source: trunk/c++_tools/classifier/NBC.cc @ 675

// $Id: NBC.cc 675 2006-10-10 12:08:45Z jari $

/*
  Copyright (C) The authors contributing to this file.

  This file is part of the yat library, http://lev.thep.lu.se/trac/yat

  The yat library is free software; you can redistribute it and/or
  modify it under the terms of the GNU General Public License as
  published by the Free Software Foundation; either version 2 of the
  License, or (at your option) any later version.

  The yat library is distributed in the hope that it will be useful,
  but WITHOUT ANY WARRANTY; without even the implied warranty of
  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
  General Public License for more details.

  You should have received a copy of the GNU General Public License
  along with this program; if not, write to the Free Software
  Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
  02111-1307, USA.
*/

#include "yat/classifier/NBC.h"

#include "yat/classifier/DataLookup2D.h"
#include "yat/classifier/MatrixLookup.h"
#include "yat/classifier/MatrixLookupWeighted.h"
#include "yat/classifier/Target.h"
#include "yat/statistics/AveragerWeighted.h"
#include "yat/utility/matrix.h"

#include <vector>

namespace theplu {
namespace classifier {

  NBC::NBC(const MatrixLookup& data, const Target& target) 
    : SupervisedClassifier(target), data_(data)
  {
  }

  NBC::NBC(const MatrixLookupWeighted& data, const Target& target) 
    : SupervisedClassifier(target), data_(data)
  {
  }

  NBC::~NBC()   
  {
  }


  SupervisedClassifier* 
  NBC::make_classifier(const DataLookup2D& data, const Target& target) const 
  {     
    NBC* ncc=0;
    if(data.weighted()) {
      ncc=new NBC(dynamic_cast<const MatrixLookupWeighted&>(data),target);
    }
    else {
      ncc=new NBC(dynamic_cast<const MatrixLookup&>(data),target);
    }
    return ncc;
  }


  bool NBC::train()
  {   
    sigma_=centroids_=utility::matrix(data_.rows(), target_.nof_classes());
    utility::matrix nof_in_class(data_.rows(), target_.nof_classes());
    
    
    for(size_t i=0; i<data_.rows(); ++i) {
      std::vector<statistics::AveragerWeighted> aver(target_.nof_classes());
      for(size_t j=0; j<data_.columns(); ++j) {
        if (data_.weighted()){
          const MatrixLookupWeighted& data = 
            dynamic_cast<const MatrixLookupWeighted&>(data_);
            aver[target_(j)].add(data.data(i,j), data.weight(i,j));
        }
        else
          aver[target_(j)].add(data_(i,j),1.0);
      }
      for (size_t j=0; target_.nof_classes(); ++j){
        centroids_(i,j) = aver[j].mean();
        sigma_(i,j) = aver[j].variance();
      }
    }   
    trained_=true;
    return trained_;
  }


  void NBC::predict(const DataLookup2D& input,                    
                    utility::matrix& prediction) const
  {   
    std::cerr << "NBC::predict not implemented\n";
    exit(1);
  }


}} // of namespace classifier and namespace theplu