seq_step_hybrid.hpp

Go to the documentation of this file.

#ifndef FSTSEARCHSEQSTEPHYBRID_H
#define FSTSEARCHSEQSTEPHYBRID_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 <sstream>
#include <list>
#include "error.hpp"
#include "global.hpp"
#include "seq_step.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 FILTERCRITERION>
class Sequential_Step_Hybrid : public Sequential_Step<RETURNTYPE,DIMTYPE,SUBSET,CRITERION>{
public:
        typedef Sequential_Step<RETURNTYPE,DIMTYPE,SUBSET,CRITERION> parent; 
        typedef std::shared_ptr<FILTERCRITERION> PFilterCriterion; 
        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; 
        Sequential_Step_Hybrid(const PFilterCriterion filtercrit, const DIMTYPE keep_perc, const DIMTYPE keep_max=1000, PEvaluatorEngine engine=PEvaluatorEngine()):Sequential_Step<RETURNTYPE,DIMTYPE,SUBSET,CRITERION>(),_engine(engine),track(false) {assert(keep_perc<=100); assert(keep_max>0); assert(filtercrit); _filtercrit=filtercrit; _keep_perc=keep_perc; _keep_max=keep_max; _listsize=0; if(!_engine) _engine.reset(new Candidate_Evaluator_Sequential<RETURNTYPE,DIMTYPE,SUBSET,CRITERION>()); notify("Sequential_Step_Hybrid constructor.");}
        virtual ~Sequential_Step_Hybrid() {notify("Sequential_Step_Hybrid destructor.");}
 
        void set_prefiltering_limits(const DIMTYPE keep_perc, const DIMTYPE keep_max) {assert(keep_perc<=100); assert(keep_max>0); _keep_perc=keep_perc; _keep_max=keep_max;} 
        DIMTYPE get_prefiltering_perc() const {return _keep_perc;} 
        DIMTYPE get_prefiltering_max() const {return _keep_max;}   
 
        // NOTE: crit is expected to be already initialize()d before use here
        inline bool evaluate_candidates(RETURNTYPE &result, const PSubset sub, const PCriterion crit, const DIMTYPE _generalization_level=1, std::ostream& os=std::cout) override; 
 
        virtual std::ostream& print(std::ostream& os) const override; 
protected:
        inline bool filter_candidates(const PSubset sub, const DIMTYPE _generalization_level, std::ostream& os); 
        inline bool test_candidate(const PSubset sub); 
 
        PEvaluatorEngine _engine; 
        PFilterCriterion _filtercrit; 
        DIMTYPE _keep_perc; 
        DIMTYPE _keep_max; 

        class SubsetCandidate {
        public:
                SubsetCandidate(const RETURNTYPE value, const PSubset sub) : _value(value), _sub(new SUBSET(*sub)) {} 
                const RETURNTYPE _value; 
                const PSubset _sub;      
        };
        typedef std::list<SubsetCandidate> CANDIDATELIST; 
 
        DIMTYPE _listsize; 
        CANDIDATELIST _filterlist; 
        typename CANDIDATELIST::iterator iter; 
 
private:
        bool track; 
};
 
template<class RETURNTYPE, typename DIMTYPE, class SUBSET, class CRITERION, class FILTERCRITERION>
std::ostream& Sequential_Step_Hybrid<RETURNTYPE,DIMTYPE,SUBSET,CRITERION,FILTERCRITERION>::print(std::ostream& os) const
{
        if(_engine->is_threaded()) os << "Sequential_Step_Hybrid(keep_perc="<<_keep_perc<<", max="<<_keep_max<<", threads="<<_engine->get_max_threads()<<")";
        else os << "Sequential_Step_Hybrid(keep_perc="<<_keep_perc<<", max="<<_keep_max<<")";
        if(_filtercrit) os << " with filter " << *_filtercrit;
        if(parent::result_tracker_active()) os << " with " << *parent::_tracker;
        return os;
}
 
template<class RETURNTYPE, typename DIMTYPE, class SUBSET, class CRITERION, class FILTERCRITERION>
bool Sequential_Step_Hybrid<RETURNTYPE,DIMTYPE,SUBSET,CRITERION,FILTERCRITERION>::test_candidate(const PSubset sub)
{
        assert(sub);
        assert(_filtercrit);
        RETURNTYPE val;
        DIMTYPE _idx=0;
        assert(sub->get_d()!=0);
        // the filter criterion's values are deliberately NOT fed to the result tracker: the tracker
        // would then hold values of two different criteria, which are not comparable with each other
        if(!_filtercrit->evaluate(val,sub)) return false;
        for(iter=_filterlist.begin(); _idx<_listsize && iter!=_filterlist.end() && (val<iter->_value || (val==iter->_value && sub->get_d()>=iter->_sub->get_d())); iter++) {++_idx;}
        if(_idx<_listsize) { // candidate good enough to be inserted
                _filterlist.insert(iter,SubsetCandidate(val,sub));
                if(_filterlist.size()>_listsize) _filterlist.pop_back();
        }
        return true;
}
 
template<class RETURNTYPE, typename DIMTYPE, class SUBSET, class CRITERION, class FILTERCRITERION>
bool Sequential_Step_Hybrid<RETURNTYPE,DIMTYPE,SUBSET,CRITERION,FILTERCRITERION>::filter_candidates(const PSubset sub, const DIMTYPE _generalization_level, std::ostream& os)
{
        assert(sub);
        _filterlist.clear();
        assert(_keep_perc<=100);
        assert(_keep_max>0);
        assert(_generalization_level>=1 && _generalization_level<=sub->get_n());
        
