criterion_normal.hpp

Go to the documentation of this file.

#ifndef FSTCRITERIONNORMAL_H
#define FSTCRITERIONNORMAL_H
 /* 
=========================================================================
Copyright and license:
  * FST4 software (with the exception of any bundled or externally linked
    third-party components) is Copyright (C) 2000-present Institute of
    Information Theory and Automation of the Czech Academy of Sciences (UTIA).
  * FST4 is free software: you can redistribute it and/or modify it under
    the terms of the GNU Affero General Public License as published by the
    Free Software Foundation, version 3. The full text of the license is in
    the file LICENSE in the distribution root and at
    https://www.gnu.org/licenses/agpl-3.0.html.
  * FST4 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 Affero General Public
    License for more details.
  * Closed-source use without the AGPL's copyleft obligations requires a
    commercial license from UTIA; in case of interest write to
    utia@utia.cas.cz. LICENSING.md in the distribution root explains both
    options, the contributor license agreement that every contribution
    requires, and the contacts (technical questions and pull requests:
    somol@utia.cas.cz, with "FST" in the subject line).
========================================================================== */
 
#include <memory>
#include <cassert>
#include <iostream>
#include <cmath>
#include <string>
#include "error.hpp"
#include "global.hpp"
#include "criterion.hpp"
#include "model_normal.hpp"
#include "indexed_vector.hpp"
#include "indexed_matrix.hpp"
 
/*============== Template parameter type naming conventions ==============
--------- Numeric types: -------------------------------------------------
DATATYPE - data sample values - usually real numbers (but may be integers
          in text processing etc.)
REALTYPE - must be real numbers - for representing intermediate results of 
          calculations like mean, covariance etc.
IDXTYPE - index values for enumeration of data samples - (nonnegative) integers, 
          extent depends on numbers of samples in data
DIMTYPE - index values for enumeration of features (dimensions), or classes (not 
          class sizes) - (nonnegative) integers, usually lower extent than IDXTYPE, 
          but be aware of expressions like _classes*_features*_features ! 
          in linearized representations of feature matrices for all classes
BINTYPE - feature selection marker type - represents ca. <10 different feature 
          states (selected, deselected, sel./desel. temporarily 1st nested loop, 2nd...)
RETURNTYPE - criterion value: real value, but may be extended in future to support 
          multiple values 
--------- Class types: ---------------------------------------------------
SUBSET       - class of class type Subset 
CLASSIFIER   - class implementing interface defined in abstract class Classifier 
EVALUATOR    - class implementing interface defined in abstract class Sequential_Step 
DISTANCE     - class implementing interface defined in abstract class Distance 
DATAACCESSOR - class implementing interface defined in abstract class Data_Accessor 
INTERVALCONTAINER - class of class type Data_Intervaller 
CONTAINER    - STL container of class type Data_Interval  
========================================================================== */
 
namespace FST {

template<class RETURNTYPE, typename DATATYPE, typename REALTYPE, typename IDXTYPE, typename DIMTYPE, class SUBSET, class DATAACCESSOR>
class Criterion_Normal : public Criterion_Filter<RETURNTYPE,SUBSET> { // abstract class
public:
        typedef std::shared_ptr<DATAACCESSOR> PDataAccessor;  
        typedef std::shared_ptr<SUBSET> PSubset;              
        Criterion_Normal();
        virtual ~Criterion_Normal() {notify("Criterion_Normal destructor.");}
        virtual bool initialize(PDataAccessor da);
 
        virtual bool evaluate(RETURNTYPE &result, const PSubset sub) override; 

        virtual bool is_monotonic() const override {return true;}
 
        DIMTYPE get_n() const {assert(_model); return _model->get_n();} 
        DIMTYPE get_d() const {assert(_model); return _model->get_d();} 
 
        virtual std::ostream& print(std::ostream& os) const override {os << criterion_name() << "()"; return os;}
protected:
        Criterion_Normal(const Criterion_Normal& cn);
protected:
        // hooks for the concrete two-class normal criteria, called by the template methods above
        virtual const char* criterion_name() const =0; 
        virtual void allocate_buffers() =0; 
        virtual void update_derived_model() =0; 
        virtual bool evaluate_narrowed(RETURNTYPE &result, const PSubset sub) =0;

        void alloc_vector(std::unique_ptr<Indexed_Vector<DATATYPE,DIMTYPE,SUBSET> > &v) {
                if(!v) v.reset(new Indexed_Vector<DATATYPE,DIMTYPE,SUBSET>);
                if(get_n()>v->get_n()) v->reset(get_n());
        }

