data_intervaller.hpp

Go to the documentation of this file.

#ifndef FSTDATAINTERVALLER_H
#define FSTDATAINTERVALLER_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 <algorithm>
#include <iostream>
#include <sstream>
#include <vector> // for blockiter - array of iterators indexed by loopdepth
#include "error.hpp"
#include "global.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<typename IDXTYPE>
struct Data_Interval {
        IDXTYPE startidx; 
        IDXTYPE count;    
};
 
template <class CONTAINER, typename IDXTYPE>
class Data_Intervaller;
 
template <class CONTAINER, typename IDXTYPE>
std::ostream& operator<<(std::ostream& os, const Data_Intervaller<CONTAINER,IDXTYPE>& ia);

template<class CONTAINER, typename IDXTYPE>
class Data_Intervaller : public CONTAINER {
public:
        Data_Intervaller() {notify("Data_Intervaller constructor.");};
        Data_Intervaller(const Data_Intervaller& tin);
        virtual ~Data_Intervaller() {notify("Data_Intervaller destructor.");};
        Data_Interval<IDXTYPE>* getFirstBlock(const unsigned int loopdepth=0); 
        Data_Interval<IDXTYPE>* getNextBlock(const unsigned int loopdepth=0); 
        bool check_validity(const IDXTYPE maxidx);
        IDXTYPE sum();  
        IDXTYPE max_idx();      
        void reduce(const std::shared_ptr<Data_Intervaller<CONTAINER,IDXTYPE> > reducer, std::shared_ptr<Data_Intervaller<CONTAINER,IDXTYPE> > target);
        friend std::ostream& operator<< <>(std::ostream& os, const Data_Intervaller<CONTAINER,IDXTYPE>& ia);
private:
        typedef typename Data_Intervaller<CONTAINER,IDXTYPE>::iterator TCI; 
        std::vector<TCI> blockiter; 
};
 
template<class CONTAINER, typename IDXTYPE>
Data_Intervaller<CONTAINER,IDXTYPE>::Data_Intervaller(const Data_Intervaller& tin)
{
        notify("Data_Intervaller copy constructor.");
        this->clear();
        for(typename Data_Intervaller<CONTAINER,IDXTYPE>::const_iterator iter=tin.begin();iter!=tin.end();iter++) this->push_back(*iter);
        // blockiter deliberately NOT copied: it holds iterators into the SOURCE container, which
        // would be invalid here — the copy starts with no active block loops; getFirstBlock()
        // (re)initializes the cursor of whichever loopdepth is used next
}

template<class CONTAINER, typename IDXTYPE>
std::ostream& operator<<(std::ostream& os, const Data_Intervaller<CONTAINER,IDXTYPE>& ia) {
        for(typename Data_Intervaller<CONTAINER,IDXTYPE>::const_iterator iter=ia.begin();iter!=ia.end();iter++) os << "si:" << iter->startidx << ", c:" << iter->count << std::endl;
        return os;
}
 
template<class CONTAINER, typename IDXTYPE>
Data_Interval<IDXTYPE>* Data_Intervaller<CONTAINER,IDXTYPE>::getFirstBlock(const unsigned int loopdepth)
{
        if(blockiter.size()<=loopdepth) blockiter.resize(loopdepth+1);
        blockiter[loopdepth]=this->begin();
        if(blockiter[loopdepth]!=this->end()) return &(*blockiter[loopdepth]);
        else return nullptr;
}
 
template<class CONTAINER, typename IDXTYPE>
Data_Interval<IDXTYPE>* Data_Intervaller<CONTAINER,IDXTYPE>::getNextBlock(const unsigned int loopdepth)
{
        // NOTE: getNextBlock() must be preceded by getFirstBlock() with the same loopdepth value, otherwise the behaviour is undefined
        assert(loopdepth<blockiter.size());
        ++blockiter[loopdepth];
        if(blockiter[loopdepth]!=this->end()) return &(*blockiter[loopdepth]);
        else return nullptr;
}
 
