NICE_VisLearning/math/cluster/KMedian.h

/** 
* @file KMedian.h
 * @brief KMedian (aka K-medoid)
* @author Alexander Freytag
* @date 23-04-2013 (dd-mm-yyyy)

*/
#ifndef KMEDIANINCLUDE
#define KMEDIANINCLUDE

#include "core/vector/VectorT.h"
#include "core/vector/MatrixT.h"
  
#include "ClusterAlgorithm.h"
#include <core/vector/Distance.h>

namespace OBJREC {

  /**
   * @class KMedian
   * @brief KMedian (aka K-medoid)
   * @author Alexander Freytag
   * @date 23-04-2013 (dd-mm-yyyy)
  */    
  class KMedian : public ClusterAlgorithm
  {

      protected:
        
      /************************
       * 
       *   protected variables
       * 
       **************************/ 
      
        //! desired number of clusters
        int noClasses;
        
        //! specify which distance to use for calculating assignments
        std::string distanceType;
        
        //! the actual distance metric
        NICE::VectorDistance<double> *distancefunction;
        
        double d_minDelta;
        int i_maxIterations;
        
  
       /************************
       * 
       *   protected methods
       * 
       **************************/  
      
        //! compute the distance between two features using the specified distance metric
        double vectorDistance(const NICE::Vector &vector1, const NICE::Vector &vector2, uint distancetype);
        
        //! compute assignments of all given features wrt to the currently known prototypes (cluster medoids) == ~ E-step
        double compute_assignments ( const NICE::VVector & features,
                  const NICE::VVector & prototypes,
                  std::vector<int> & assignment );

        //! compute number of assignments for every currently found cluster
        double compute_weights ( const NICE::VVector & features,
              std::vector<double> & weights,
              std::vector<int>    & assignment );

        //! compute the difference between prototypes of previous iteration and those currently found
        double compute_delta ( const NICE::VVector & oldprototypes,
                    const NICE::VVector & prototypes );

        //! compute (update) prototypes given the current assignments == ~ M-step
        int compute_prototypes ( const NICE::VVector & features,
                NICE::VVector & prototypes,
                std::vector<double> & weights,
                const std::vector<int>    & assignment );

        //! have an initial guess, i.e., randomly pick some features as initial cluster centroids
        void initial_guess ( const NICE::VVector & features,
                NICE::VVector & prototypes );
        
        //! give additional information for the current iteration
        void print_iteration ( int iterations, 
                  NICE::VVector & prototypes,
                  double delta );

      public:
    
        /**
        * @brief standard constructor
        * @param noClasses the number of clusters to be computed
        * @param distanceMode a string specifying the distance function to be used (default: euclidean)
        */
        KMedian( int noClasses , std::string distanceMode="euclidean");
            
        /** simple destructor */
        virtual ~KMedian();
          
        /**
        *@brief this is the actual method that performs the clustering for a given set of features
        *@author Alexander Freytag
        *@date 25-04-2013 (dd-mm-yyyy)
        *@param   features input features to be clustered
        *@param   prototypes computed prototypes (cluster medoids) for the given samples
        *@param   weights number of assignments for every cluster
        *@param   assignment explicite assignments of features to computed cluster medoids
        */        
        void cluster ( const NICE::VVector & features,
                NICE::VVector & prototypes,
                std::vector<double> & weights,
                std::vector<int>    & assignment );

  };


} // namespace

#endif