim(main.a_new.sip, ha.candidate.sip_cand); feature_vector[2] = ip_s_d_sim(main.a_new.sip, ha); feature_vector[3] = dport_sim(main.a_new.dport, ha); freq_weight(main.a_new.atype, ha, freq_avg, weight_avg , wm); feature_vector[4] = weight_avg; feature_vector[5] = freq_avg; double[] values = new double[]{feature_vector[0],feature_vector[1],feature_vector[2],feature_vector[3],feature_vector[4],feature_vector[5]}; denseinstance newinst = new denseinstance(1.0,values); instances dataunlabeled = new instances("testinstances", atts, 0); dataunlabeled.add(newinst); dataunlabeled.setclassindex(dataunlabeled.numattributes() - 1); double clslable = lgb.classifyinstance(inst); } catch (exception ex) { //logger.getlogger(module2.class.getname()).log(level.severe, null, ex); } return clslable;}
where did newdata come from? need load file correct classification, use class load features file: http://weka.sourceforge.net/doc/weka/core/converters/arffloader.html
i'm not posting example code because use weka matlab, dont have examples in java.
Comments
Post a Comment