NCC.h

#ifndef _theplu_yat_classifier_ncc_
#define _theplu_yat_classifier_ncc_

// $Id: NCC.h 3562 2017-01-04 01:16:07Z peter $

/*
  Copyright (C) 2005 Peter Johansson, Markus Ringnér
  Copyright (C) 2006, 2007, 2008 Jari Häkkinen, Peter Johansson, Markus Ringnér
  Copyright (C) 2009, 2010, 2017 Peter Johansson

  This file is part of the yat library, http://dev.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 3 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 yat. If not, see <http://www.gnu.org/licenses/>.
*/

#include "MatrixLookup.h"
#include "MatrixLookupWeighted.h"
#include "SupervisedClassifier.h"
#include "Target.h"

#include "yat/statistics/Averager.h"
#include "yat/statistics/AveragerWeighted.h"
#include "yat/utility/concept_check.h"
#include "yat/utility/Exception.h"
#include "yat/utility/Matrix.h"
#include "yat/utility/MatrixWeighted.h"
#include "yat/utility/Vector.h"
#include "yat/utility/stl_utility.h"
#include "yat/utility/yat_assert.h"

#include <boost/concept_check.hpp>

#include <iterator>
#include <map>
#include <cmath>

namespace theplu {
namespace yat {
namespace classifier {


  template <typename Distance>
  class NCC : public SupervisedClassifier
  {

  public:
    NCC(void);

    NCC(const Distance&);


    virtual ~NCC(void);

    const utility::Matrix& centroids(void) const;

    NCC<Distance>* make_classifier(void) const;

    void predict(const MatrixLookup& data, utility::Matrix& results) const;

    void predict(const MatrixLookupWeighted& data, utility::Matrix& results) const;

    void train(const MatrixLookup& data, const Target& targets);


    void train(const MatrixLookupWeighted& data, const Target& targets);


  private:

    void predict_unweighted(const MatrixLookup&, utility::Matrix&) const;
    void predict_weighted(const MatrixLookupWeighted&, utility::Matrix&) const;

    utility::Matrix centroids_;
    bool centroids_nan_;
    Distance distance_;
  };

  // templates

  template <typename Distance>
  NCC<Distance>::NCC()
    : SupervisedClassifier(), centroids_nan_(false)
  {
    BOOST_CONCEPT_ASSERT((utility::DistanceConcept<Distance>));
  }

  template <typename Distance>
  NCC<Distance>::NCC(const Distance& dist)
    : SupervisedClassifier(), centroids_nan_(false), distance_(dist)
  {
    BOOST_CONCEPT_ASSERT((utility::DistanceConcept<Distance>));
  }


  template <typename Distance>
  NCC<Distance>::~NCC()
  {
  }


  template <typename Distance>
  const utility::Matrix& NCC<Distance>::centroids(void) const
  {
    return centroids_;
  }


  template <typename Distance>
  NCC<Distance>*
  NCC<Distance>::make_classifier() const
  {
    // All private members should be copied here to generate an
    // identical but untrained classifier
    return new NCC<Distance>(distance_);
  }

  template <typename Distance>
  void NCC<Distance>::train(const MatrixLookup& data, const Target& target)
  {
    centroids_.resize(data.rows(), target.nof_classes());
    for(size_t i=0; i<data.rows(); i++) {
      std::vector<statistics::Averager> class_averager;
      class_averager.resize(target.nof_classes());
      for(size_t j=0; j<data.columns(); j++) {
        class_averager[target(j)].add(data(i,j));
      }
      for(size_t c=0;c<target.nof_classes();c++) {
        centroids_(i,c) = class_averager[c].mean();
      }
    }
  }


  template <typename Distance>
  void NCC<Distance>::train(const MatrixLookupWeighted& data, const Target& target)
  {
    centroids_.resize(data.rows(), target.nof_classes());
    for(size_t i=0; i<data.rows(); i++) {
      std::vector<statistics::AveragerWeighted> class_averager;
      class_averager.resize(target.nof_classes());
      for(size_t j=0; j<data.columns(); j++)
        class_averager[target(j)].add(data.data(i,j),data.weight(i,j));
      for(size_t c=0;c<target.nof_classes();c++) {
        if(class_averager[c].sum_w()==0) {
          centroids_nan_=true;
        }
        centroids_(i,c) = class_averager[c].mean();
      }
    }
  }


  template <typename Distance>
  void NCC<Distance>::predict(const MatrixLookup& test,
                              utility::Matrix& prediction) const
  {
    utility::yat_assert<utility::runtime_error>
      (centroids_.rows()==test.rows(),
       "NCC::predict test data with incorrect number of rows");

    prediction.resize(centroids_.columns(), test.columns());

    // If weighted training data has resulted in NaN in centroids:
    // weighted calculations
    if(centroids_nan_) {
      predict_weighted(MatrixLookupWeighted(test),prediction);
    }
    // If unweighted training data: unweighted calculations
    else {
      predict_unweighted(test,prediction);
    }
  }

  template <typename Distance>
  void NCC<Distance>::predict(const MatrixLookupWeighted& test,
                              utility::Matrix& prediction) const
  {
    utility::yat_assert<utility::runtime_error>
      (centroids_.rows()==test.rows(),
       "NCC::predict test data with incorrect number of rows");

    prediction.resize(centroids_.columns(), test.columns());
    predict_weighted(test,prediction);
  }


  template <typename Distance>
  void NCC<Distance>::predict_unweighted(const MatrixLookup& test,
                                         utility::Matrix& prediction) const
  {
    for(size_t j=0; j<test.columns();j++)
      for(size_t k=0; k<centroids_.columns();k++)
        prediction(k,j) = distance_(test.begin_column(j), test.end_column(j),
                                    centroids_.begin_column(k));
  }

  template <typename Distance>
  void NCC<Distance>::predict_weighted(const MatrixLookupWeighted& test,
                                       utility::Matrix& prediction) const
  {
    utility::MatrixWeighted weighted_centroids(centroids_);
    for(size_t j=0; j<test.columns();j++)
      for(size_t k=0; k<centroids_.columns();k++)
        prediction(k,j) = distance_(test.begin_column(j), test.end_column(j),
                                    weighted_centroids.begin_column(k));
  }


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

#endif