        // determine maximum _filterlist size: keep_perc percent of the candidates, capped at
        // keep_max, but never less than one - a shortlist of zero would leave the main criterion
        // nothing to evaluate, so keep_perc==0 means "shortlist the single best by filtercrit"
        _listsize=DIMTYPE(((double)_keep_perc/100.0)*sub->getNoOfCandidateSubsets(_generalization_level,false/*reverse*/));
        if(_keep_max<_listsize) _listsize=_keep_max;
        if(_listsize==0) _listsize=1;
        
        // first build candidate list _filterlist (pre-filter using _filtercrit criterion)
        bool b=sub->getFirstCandidateSubset(_generalization_level,false/*reverse*/); if(!b) return false; // no candidate subsets can be traversed for whatever reason
        if(!test_candidate(sub)) return false;
        b=sub->getNextCandidateSubset(); // evaluate the remaining candidates
        while(b) {
                if(!test_candidate(sub)) return false;
                b=sub->getNextCandidateSubset();
        }
        assert(_filterlist.size()>0);
        if(parent::output_detailed()) {
                std::ostringstream sos; 
                sos << "candidate list of "<<_filterlist.size() << ":" << std::endl;
                for(iter=_filterlist.begin(); iter!=_filterlist.end(); iter++) {sos << iter->_value << " ~ " << *(iter->_sub) << std::endl;}
                sos << std::endl << std::flush;
                syncout::print(os,sos);
        }
        return true;
}
 
template<class RETURNTYPE, typename DIMTYPE, class SUBSET, class CRITERION, class FILTERCRITERION>
bool Sequential_Step_Hybrid<RETURNTYPE,DIMTYPE,SUBSET,CRITERION,FILTERCRITERION>::evaluate_candidates(RETURNTYPE &result, const PSubset sub, const PCriterion crit, const DIMTYPE _generalization_level, std::ostream& os)
{
        assert(sub);
        assert(crit);
        assert(_filtercrit);
        assert(_keep_perc<=100);
        assert(_keep_max>0);
        assert(_generalization_level>=1 && _generalization_level<=sub->get_n());
        track=parent::result_tracker_active();
 
        if(!filter_candidates(sub,_generalization_level,os)) {if(parent::output_normal()) {std::ostringstream sos; sos << "FAILURE filter_candidates() sub=" << *sub << std::endl << std::endl << std::flush; syncout::print(os,sos);} return false;}
        assert(_filterlist.size()>0);
 
        if(_keep_perc==0) { // shortlist of one: no main-criterion SELECTION, but the main criterion
                            // is still evaluated on that candidate and its value is what we return
                assert(_filterlist.size()>0);
                sub->stateless_copy( *((_filterlist.begin())->_sub) );
                assert(sub->get_d()!=0);
                if(!crit->evaluate(result,sub)) {if(parent::output_normal()) {std::ostringstream sos; sos << "FAILURE crit->eval() sub=" << *(sub) << std::endl << std::endl << std::flush; syncout::print(os,sos);} return false;}
                if(track) parent::_tracker->add(result,sub);
                return true;
        }
 
        // main-criterion phase through the injected engine (sequential in-line by default,
        // thread-pooled when constructed with Candidate_Evaluator_Threaded); the engine fires the
        // per-result callback in candidate (add) order and getBestResult() breaks ties by earliest
        // candidate, so results and tracker feed are the same for any thread count
        assert(_engine);
        typename EVALUATORENGINE::ResultCallback on_result;
        if(track) {
                typename parent::PResultTracker tracker=parent::_tracker;
                on_result=[tracker](const RETURNTYPE val, const PSubset &csub, const DIMTYPE) {tracker->add(val,csub);};
        }
        _engine->initialize(crit,(DIMTYPE)_filterlist.size(),on_result);
        for(iter=_filterlist.begin();iter!=_filterlist.end();iter++) {
                if(!_engine->add_candidate(iter->_sub)) {if(parent::output_normal()) {std::ostringstream sos; sos << "FAILURE crit->eval() sub=" << *(iter->_sub) << std::endl << std::endl << std::flush; syncout::print(os,sos);} return false;}
        }
        PSubset psub;
        DIMTYPE dummyfeature;
        if(!_engine->getBestResult(result,psub,dummyfeature)) {if(parent::output_normal()) {std::ostringstream sos; sos << "FAILURE crit->eval() (no candidate evaluated)" << std::endl << std::endl << std::flush; syncout::print(os,sos);} return false;}
        assert(psub);
        sub->stateless_copy(*psub);
        assert(sub->get_d()!=0);
 
        return true;
}
 
 
} // namespace
#endif // FSTSEARCHSEQSTEPHYBRID_H ///:~