template<class CONTAINER, typename IDXTYPE>
bool Data_Intervaller<CONTAINER,IDXTYPE>::check_validity(const IDXTYPE maxidx)
{
        if(this->empty()) {{std::ostringstream sos; sos << "Data_Intervaller is empty" << std::endl; syncout::print(std::cerr,sos);} return false;}
        TCI iter=this->begin();
        IDXTYPE pivot=iter->startidx+iter->count;
        if(iter->startidx<0 || (maxidx>0 && (pivot>maxidx)) ) {{std::ostringstream sos; sos <<"first is wrong"<<std::endl; syncout::print(std::cerr,sos);} return false;} // the first interval reaches outside <0,maxidx>
        iter++;
        while(iter!=this->end())
        {
                if(iter->startidx<pivot) {{std::ostringstream sos; sos <<"iter->startidx="<<iter->startidx<<", pivot="<<pivot<<std::endl; syncout::print(std::cerr,sos);} return false;}
                pivot=iter->startidx+iter->count;
                if(maxidx>0 && (pivot>maxidx)) {{std::ostringstream sos; sos <<"startidx+count>maxidx"<<std::endl; syncout::print(std::cerr,sos);} return false;}
                ++iter;
        }
        return true;
}
 
template<class CONTAINER, typename IDXTYPE>
IDXTYPE Data_Intervaller<CONTAINER,IDXTYPE>::sum()
{
        IDXTYPE cnt=0;
        for(TCI iter=this->begin();iter!=this->end();iter++) cnt+=iter->count;
        return cnt;
}
 
template<class CONTAINER, typename IDXTYPE>
IDXTYPE Data_Intervaller<CONTAINER,IDXTYPE>::max_idx()
{
        IDXTYPE mx=0;
        for(TCI iter=this->begin();iter!=this->end();iter++) if(iter->count>0 && iter->startidx+iter->count-1>mx) mx=iter->startidx+iter->count-1; // count==0: startidx+count-1 underflows unsigned IDXTYPE
        return mx;
}
 
template<class CONTAINER, typename IDXTYPE>
void Data_Intervaller<CONTAINER,IDXTYPE>::reduce(const std::shared_ptr<Data_Intervaller<CONTAINER,IDXTYPE> > reducer, std::shared_ptr<Data_Intervaller<CONTAINER,IDXTYPE> > target)
{
        try{
                assert(sum()>reducer->max_idx()); // the reducer indexes INTO this list: its largest index must be below this list's sample count
                target->clear();
                typename Data_Intervaller<CONTAINER,IDXTYPE>::const_iterator rediter=reducer->begin();
                IDXTYPE Mbottom=0;
                for(TCI iter=this->begin();iter!=this->end();iter++) {
                        if((*iter).count==0) continue; // empty interval: Mtop below would underflow unsigned IDXTYPE
                        bool stop=false;
                        while((!stop) && (rediter!=reducer->end())) {
                                if((*rediter).count==0) {rediter++; continue;} // empty interval: Rtop below would underflow unsigned IDXTYPE
                                IDXTYPE Rbottom=(*rediter).startidx;
                                IDXTYPE Rtop=Rbottom+(*rediter).count-1;
                                IDXTYPE MTRUEbottom=(*iter).startidx;
                                IDXTYPE Mtop=Mbottom+(*iter).count-1;
                                if(!(Rtop<Mbottom || Rbottom>Mtop)) { //write intersection to target
                                        IDXTYPE ISCbottom=Rbottom; if(Rbottom<Mbottom) ISCbottom=Mbottom;
                                        IDXTYPE ISCtop=Rtop; if(Rtop>Mtop) ISCtop=Mtop;
                                        Data_Interval<IDXTYPE> I={MTRUEbottom+(ISCbottom-Mbottom), ISCtop-ISCbottom+1};
                                        target->push_back(I);
                                }
                                if(Rtop>=Mtop) stop=true;
                                if(Rtop<=Mtop) rediter++;
                        }
                        Mbottom+=(*iter).count;
                }
                
        } catch(...) {
                throw fst_error("Data_Intervaller::reduce() error.");
        }
}
 
 
} // namespace
#endif // FSTDATAINTERVALLER_H ///:~