data_accessor.hpp

Go to the documentation of this file.

#ifndef FSTDATAACCESSOR_H
#define FSTDATAACCESSOR_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 <vector>
#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 {

enum DataPart {
  NONE=0,      
  TRAIN=1,     
  TEST=2,      
  TRAINTEST=4, 
  ALL=8        
};

template<typename DATATYPE, typename IDXTYPE>
class Data_Accessor : public Clonable // abstract class
{
        public:
                typedef const DATATYPE* PPattern; 
                Data_Accessor() {notify("Data_Accessor constructor");}
                virtual ~Data_Accessor() {notify("Data_Accessor destructor");}  
                
                virtual unsigned int getNoOfClasses() const =0;              
                virtual unsigned int getNoOfFeatures() const =0;             
                virtual IDXTYPE getClassSize(const unsigned int c) const =0; 
                virtual IDXTYPE getClassSizeSum() const =0;                  
 
                virtual void setClass(const int c) =0;   
                virtual int  getClass() const =0;        
 
                virtual unsigned int getNoOfSplits() const =0;  
                virtual bool getFirstSplit()=0;                 
                virtual bool getNextSplit()=0;                  
                virtual unsigned int getSplitIndex() const =0;  

                virtual IDXTYPE getNoOfBlocks(const DataPart ofwhat) const =0;
                virtual bool getFirstBlock(const DataPart ofwhat, PPattern &firstpattern, IDXTYPE &patterns, const unsigned int loopdepth=0)=0;
                virtual bool getNextBlock(const DataPart ofwhat, PPattern &firstpattern, IDXTYPE &patterns, const unsigned int loopdepth=0)=0;

                struct Block {
                        PPattern data;  
                        IDXTYPE size;   
                };

                class Block_Range {
                public:
                        class iterator {
                        public:
                                iterator(Block_Range *r, const bool done) : _r(r), _done(done) {_cur.data=nullptr; _cur.size=0; if(!_done) _done=!_r->_da->getFirstBlock(_r->_part,_cur.data,_cur.size,_r->_depth);}
                                const Block& operator*() const {return _cur;} 
                                iterator& operator++() {_done=!_r->_da->getNextBlock(_r->_part,_cur.data,_cur.size,_r->_depth); return *this;} 
                                bool operator!=(const iterator& o) const {return _done!=o._done;} 
                        private:
                                Block_Range *_r; 
                                bool _done;       
                                Block _cur;       
                        };
                        Block_Range(Data_Accessor *da, const DataPart part) : _da(da), _part(part), _depth(da->acquire_block_loop_slot()) {}
                        ~Block_Range() {_da->release_block_loop_slot(_depth);}
                        iterator begin() {return iterator(this,false);} 
                        iterator end() {return iterator(this,true);} 
                        unsigned int loopdepth() const {return _depth;} 
                        // neither copyable nor movable: exactly one owner of the loopdepth slot. blocks()
                        // can still return a range by value because C++17 guaranteed copy elision
                        // materializes the return value in place, with no copy or move involved.
                        Block_Range(const Block_Range&) = delete;
                        Block_Range& operator=(const Block_Range&) = delete;
                private:
                        Data_Accessor *_da;       
                        const DataPart _part;      
                        const unsigned int _depth; 
                };
                Block_Range blocks(const DataPart ofwhat) {return Block_Range(this,ofwhat);}
                virtual IDXTYPE getBlockIndex(const unsigned int loopdepth=0) const =0;
                virtual IDXTYPE getNoOfPatterns(const DataPart ofwhat) const =0;
                virtual void substitute(const DataPart source, const DataPart target)=0;
                virtual void resubstitute()=0;
 
                Data_Accessor* clone() const override =0;
                Data_Accessor* sharing_clone() const override =0;
                Data_Accessor* stateless_clone() const override =0;
        private:
                static const unsigned int _first_acquired_loopdepth = 4;
                std::vector<bool> _block_slot_used; 
                unsigned int acquire_block_loop_slot() {
                        for(unsigned int i=0;i<(unsigned int)_block_slot_used.size();++i) if(!_block_slot_used[i]) {_block_slot_used[i]=true; return _first_acquired_loopdepth+i;}
                        _block_slot_used.push_back(true);
                        return _first_acquired_loopdepth+(unsigned int)(_block_slot_used.size()-1);
                }

                void release_block_loop_slot(const unsigned int depth) {
                        assert(depth>=_first_acquired_loopdepth);
                        const unsigned int i=depth-_first_acquired_loopdepth;
                        if(i<(unsigned int)_block_slot_used.size()) _block_slot_used[i]=false;
                }
};
 
 
} // namespace
#endif // FSTDATAACCESSOR_H ///:~