search_branch_and_bound_improved.hpp

Go to the documentation of this file.

#ifndef FSTSEARCHBRANCHANDBOUNDIMPROVED_H
#define FSTSEARCHBRANCHANDBOUNDIMPROVED_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 "search_branch_and_bound.hpp"
#include "error.hpp"
#include "global.hpp"
#include "result_tracker.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_Branch_And_Bound_Improved : public Search_Branch_And_Bound<RETURNTYPE,DIMTYPE,SUBSET,CRITERION>{
public:
        typedef Search_Branch_And_Bound<RETURNTYPE,DIMTYPE,SUBSET,CRITERION> parent; 
        typedef typename parent::PCriterion PCriterion; 
        typedef typename parent::PSubset PSubset; 
        typedef typename parent::PNode PNode; 
        typedef typename parent::Node Node; 
        typedef typename parent::NodeType NodeType; 
        typedef typename parent::PEvaluatorEngine PEvaluatorEngine; 
        explicit Search_Branch_And_Bound_Improved(PEvaluatorEngine engine=PEvaluatorEngine()):Search_Branch_And_Bound<RETURNTYPE,DIMTYPE,SUBSET,CRITERION>(engine) {notify("Search_Branch_And_Bound_Improved constructor.");} 
        virtual ~Search_Branch_And_Bound_Improved() {notify("Search_Branch_And_Bound_Improved destructor.");}
 
        // for search() implementation see parent class
 
        virtual std::ostream& print(std::ostream& os) const override {
                if(parent::get_engine()->is_threaded()) os << "Improved Branch & Bound (IBB)  [Search_Branch_And_Bound_Improved(threads="<<parent::get_engine()->get_max_threads()<<")]";
                else os << "Improved Branch & Bound (IBB)  [Search_Branch_And_Bound_Improved()]";
                return os;
        }
 
protected:
        // the following may be overriden in descendant Branch and Bound specialization classes
        virtual void initialize(const DIMTYPE d, const DIMTYPE n, const PCriterion crit) override {} 
        virtual void pre_evaluate_availables() override; 
        virtual void post_process_tree_level() override{} 
        virtual bool cut_possible() override; 
};
 
template<class RETURNTYPE, typename DIMTYPE, class SUBSET, class CRITERION>
void Search_Branch_And_Bound_Improved<RETURNTYPE,DIMTYPE,SUBSET,CRITERION>::pre_evaluate_availables()
{
        assert(parent::get_criterion());
        assert(parent::get_engine());
        const PSubset &currentset=parent::get_currentset();
        // pre-evaluate available features before next tree level construction;
        // computed values are written back into the corresponding _available node,
        // keyed by the feature tag (Node::feature indexes _available by position)
        typename parent::EVALUATORENGINE::ResultCallback on_result=[this](const RETURNTYPE value, const PSubset&, const DIMTYPE feat) {
                PNode avail;
                if(this->getAvailable(feat,avail)) {
                        avail->value=value;
                        avail->type=parent::COMPUTED;
                }
        };
        parent::get_engine()->initialize(parent::get_criterion(), parent::get_n(), on_result);
        PNode avail;
        for(bool got=this->getFirstAvailable(avail);got;got=this->getNextAvailable(avail))
        {
                assert(currentset->selected_raw(avail->feature));
                currentset->deselect_raw(avail->feature);
                if(!parent::get_engine()->add_candidate(currentset,avail->feature)) throw FST::fst_error("Criterion evaluation failure.");
                currentset->select_raw(avail->feature);
        }
        // fail as loudly as the sequential path's add_candidate throw above: a criterion
        // exception thrown on a worker thread is rethrown right here on the master, and a
        // failed evaluation marks the whole batch failed - in which case no on_result
        // callback fired, every available stays UNKNOWN with a stale value, and the level
        // sort-in would feed cut_possible() garbage (it expects COMPUTED nodes)
        if(!parent::get_engine()->collect()) throw FST::fst_error("Criterion evaluation failure.");
}
 
template<class RETURNTYPE, typename DIMTYPE, class SUBSET, class CRITERION>
bool Search_Branch_And_Bound_Improved<RETURNTYPE,DIMTYPE,SUBSET,CRITERION>::cut_possible()
{
        if(parent::is_bound_valid()) {
                // the node's value is always COMPUTED here: IBB evaluates every available feature
                // in pre_evaluate_availables() before the level is built, so - unlike in FBB - no
                // node can reach this point carrying a merely predicted value
                Node &currentnode=parent::get_current_node(); assert(currentnode.type==parent::COMPUTED);
                if(currentnode.value<=parent::get_bound_value()) {
                        return true;
                }
        }
        return false;
}
 
} // namespace
#endif // FSTSEARCHBRANCHANDBOUNDIMPROVED_H ///:~