data_splitter_cv.hpp

Go to the documentation of this file.

#ifndef FSTDATASPLITTERCV_H
#define FSTDATASPLITTERCV_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 <cstdlib>
#include <ctime>
#include <vector>
#include "error.hpp"
#include "global.hpp"
#include "data_splitter.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 {
 
// CROSS-VALIDATION

template<class INTERVALCONTAINER, typename IDXTYPE>
class Data_Splitter_CV : public Clonable_Impl<Data_Splitter_CV<INTERVALCONTAINER,IDXTYPE>,Data_Splitter<INTERVALCONTAINER,IDXTYPE>,CLONE_INHERIT,CLONE_INHERIT,CLONE_DEEP> {
public:
        typedef Clonable_Impl<Data_Splitter_CV,Data_Splitter<INTERVALCONTAINER,IDXTYPE>,CLONE_INHERIT,CLONE_INHERIT,CLONE_DEEP> parent_impl; 
        Data_Splitter_CV(const IDXTYPE _kfold) : parent_impl(), kfold(_kfold), tmpod(0) {assert(_kfold>1); notify("Data_Splitter_CV constructor.");} 
        Data_Splitter_CV(const Data_Splitter_CV& dsp) : parent_impl(dsp), kfold(dsp.kfold), tmpod(0) {notify("Data_Splitter_CV copy constructor.");} 
        virtual ~Data_Splitter_CV() {notify("Data_Splitter_CV destructor.");}
        virtual IDXTYPE getNoOfSplits() const override {return kfold;}
 
        virtual std::ostream& print(std::ostream& os) const override {os << "Data_Splitter_CV(" << kfold << ")"; return os;}
protected:
        typedef Data_Splitter<INTERVALCONTAINER,IDXTYPE> TCC; 
        // Template-method hooks: makeFirstSplit()/makeNextSplit() skeletons live in Data_Splitter
        virtual const char* splitter_name() const override {return "Data_Splitter_CV";}
        virtual bool prepareFirstSplit() override {
                tmpn.resize(TCC::csplit.size());
                tmpstartidx.resize(TCC::csplit.size());
                tmpod=kfold;
                return true;
        }
        virtual bool prepareNextSplit() override {return tmpod>0;}
        virtual void splitClassFirst(typename TCC::ClassIterator c, const unsigned int cidx) override {
                tmpstartidx[cidx]=0;
                tmpn[cidx]=(*c)->n;
 
                const IDXTYPE tcs=tmpn[cidx]/tmpod;
                Data_Interval<IDXTYPE> tri={tcs,(*c)->n-tcs};   (*c)->train->clear();   (*c)->train->push_back(tri);
                Data_Interval<IDXTYPE> tei={0,tcs};     (*c)->test->clear();    (*c)->test->push_back(tei);
 
                tmpstartidx[cidx]+=tcs;
                tmpn[cidx]-=tcs;
        }
        virtual void splitClassNext(typename TCC::ClassIterator c, const unsigned int cidx) override {
                const IDXTYPE tcs=tmpn[cidx]/tmpod;
                Data_Interval<IDXTYPE> tri={0,tmpstartidx[cidx]};       (*c)->train->clear();   (*c)->train->push_back(tri);
                if(tmpod>1) {Data_Interval<IDXTYPE> tri2={tmpstartidx[cidx]+tcs,(*c)->n-(tmpstartidx[cidx]+tcs)}; (*c)->train->push_back(tri2);}
                Data_Interval<IDXTYPE> tei={tmpstartidx[cidx],tcs};     (*c)->test->clear();    (*c)->test->push_back(tei);
 
                tmpstartidx[cidx]+=tcs;
                tmpn[cidx]-=tcs;
        }
        virtual void finishSplit() override {tmpod--;}
private:
        const IDXTYPE kfold; 
 
        IDXTYPE tmpod; 
        std::vector<IDXTYPE> tmpn; 
        std::vector<IDXTYPE> tmpstartidx; 
};
 
 
} // namespace
#endif // FSTDATASPLITTERCV_H ///:~