source: trunk/yat/classifier/EnsembleBuilder.h @ 1079

#ifndef _theplu_yat_classifier_ensemblebuilder_ 
#define _theplu_yat_classifier_ensemblebuilder_ 

// $Id$

/*
  Copyright (C) 2005 Markus Ringnér
  Copyright (C) 2006 Jari Häkkinen, Markus Ringnér, Peter Johansson
  Copyright (C) 2007, 2008 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 "FeatureSelector.h";
#include "Sampler.h"
#include "SubsetGenerator.h"
#include "yat/statistics/Averager.h"

#include <vector>

namespace theplu {
namespace yat {
namespace classifier {  

  ///
  /// @brief Class for ensembles of supervised classifiers
  ///
  template <class Classifier, class Data>
  class EnsembleBuilder
  {
  
  public:
    typedef Classifier classifier_type;
    typedef Data data_type;

    ///
    /// Constructor.
    ///
    EnsembleBuilder(const Classifier&, const Sampler&);

    ///
    /// Constructor.
    ///
    EnsembleBuilder(const Classifier&, const Sampler&, 
                    FeatureSelector&);

    ///
    /// Destructor.
    ///
    virtual ~EnsembleBuilder(void);

    ///
    /// Generate ensemble. Function trains each member of the Ensemble.
    ///
    void build(void);

    ///
    /// @Return classifier
    ///
    const Classifier& classifier(size_t i) const;
      
    ///
    /// @Return Number of classifiers in ensemble
    ///
    u_long size(void) const;

    ///
    /// @brief Generate validation data for ensemble
    ///
    /// validate()[i][j] return averager for class @a i for sample @a j
    ///
    const std::vector<std::vector<statistics::Averager> >& validate(void);
    
    /**
       Predict a dataset using the ensemble.
       
       If @a data is a KernelLookup each column should correspond to a
       test sample and each row should correspond to a training
       sample. More exactly row \f$ i \f$ in @a data should correspond
       to the same sample as row/column \f$ i \f$ in the training
       kernel corresponds to.
    */
    void predict(const Data& data, 
                 std::vector<std::vector<statistics::Averager> > &);

  private:
    // no copying
    EnsembleBuilder(const EnsembleBuilder&);
    const EnsembleBuilder& operator=(const EnsembleBuilder&);
    

    const Classifier& mother_;
    SubsetGenerator<Data>* subset_;
    std::vector<Classifier*> classifier_;
    std::vector<std::vector<statistics::Averager> > validation_result_;

  };
  

  // implementation

  template <class C, class D> 
  EnsembleBuilder<C,D>::EnsembleBuilder(const C& sc, 
                                        const Sampler& sampler) 
    : mother_(sc),subset_(new SubsetGenerator<D>(sampler,sc.data()))
  {
  }


  template <class C, class D> 
  EnsembleBuilder<C, D>::EnsembleBuilder(const C& sc, const Sampler& sampler,
                                         FeatureSelector& fs) 
    : mother_(sc),
      subset_(new SubsetGenerator<D>(sampler,sc.data(),fs))
  {
  }


  template <class C, class D> 
  EnsembleBuilder<C, D>::~EnsembleBuilder(void) 
  {
    for(size_t i=0; i<classifier_.size(); i++)
      delete classifier_[i];
    delete subset_;
  }


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


  template <class C, class D> 
  const C& EnsembleBuilder<C, D>::classifier(size_t i) const
  {
    return *(classifier_[i]);
  }


  template <class C, class D> 
  u_long EnsembleBuilder<C, D>::size(void) const
  {
    return classifier_.size();
  }


  template <class C, class D> 
  void EnsembleBuilder<C, D>::predict
  (const D& 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 D* 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));    
  }

  
  template <class C, class D> 
  const std::vector<std::vector<statistics::Averager> >& 
  EnsembleBuilder<C, D>::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

#endif