data_splitter_randfix.hpp

Go to the documentation of this file.

#ifndef FSTDATASPLITTERRANDFIX_H
#define FSTDATASPLITTERRANDFIX_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_randrand.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 {
 
// NOTE: this is a special-purpose modification of Data_Splitter_RandomRandom
//       that generates train data equally to Data_Splitter_RandomRandom
//       but selects always the same test data (consecutive interval at the end of each class)

template<class INTERVALCONTAINER, typename IDXTYPE, typename BINTYPE>
class Data_Splitter_TrainRandom_TestFixed : public Clonable_Impl<Data_Splitter_TrainRandom_TestFixed<INTERVALCONTAINER,IDXTYPE,BINTYPE>,Data_Splitter_RandomRandom<INTERVALCONTAINER,IDXTYPE,BINTYPE>,CLONE_INHERIT,CLONE_INHERIT,CLONE_DEEP> {
public:
        typedef Data_Splitter_RandomRandom<INTERVALCONTAINER,IDXTYPE,BINTYPE> parent; 
        typedef Clonable_Impl<Data_Splitter_TrainRandom_TestFixed,parent,CLONE_INHERIT,CLONE_INHERIT,CLONE_DEEP> parent_impl; 
        Data_Splitter_TrainRandom_TestFixed(const IDXTYPE _splits, const IDXTYPE _perctrain, const IDXTYPE _perctest, const bool randomize=false) : parent_impl(_splits, _perctrain, _perctest, randomize) {notify("Data_Splitter_TrainRandom_TestFixed constructor.");} 
        Data_Splitter_TrainRandom_TestFixed(const Data_Splitter_TrainRandom_TestFixed& dsp) : parent_impl(dsp) {notify("Data_Splitter_TrainRandom_TestFixed copy constructor.");} 
        virtual ~Data_Splitter_TrainRandom_TestFixed() {notify("Data_Splitter_TrainRandom_TestFixed destructor.");}
 
        virtual std::ostream& print(std::ostream& os) const override {os << "Data_Splitter_TrainRandom_TestFixed(splits=" << parent::splits << ", %train=" << parent::perctrain << ", %test=" << parent::perctest << ")"; return os;}
protected:
        typedef Data_Splitter<INTERVALCONTAINER,IDXTYPE> TCC; 
        virtual void makeRandomSplit(const IDXTYPE n, const std::shared_ptr<INTERVALCONTAINER> list_train, const std::shared_ptr<INTERVALCONTAINER> list_test) override;
};
 
template<class INTERVALCONTAINER, typename IDXTYPE, typename BINTYPE>
void Data_Splitter_TrainRandom_TestFixed<INTERVALCONTAINER,IDXTYPE,BINTYPE>::makeRandomSplit(const IDXTYPE n, const std::shared_ptr<INTERVALCONTAINER> list_train, const std::shared_ptr<INTERVALCONTAINER> list_test)
{
        try {
                assert(list_train);
                assert(list_test);
                assert(n>0);
                assert(parent::perctrain+parent::perctest<=100);
                if(!parent::_data || parent::_n_max<n) {parent::_data.reset(new BINTYPE[n]); parent::_n_max=n;}
                const BINTYPE id_empty = 0;
                const BINTYPE id_train = 1;
                const IDXTYPE tesiz=(n * parent::perctest)/100;
                const IDXTYPE trsiz= (parent::perctrain+parent::perctest==100) ? n-tesiz : (n * parent::perctrain)/100;
                assert(trsiz+tesiz<=n);
                IDXTYPE i;
                for(i=0;i<n;i++) parent::_data[i]=id_empty;
 
                // now fill randomly perctrain% for training; the test part is the fixed trailing interval
                // NOTE: acceleration - whichever of the train set and its complement is smaller is the one
                //       actually drawn, so the number of random draws is min{perctrain,100-perctrain-perctest}
                //       rather than always perctrain; the other side is produced by pre-filling _data
                if(parent::perctrain<=(100-parent::perctest)/2) {
                        parent::fill_randomly(n,id_empty,id_train,trsiz/*count*/,0/*minidx*/,n-1-tesiz/*maxidx*/); // randomly choose train samples
                } else {
                        parent::fill(n,id_empty,id_train,0/*minidx*/,n-1-tesiz/*maxidx*/);
                        parent::fill_randomly(n,id_train,id_empty,n-tesiz-trsiz/*count*/,0/*minidx*/,n-1-tesiz/*maxidx*/); // randomly choose non-train samples
                }
 
                // now transform the binary representation to TCC::train list and create TCC::test list
                parent::translate(n,id_train,list_train);
                list_test->clear();
                if(tesiz>0) {Data_Interval<IDXTYPE> tin={n-tesiz,tesiz}; list_test->push_back(tin);}
 
        } catch(...) {
                throw fst_error("Data_Splitter_TrainRandom_TestFixed::makeRandomSplit() error.");
        }
}
 
 
} // namespace
#endif // FSTDATASPLITTERRANDFIX_H ///:~