search_ranking.hpp

Go to the documentation of this file.

#ifndef FSTSEARCHRANKING_H
#define FSTSEARCHRANKING_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>
#ifdef FST_THREADED
#include <mutex>
#endif
#include <iostream>
#include <sstream>
#include <list>
#include "error.hpp"
#include "global.hpp"
#include "stopwatch.hpp"
#include "search.hpp"
#include "candidate_evaluator.hpp"
#include "candidate_evaluator_sequential.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 DIMTYPE, class SUBSET, class CRITERION>
class Search_Ranking : public Search<RETURNTYPE,DIMTYPE,SUBSET,CRITERION>{
public:
        typedef Search<RETURNTYPE,DIMTYPE,SUBSET,CRITERION> parent; 
        typedef std::shared_ptr<CRITERION> PCriterion;             
        typedef std::shared_ptr<SUBSET> PSubset;                   
        typedef Candidate_Evaluator<RETURNTYPE,DIMTYPE,SUBSET,CRITERION> EVALUATORENGINE; 
        typedef std::shared_ptr<EVALUATORENGINE> PEvaluatorEngine; 
        explicit Search_Ranking(PEvaluatorEngine engine=PEvaluatorEngine()):Search<RETURNTYPE,DIMTYPE,SUBSET,CRITERION>(),_engine(engine) {
                if(!_engine) _engine.reset(new Candidate_Evaluator_Sequential<RETURNTYPE,DIMTYPE,SUBSET,CRITERION>());
                notify("Search_Ranking constructor.");
        }
        virtual ~Search_Ranking() {notify("Search_Ranking destructor.");}
 
        // creates FEATURELIST, must be called before get*Feature() and search()
        virtual bool evaluate_individuals(const DIMTYPE n, const PCriterion crit, std::ostream& os=std::cout) = 0; 
 
        // NOTE: crit is expected to be already initialize()d before use here
        virtual bool search(const DIMTYPE target_d, RETURNTYPE &result, const PSubset sub, const PCriterion crit, std::ostream& os=std::cout) override;
 
        bool getFirstFeature(RETURNTYPE &value, DIMTYPE &feature) const; 
        bool getNextFeature(RETURNTYPE &value, DIMTYPE &feature) const; 
 
  virtual std::ostream& print(std::ostream& os) const override {os << "Search_Ranking() abstract class"; return os;};
protected:
        PEvaluatorEngine _engine; 
        typedef struct {
                DIMTYPE feature;    
                RETURNTYPE critval; 
        } OneFeature;
        typedef std::list<OneFeature> FEATURELIST; 
        FEATURELIST bifs; 
private:
        mutable typename FEATURELIST::const_iterator get_iter; 
#ifdef FST_THREADED
        mutable std::mutex get_iter_mutex; 
#endif
};
 
template<class RETURNTYPE, typename DIMTYPE, class SUBSET, class CRITERION>
bool Search_Ranking<RETURNTYPE,DIMTYPE,SUBSET,CRITERION>::getFirstFeature(RETURNTYPE &value, DIMTYPE &feature) const
{
#ifdef FST_THREADED
        std::unique_lock<std::mutex> lock(get_iter_mutex);
#endif
        get_iter = bifs.begin();
        if(get_iter!=bifs.end()) {
                value=(*get_iter).critval;
                feature=(*get_iter).feature;
                get_iter++;
                return true;
        } else return false;
}
 
template<class RETURNTYPE, typename DIMTYPE, class SUBSET, class CRITERION>
bool Search_Ranking<RETURNTYPE,DIMTYPE,SUBSET,CRITERION>::getNextFeature(RETURNTYPE &value, DIMTYPE &feature) const
{
#ifdef FST_THREADED
        std::unique_lock<std::mutex> lock(get_iter_mutex);
#endif
        if(get_iter!=bifs.end()) {
                value=(*get_iter).critval;
                feature=(*get_iter).feature;
                get_iter++;
                return true;
        } else return false;
}
 
template<class RETURNTYPE, typename DIMTYPE, class SUBSET, class CRITERION>
bool Search_Ranking<RETURNTYPE,DIMTYPE,SUBSET,CRITERION>::search(const DIMTYPE target_d, RETURNTYPE &result, const PSubset sub, const PCriterion crit, std::ostream& os) // returns found subset + criterion value
{
        StopWatch swatch;
        notify("Search_Ranking::search().");
        bool track=parent::result_tracker_active(); if(track) parent::_tracker->set_output_detail(parent::get_output_detail());
        assert(sub);
        assert(crit);
        assert(sub->get_n()>0);
        assert(target_d<sub->get_n());
        DIMTYPE _n=sub->get_n();
 
        if(parent::output_normal()) {
                msgbuf sos; 
                sos << "---------------------------------------" << std::endl;
                sos << "Starting " << *this << std::endl;
                sos << "with Criterion: " << *crit << std::endl;
                if(target_d==0) sos << "Subset size to be optimized." << std::endl; else sos << "Target subset size set to: " << target_d << std::endl;
                sos << std::endl << std::flush;
                this->report(os,sos);
        }
 
        if(!evaluate_individuals(_n,crit,os)) return false;
 
        std::shared_ptr<SUBSET> tempsub(new SUBSET(_n));
        typename FEATURELIST::const_iterator iter;
        DIMTYPE i;
        if(target_d>0) { // return subset of size target_d
                sub->deselect_all();
                for(iter=bifs.begin(),i=0; iter!=bifs.end() && i<target_d; iter++,i++) sub->select((*iter).feature);
                if(!crit->evaluate(result,sub)) return false;
                if(track) parent::_tracker->add(result,sub);
        }
        else { // find best dimensionality
                tempsub->deselect_all();
                sub->deselect_all();
                assert(bifs.begin()!=bifs.end());
                assert(_engine);
 
                // per-candidate work: track, keep best, report progress - fired in
                // candidate (i.e., growing-subset-size) order by either engine; the
                // sequential one fires it interleaved with the evaluations themselves
                bool first=true;
                RETURNTYPE best=RETURNTYPE();
                typename EVALUATORENGINE::ResultCallback on_result=[&](const RETURNTYPE cval, const PSubset &csub, const DIMTYPE) {
                        if(track) parent::_tracker->add(cval,csub);
                        if(first || cval>best) {
                                best=cval;
                                sub->stateless_copy(*csub);
                                first=false;
                                if(parent::output_normal()) this->report_solution(os, cval, *csub, msgbuf() << "new best result="<<cval<<", " << *csub << std::endl << std::endl << std::flush);
                        } else {
                                if(parent::output_normal()) this->report_solution(os, cval, *csub, msgbuf() << "result="<<cval<<", " << *csub << std::endl << std::endl << std::flush);
                        }
                };
                _engine->initialize(crit, _n, on_result);
                for(iter=bifs.begin(); iter!=bifs.end(); iter++) {
                        tempsub->select((*iter).feature);
                        if(!_engine->add_candidate(tempsub)) return false;
                }
                if(!_engine->collect()) return false;
                result=best;
        }
        if(parent::output_normal()) {
                msgbuf sos; 
                sos << "......................................." << std::endl;
                sos << *this << " search finished. " << swatch << std::endl;
                sos << "Search result: "<< std::endl << *sub << std::endl << "Criterion value: " << result << std::endl << std::endl << std::flush;
                this->report(os,sos);
        }
        return true;
}
 
 
} // namespace
#endif // FSTSEARCHRANKING_H ///:~