distance.hpp

Go to the documentation of this file.

#ifndef FSTDISTANCE_H
#define FSTDISTANCE_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 <list>
#include <cstring> // memcpy
#include "error.hpp"
#include "global.hpp"
#include "clonable.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 DATATYPE, typename DIMTYPE, class SUBSET>
class Distance : public Clonable {
public:
        typedef std::shared_ptr<SUBSET> PSubset;                  
        Distance() : _n(0), _d(0) {}
        Distance(const Distance &d);
        virtual ~Distance() {}
        void reset(const DIMTYPE n);

        void narrow_to(const PSubset sub); // fill _index[] -> access to data is then mapped to sub-matrix
        void denarrow(); // reset _index[] -> access is reset to the full matrix
 
        DIMTYPE get_n() const {return _n;} 
        DIMTYPE get_d() const {return _d;} 

        virtual DATATYPE distance(const DATATYPE *pattern1, const DATATYPE *pattern2) =0;
 
        Distance* clone() const override =0;
        Distance* sharing_clone() const override {throw fst_error("Distance::sharing_clone() not supported, use Distance::clone() instead.");}
        Distance* stateless_clone() const override {throw fst_error("Distance::stateless_clone() not supported, use Distance::clone() instead.");}
protected:
        DIMTYPE _n;                          
        DIMTYPE _d;                          
        std::unique_ptr<DIMTYPE[]> _index;   
};
 
template<typename DATATYPE, typename DIMTYPE, class SUBSET>
Distance<DATATYPE,DIMTYPE,SUBSET>::Distance(const Distance& d) :
        _n(d._n),
        _d(d._d)
{
        notify("Distance copy-constructor.");
        if(_n>0) {_index.reset(new DIMTYPE[_n]); memcpy((void *)_index.get(),(void *)(d._index).get(),sizeof(DIMTYPE)*_n);}
}
 
template<typename DATATYPE, typename DIMTYPE, class SUBSET>
void Distance<DATATYPE,DIMTYPE,SUBSET>::reset(const DIMTYPE n)
{
        assert(n>0);
        _n=n;
        _index.reset(new DIMTYPE[_n]);
        for(DIMTYPE i=0;i<_n;i++) _index[i]=i;
        _d=_n;
}
 
template<typename DATATYPE, typename DIMTYPE, class SUBSET>
void Distance<DATATYPE,DIMTYPE,SUBSET>::narrow_to(const PSubset sub)
{
        assert(_n>=sub->get_d_raw()); // precondition: enough space to store the subset
        assert(_index);
        _d=0;
        for(DIMTYPE f : sub->selected_features()) _index[_d++]=f;
        assert(_d>0);
}
 
template<typename DATATYPE, typename DIMTYPE, class SUBSET>
void Distance<DATATYPE,DIMTYPE,SUBSET>::denarrow()
{
        assert(_index);
        for(DIMTYPE i=0;i<_n;i++) _index[i]=i;
        _d=_n;
}
 
 
} // namespace
#endif // FSTDISTANCE_H ///:~