[Machine learning] Naive Bayes (Naivebayes)

C + + Description:

1#include <iostream>2#include <string>3#include <fstream>4#include <sstream>5#include <vector>6#include <map>7#include <Set>8 9 using namespacestd;Ten  One classNaivebayes { A  Public: -     voidLoad_data (stringpath); -     voidTrain_model (); the     intPredictConstvector<int> &item); - Private: -vector<vector<int>>data; -map<pair<int,int,Double> c_p;//conditional Prob +map<int,Double> p_p;//Prior prob - }; +  A voidNaivebayes::load_data (stringpath) { at ifstream Fin (PATH.C_STR ()); -     if(!Fin) { -Cerr <<"Open File Error"<<Endl; -Exit1); -     } -  in     stringLine ; -      while(Getline (Fin, line)) { to         if(Line.size () >1) { + stringstream sin (line); -             intElem; thevector<int>tmp; *              while(Sin >>elem) { $ Tmp.push_back (elem);Panax Notoginseng             } - Data.push_back (TMP); the         } +     } A fin.close (); the } +  - voidNaivebayes::train_model () { $      for(Auto &d:data) { $         intLen =d.size (); -P_p[d[len-1]] += (1.0/data.size ()); -     } the  -      for(Auto &p:p_p) {Wuyi         intLabel =P.first; the         DoublePrior =P.second; -          for(Auto &d:data) { Wu              for(inti =0; I < d.size (); ++i) { -C_p[make_pair (D[i], label)] + = (1.0/(Prior *data.size ())); About             } $         } -     } - } -  A intNaivebayes::p redict (Constvector<int> &Item) {  +     intresult; the     DoubleMax_prob =0.0; -      for(Auto &p:p_p) { $         intLabel =P.first; the         DoublePrior =P.second; the         DoubleProb =Prior; the          for(inti =0; I < item.size ()-1; ++i) { theProb *=C_p[make_pair (Item[i], label)]; -         } in  the         if(Prob >Max_prob) { theMax_prob =prob; Aboutresult =label; the         } the     } the  +     returnresult; - } the Bayi intMain () { the Naivebayes Naive_bayes; theNaive_bayes.load_data (string("Result.txt")); - Naive_bayes.train_model (); -  thevector<int> item{2,4}; thecout <<naive_bayes.predict (item); the     return 0; the}

Data set:

1 4-11 5-11 5 11 4 11 4-12 4-12 5-12 5 12 6 12 6 13 6 13 5 13 5 13 6 13 6-1

[Machine learning] Naive Bayes (Naivebayes)