data_splitter.hpp

Go to the documentation of this file.

#ifndef FSTDATASPLITTER_H
#define FSTDATASPLITTER_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 <string>
#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<class INTERVALCONTAINER, typename IDXTYPE>
class Data_Splitter;
 
template<class INTERVALCONTAINER, typename IDXTYPE>
std::ostream& operator<<(std::ostream& os, const Data_Splitter<INTERVALCONTAINER,IDXTYPE>& ds);

template<class INTERVALCONTAINER, typename IDXTYPE>
class Data_Splitter : public Clonable {
        friend std::ostream& operator<< <>(std::ostream& os, const Data_Splitter<INTERVALCONTAINER,IDXTYPE>& ds);
public:
        typedef std::shared_ptr<INTERVALCONTAINER> PIntervaller;  
        Data_Splitter() {csplit.clear(); notify("Data_Splitter constructor.");}
        Data_Splitter(const Data_Splitter& dsp);
        virtual ~Data_Splitter() {notify("Data_Splitter destructor.");}

        void assign(const unsigned int _clsidx, const PIntervaller _train, const PIntervaller _test);
        void set_n(const unsigned int _clsidx, const IDXTYPE _n);
        IDXTYPE get_n(const unsigned int _clsidx) const; 
 
        virtual IDXTYPE getNoOfSplits() const =0;       
        bool makeFirstSplit();
        bool makeNextSplit();
 
        Data_Splitter* clone() const override {throw fst_error("Data_Splitter::clone() not supported, use Data_Splitter::stateless_clone() instead.");}
        Data_Splitter* sharing_clone() const override {throw fst_error("Data_Splitter::sharing_clone() not supported, use Data_Splitter::stateless_clone() instead.");}
        Data_Splitter* stateless_clone() const override =0;
 
        virtual std::ostream& print(std::ostream& os) const override {return os;} 
 
protected:
        class TClassSplitter {
        public:
                TClassSplitter() {n=0; train.reset(); test.reset(); notify("TClassSplitter empty constructor.");}
                TClassSplitter(const TClassSplitter& cs) : n(cs.n) {
                        notify("TClassSplitter strong copy constructor begin.");
                        if(cs.train) train.reset(new INTERVALCONTAINER(*cs.train));
                        if(cs.test) test.reset(new INTERVALCONTAINER(*cs.test));
                        notify("TClassSplitter strong copy constructor end.");
                }
                ~TClassSplitter() {notify("TClassSplitter destructor.");}
                IDXTYPE n;      
                PIntervaller train;     
                PIntervaller test;      
        };
        typedef std::shared_ptr<TClassSplitter> PClassSplitter;   
        std::vector<PClassSplitter> csplit; 
        typedef typename std::vector<PClassSplitter>::const_iterator ClassIterator; 
 
        void assert_csplit() const; 
 
        // hooks a concrete splitter implements; see the class description for the call order and
        // for the contract the written intervals must satisfy
        virtual const char* splitter_name() const =0; 
        virtual bool prepareFirstSplit() {return true;} 
        virtual bool prepareNextSplit() =0; 
        virtual void splitClassFirst(ClassIterator c, const unsigned int cidx) =0; 
        virtual void splitClassNext(ClassIterator c, const unsigned int cidx) {} 
        virtual void finishSplit() {} 
};
 
template<class INTERVALCONTAINER, typename IDXTYPE>
bool Data_Splitter<INTERVALCONTAINER,IDXTYPE>::makeFirstSplit()
{
        assert_csplit();
        try {
                if(!prepareFirstSplit()) return false;
                unsigned int cidx=0;
                for(ClassIterator c=csplit.begin();c!=csplit.end();c++,cidx++) splitClassFirst(c,cidx);
                finishSplit();
        } catch(...) {
                throw fst_error(std::string(splitter_name())+"::makeFirstSplit() error.");
        }
        return true;
}
 
template<class INTERVALCONTAINER, typename IDXTYPE>
bool Data_Splitter<INTERVALCONTAINER,IDXTYPE>::makeNextSplit()
{
        try {
                if(!prepareNextSplit()) return false;
                unsigned int cidx=0;
                for(ClassIterator c=csplit.begin();c!=csplit.end();c++,cidx++) splitClassNext(c,cidx);
                finishSplit();
        } catch(...) {
                throw fst_error(std::string(splitter_name())+"::makeNextSplit() error.");
        }
        return true;
}
 
 
template<class INTERVALCONTAINER, typename IDXTYPE>
Data_Splitter<INTERVALCONTAINER,IDXTYPE>::Data_Splitter(const Data_Splitter& dsp)
{
        notify("Data_Splitter strong copy constructor begin.");
        csplit.clear();
        for(typename std::vector<PClassSplitter>::const_iterator c=dsp.csplit.begin();c!=dsp.csplit.end();c++) 
                {PClassSplitter pcs(new TClassSplitter(*(*c))); this->csplit.push_back(pcs);}
        notify("Data_Splitter strong copy constructor end.");
}
 
template<class INTERVALCONTAINER, typename IDXTYPE>
void Data_Splitter<INTERVALCONTAINER,IDXTYPE>::assign(const unsigned int _clsidx, const PIntervaller _train, const PIntervaller _test)
{
        assert(_train); 
        assert(_test);
        try {   
                while(csplit.size()<=_clsidx) {PClassSplitter pcs(new TClassSplitter); csplit.push_back(pcs);}
                csplit[_clsidx]->train=_train; 
                csplit[_clsidx]->test=_test;
        } catch(...) {
                throw fst_error("Data_Splitter::set_n() out-of-index? error.");
        }
}
        
template<class INTERVALCONTAINER, typename IDXTYPE>
void Data_Splitter<INTERVALCONTAINER,IDXTYPE>::set_n(const unsigned int _clsidx, const IDXTYPE _n)
{
        assert(_n>0); 
        try {   
                while(csplit.size()<=_clsidx) {PClassSplitter pcs(new TClassSplitter); csplit.push_back(pcs);}
                csplit[_clsidx]->n=_n;
        } catch(...) {
                throw fst_error("Data_Splitter::set_n() out-of-index? error.");
        }
}
 
template<class INTERVALCONTAINER, typename IDXTYPE>
IDXTYPE Data_Splitter<INTERVALCONTAINER,IDXTYPE>::get_n(const unsigned int _clsidx) const
{
        assert(_clsidx<csplit.size());
        try {
                return csplit[_clsidx]->n;
        } catch(...) {
                throw fst_error("Data_Splitter::get_n() out-of-index? error.");
        }
}

template<class INTERVALCONTAINER, typename IDXTYPE>
std::ostream& operator<<(std::ostream& os, const Data_Splitter<INTERVALCONTAINER,IDXTYPE>& ds) {
        return ds.print(os);
}
 
template<class INTERVALCONTAINER, typename IDXTYPE>
void Data_Splitter<INTERVALCONTAINER,IDXTYPE>::assert_csplit() const
{
#ifdef DEBUG
        assert(csplit.size()>0);
        for(ClassIterator c=csplit.begin();c!=csplit.end();c++) {
                assert((*c)->n>0);
                assert((*c)->train);
                assert((*c)->test);
        }
#endif
}
 
 
} // namespace
#endif // FSTDATASPLITTER_H ///:~