root/library/bdm/stat/merger.h @ 1009

/*!
  \file
  \brief Mergers for combination of pdfs
  \author Vaclav Smidl.

  -----------------------------------
  BDM++ - C++ library for Bayesian Decision Making under Uncertainty

  Using IT++ for numerical operations
  -----------------------------------
*/

#ifndef MERGER_H
#define MERGER_H


#include "../estim/mixtures.h"
#include "discrete.h"

namespace bdm {
using std::string;

//!Merging methods
enum MERGER_METHOD {ARITHMETIC = 1, GEOMETRIC = 2, LOGNORMAL = 3};

/*!
@brief Base class for general combination of pdfs on discrete support

Mixtures of Gaussian densities are used internally. Switching to other densities should be trivial.

The merged pdfs are expected to be of the form:
 \f[ f(x_i|y_i),  i=1..n \f]
where the resulting merger is a density on \f$ \cup [x_i,y_i] \f$ .
Note that all variables will be joined.

As a result of this feature, each source must be extended to common support
\f[ f(z_i|y_i,x_i) f(x_i|y_i) f(y_i)  i=1..n \f]
where \f$ z_i \f$ accumulate variables that were not in the original source.
These extensions are calculated on-the-fly.

However, these operations can not be performed in general. Hence, this class merges only sources on common support, \f$ y_i={}, z_i={}, \forall i \f$.
For merging of more general cases, use offsprings merger_mix and merger_grid.
*/

class merger_base : public epdf {
protected:
        //! Elements of composition
        Array<shared_ptr<pdf> > pdfs;

        //! Data link for each pdf in pdfs
        Array<datalink_m2e*> dls;

        //! Array of rvs that are not modelled by pdfs at all, \f$ z_i \f$
        Array<RV> rvzs;

        //! Data Links for extension \f$ f(z_i|x_i,y_i) \f$
        Array<datalink_m2e*> zdls;

        //! number of support points
        int Npoints;

        //! number of sources
        int Nsources;

        //! switch of the methoh used for merging
        MERGER_METHOD METHOD;
        //! Default for METHOD
        static const MERGER_METHOD DFLT_METHOD;

        //!Prior on the log-normal merging model
        double beta;
        //! default for beta
        static const double DFLT_beta;

        //! Projection to empirical density (could also be piece-wise linear)
        eEmp eSmp;

        //! debug or not debug
        bool DBG;

        //! debugging file
        it_file* dbg_file;
public:
        //! \name Constructors
        //! @{

        //! Default constructor
        merger_base () : Npoints ( 0 ), Nsources ( 0 ), DBG ( false ), dbg_file ( 0 ) {
        }

        //!Constructor from sources
        merger_base ( const Array<shared_ptr<pdf> > &S );

        //! Function setting the main internal structures
        void set_sources ( const Array<shared_ptr<pdf> > &Sources );

        //! Set support points from rectangular grid
        void set_support ( rectangular_support &Sup );

        //! Set support points from dicrete grid
        void set_support ( discrete_support &Sup ) {
                Npoints = Sup.points();
                eSmp.set_parameters ( Sup._Spoints() );
                eSmp.validate();
        }


        //! set debug file
        void set_debug_file ( const string fname ) {
                if ( DBG ) delete dbg_file;
                dbg_file = new it_file ( fname );
                DBG = ( dbg_file != 0 );
        }

        //! Set internal parameters used in approximation
        void set_method ( MERGER_METHOD MTH = DFLT_METHOD, double beta0 = DFLT_beta ) {
                METHOD = MTH;
                beta = beta0;
        }
        //! Set support points from a pdf by drawing N samples
        void set_support ( const epdf &overall, int N ) {
                eSmp.set_statistics ( overall, N );
                Npoints = N;
        }

        //! Destructor
        virtual ~merger_base() {
                for ( int i = 0; i < Nsources; i++ ) {
                        delete dls ( i );
                        delete zdls ( i );
                }
                if ( DBG ) delete dbg_file;
        };
        //!@}

        //! \name Mathematical operations
        //!@{

        //!Merge given sources in given points
        virtual void merge ();

        //! Merge log-likelihood values in points using method specified by parameter METHOD
        vec merge_points ( mat &lW );


        //! sample from merged density
//! weight w is a
        vec mean() const;

        mat covariance() const;

        vec variance() const;

        //! Compute log-probability of argument \c val
        virtual double evallog ( const vec &val ) const NOT_IMPLEMENTED(0);

        //! Returns a sample, \f$ x \f$ from density \f$ f_x()\f$
        virtual vec sample() const NOT_IMPLEMENTED(0);

        //!@}

        //! \name Access to attributes
        //! @{

        //! Access function
        eEmp& _Smp() {
                return eSmp;
        }

        //! load from setting
        void from_setting ( const Setting& set );
        
        void to_setting  (Setting  &set) const ;

        void validate() ;
        //!@}
};
UIREGISTER ( merger_base );
SHAREDPTR ( merger_base );

//! Merger using importance sampling with mixture proposal density
class merger_mix : public merger_base {
protected:
        //!Internal mixture of EF models
        MixEF Mix;
        //!Number of components in a mixture
        int Ncoms;
        //! coefficient of resampling [0,1]
        double effss_coef;
        //! stop after niter iterations
        int stop_niter;

        //! default value for Ncoms
        static const int DFLT_Ncoms;
        //! default value for efss_coef;
        static const double DFLT_effss_coef;

public:
        //!\name Constructors
        //!@{
        merger_mix () : Ncoms ( 0 ), effss_coef ( 0 ), stop_niter ( 0 ) { }

        merger_mix ( const Array<shared_ptr<pdf> > &S ) :
                        Ncoms ( 0 ), effss_coef ( 0 ), stop_niter ( 0 ) {
                set_sources ( S );
        }

        //! Set sources and prepare all internal structures
        void set_sources ( const Array<shared_ptr<pdf> > &S ) {
                merger_base::set_sources ( S );
                //Nsources = S.length();
        }

        //! Set internal parameters used in approximation
        void set_parameters ( int Ncoms0 = DFLT_Ncoms, double effss_coef0 = DFLT_effss_coef ) {
                Ncoms = Ncoms0;
                effss_coef = effss_coef0;
        }
        //!@}

        //! \name Mathematical operations
        //!@{

        //!Merge values using mixture approximation
        void merge ();

        //! sample from the approximating mixture
        vec sample () const {
                return Mix.posterior().sample();
        }
        //! loglikelihood computed on mixture models
        double evallog ( const vec &yt ) const {
                vec dtf = ones ( yt.length() + 1 );
                dtf.set_subvector ( 0, yt );
                return Mix.logpred ( dtf, vec(0) );
        }
        //!@}

        //!\name Access functions
        //!@{
//! Access function
        MixEF& _Mix() {
                return Mix;
        }
        //! Access function
        emix* proposal() {
                emix* tmp = Mix.epredictor();
                tmp->set_rv ( rv );
                return tmp;
        }
        //! from_settings
        void from_setting ( const Setting& set );
        void    to_setting  (Setting  &set) const;
        void validate();

        //! @}

};
UIREGISTER ( merger_mix );
SHAREDPTR ( merger_mix );

}

#endif // MER_H