source: trunk/yat/classifier/NBC.h @ 1090

#ifndef _theplu_yat_classifier_nbc_ 
#define _theplu_yat_classifier_nbc_ 

// $Id: NBC.h 1042 2008-02-06 18:32:30Z peter $

/*
  Copyright (C) 2006 Jari Häkkinen, Markus Ringnér, Peter Johansson
  Copyright (C) 2007 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 "SupervisedClassifier.h"
#include "yat/utility/matrix.h"

namespace theplu {
namespace yat {
namespace classifier {  

  class DataLookup1D;
  class DataLookup2D;
  class MatrixLookup;
  class MatrixLookupWeighted;
  class Target;

  /**
     @brief Naive Bayesian Classification.
  
     Each class is modelled as a multinormal distribution with
     features being independent: \f$ p(x|c) = \prod
     \frac{1}{\sqrt{2\pi\sigma_i^2}} \exp \left(
     \frac{(x_i-m_i)^2}{2\sigma_i^2)} \right)\f$
  */
  class NBC : public SupervisedClassifier
  {
  
  public:
    ///
    /// Constructor taking the training data, the target vector, and
    /// the distance measure as input.
    ///
    NBC(const MatrixLookup&, const Target&);
    
    ///
    /// Constructor taking the training data with weights, the target
    /// vector, the distance measure, and a weight matrix for the
    /// training data as input.
    ///
    NBC(const MatrixLookupWeighted&, const Target&);

    virtual ~NBC();

    const DataLookup2D& data(void) const;


    SupervisedClassifier* make_classifier(const DataLookup2D&, 
                                          const Target&) const;
    
    ///
    /// Train the classifier using the training data.
    ///
    /// For each class mean and variance are estimated for each
    /// feature (see Averager and AveragerWeighted for details).
    ///
    /// If variance can not be estimated (too few data points or all
    /// points identical) for a feature and label, then that feature
    /// is ignored for that specific label.
    ///
    /// @return true if training succedeed.
    ///
    void train();

    
    /**
       Each sample (column) in \a data is predicted and predictions
       are returned in the corresponding column in passed \a res. Each
       row in \a res corresponds to a class. The prediction is the
       estimated probability that sample belong to class \f$ j \f$

       \f$ P_j = \frac{1}{Z}\prod_i{\frac{1}{\sigma_i}}
       \exp(\frac{w_i(x_i-\mu_i)^2}{\sigma_i^2})\f$, where \f$ \mu_i
       \f$ and \f$ \sigma_i^2 \f$ are the estimated mean and variance,
       respectively. If \a data is a MatrixLookup is equivalent to
       using all weight equal to unity.
    */
    void predict(const DataLookup2D& data, utility::matrix& res) const;


  private:
    utility::matrix centroids_;
    utility::matrix sigma2_;
    const DataLookup2D& data_;

    double sum_logsigma(size_t i) const;


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

#endif