        template<typename MATRIXVALUETYPE>
        void alloc_matrix(std::unique_ptr<Indexed_Matrix<MATRIXVALUETYPE,DIMTYPE,SUBSET> > &m, const bool LUstorage=false) {
                if(!m) m.reset(new Indexed_Matrix<MATRIXVALUETYPE,DIMTYPE,SUBSET>(get_n(),LUstorage));
                if(get_n()>m->get_n()) m->reset(get_n(),LUstorage);
        }
protected:
        std::unique_ptr<Model_Normal<DATATYPE,REALTYPE,IDXTYPE,DIMTYPE,SUBSET,DATAACCESSOR> > _model; 
        std::unique_ptr<Indexed_Vector<DATATYPE,DIMTYPE,SUBSET> > _meandif; 
};
 
template<class RETURNTYPE, typename DATATYPE, typename REALTYPE, typename IDXTYPE, typename DIMTYPE, class SUBSET, class DATAACCESSOR>
Criterion_Normal<RETURNTYPE,DATATYPE,REALTYPE,IDXTYPE,DIMTYPE,SUBSET,DATAACCESSOR>::Criterion_Normal(const Criterion_Normal& cn)
{
        notify("Criterion_Normal copy-constructor.");
        if(cn._model) _model.reset(new Model_Normal<DATATYPE,REALTYPE,IDXTYPE,DIMTYPE,SUBSET,DATAACCESSOR>(*cn._model));
        if(cn._meandif) _meandif.reset(new Indexed_Vector<DATATYPE,DIMTYPE,SUBSET>(*cn._meandif));
}
 
template<class RETURNTYPE, typename DATATYPE, typename REALTYPE, typename IDXTYPE, typename DIMTYPE, class SUBSET, class DATAACCESSOR>
Criterion_Normal<RETURNTYPE,DATATYPE,REALTYPE,IDXTYPE,DIMTYPE,SUBSET,DATAACCESSOR>::Criterion_Normal()
{
        notify("Criterion_Normal constructor.");
        _model.reset(new Model_Normal<DATATYPE,REALTYPE,IDXTYPE,DIMTYPE,SUBSET,DATAACCESSOR>);
}
 
template<class RETURNTYPE, typename DATATYPE, typename REALTYPE, typename IDXTYPE, typename DIMTYPE, class SUBSET, class DATAACCESSOR>
bool Criterion_Normal<RETURNTYPE,DATATYPE,REALTYPE,IDXTYPE,DIMTYPE,SUBSET,DATAACCESSOR>::initialize(PDataAccessor da)
{
        if(da->getNoOfClasses()!=2) throw fst_error(std::string(criterion_name())+"() defined for two-class problems only.");
        notify("Criterion_Normal::initialize().");
        assert(_model);
        _model->learn(da);
 
        alloc_vector(_meandif);
        _meandif->copy_raw(_model->get_mean()[0]);
        _meandif->subtract_raw(_model->get_mean()[1]);
 
        allocate_buffers();
        update_derived_model();
        return true;
}
 
template<class RETURNTYPE, typename DATATYPE, typename REALTYPE, typename IDXTYPE, typename DIMTYPE, class SUBSET, class DATAACCESSOR>
bool Criterion_Normal<RETURNTYPE,DATATYPE,REALTYPE,IDXTYPE,DIMTYPE,SUBSET,DATAACCESSOR>::evaluate(RETURNTYPE &result, const PSubset sub)
{
        notify("Criterion_Normal::evaluate().");
        assert(_model);
        assert(get_n()>0);
        assert(_meandif);
        assert(get_n()==_meandif->get_n());
        assert(sub);
 
        if(sub->get_d_raw()==0) return false;
 
        _model->narrow_to(sub);
        _meandif->narrow_to(sub);
        if(!evaluate_narrowed(result,sub)) return false;
        // A non-finite value (NaN or an infinity) means the normal-model arithmetic broke down
        // on this subset -- an inverse or determinant of a numerically singular covariance. It
        // must never reach a search: NaN compares false against everything, so a search would
        // silently accept or reject candidates on garbage and still report success.
        if(!std::isfinite(result))
                throw FST::fst_error(std::string(criterion_name())+"::evaluate: non-finite criterion value on the evaluated subset (numerically singular class covariance; reduce the subset size, drop constant or collinear features, or use more training data)");
        return true;
}
 
 
} // namespace
#endif // FSTCRITERIONNORMAL_H ///:~