source: trunk/yat/classifier/EnsembleBuilder.cc @ 1072

// $Id$

/*
  Copyright (C) 2005 Markus Ringnér
  Copyright (C) 2006 Jari Häkkinen, Markus Ringnér, Peter Johansson
  Copyright (C) 2007 Jari Häkkinen, Peter Johansson

  This file is part of the yat library, http://trac.thep.lu.se/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 "EnsembleBuilder.h"
#include "DataLookup2D.h"
#include "FeatureSelector.h"
#include "KernelLookup.h"
#include "MatrixLookup.h"
#include "MatrixLookupWeighted.h"
#include "Sampler.h"
#include "SubsetGenerator.h"
#include "SupervisedClassifier.h"
#include "Target.h"
#include "yat/utility/matrix.h"

#include <cassert>

namespace theplu {
namespace yat {
namespace classifier {

  EnsembleBuilder::EnsembleBuilder(const SupervisedClassifier& sc, 
                                   const Sampler& sampler) 
    : mother_(sc),subset_(new SubsetGenerator<DataLookup2D>(sampler,sc.data()))
  {
  }

  EnsembleBuilder::EnsembleBuilder(const SupervisedClassifier& sc, 
                                   const Sampler& sampler,
                                   FeatureSelector& fs) 
    : mother_(sc),
      subset_(new SubsetGenerator<DataLookup2D>(sampler,sc.data(),fs))
  {
  }

  EnsembleBuilder::~EnsembleBuilder(void) 
  {
    for(size_t i=0; i<classifier_.size(); i++)
      delete classifier_[i];
    delete subset_;
  }

  void EnsembleBuilder::build(void) 
  {
    for(u_long i=0; i<subset_->size();++i) {
      SupervisedClassifier* classifier=
        mother_.make_classifier(subset_->training_data(i), 
                                subset_->training_target(i));
      classifier->train();
      classifier_.push_back(classifier);
    }   
  }


  const SupervisedClassifier& EnsembleBuilder::classifier(size_t i) const
  {
    return *(classifier_[i]);
  }


  u_long EnsembleBuilder::size(void) const
  {
    return classifier_.size();
  }


  void EnsembleBuilder::predict
  (const DataLookup2D& data, 
   std::vector<std::vector<statistics::Averager> >& result)
  {
    result.clear();
    result.reserve(subset_->target().nof_classes());    
    for(size_t i=0; i<subset_->target().nof_classes();i++)
      result.push_back(std::vector<statistics::Averager>(data.columns()));
    
    utility::matrix prediction;  

    for(u_long k=0;k<subset_->size();++k) {       
      const DataLookup2D* sub_data =
        data.selected(subset_->training_features(k));
      assert(sub_data);
      classifier(k).predict(*sub_data,prediction);
      delete sub_data;
    }

    for(size_t i=0; i<prediction.rows();i++) 
      for(size_t j=0; j<prediction.columns();j++) 
        result[i][j].add(prediction(i,j));    
  }

  
  const std::vector<std::vector<statistics::Averager> >& 
  EnsembleBuilder::validate(void)
  {
    validation_result_.clear();

    validation_result_.reserve(subset_->target().nof_classes());    
    for(size_t i=0; i<subset_->target().nof_classes();i++)
      validation_result_.push_back(std::vector<statistics::Averager>(subset_->target().size()));
    
    utility::matrix prediction;  
    for(u_long k=0;k<subset_->size();k++) {
      classifier(k).predict(subset_->validation_data(k),prediction);
      
      // map results to indices of samples in training + validation data set
      for(size_t i=0; i<prediction.rows();i++) 
        for(size_t j=0; j<prediction.columns();j++) {
          validation_result_[i][subset_->validation_index(k)[j]].
            add(prediction(i,j));
        }           
    }
    return validation_result_;
  }

}}} // of namespace classifier, yat, and theplu