data_accessor_splitting_memCSV.hpp

Go to the documentation of this file.

#ifndef FSTDATAACCESSORSPLITTINGMEMCSV_H
#define FSTDATAACCESSORSPLITTINGMEMCSV_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 <iostream>
#include <sstream>
#include <vector>
 
#include "error.hpp"
#include "global.hpp"
#include "data_accessor_splitting_mem.hpp"
#include "data_file_CSV.hpp"
 
namespace FST {

template<typename DATATYPE, typename IDXTYPE, class INTERVALCONTAINER>
class Data_Accessor_Splitting_MemCSV : public Clonable_Impl<Data_Accessor_Splitting_MemCSV<DATATYPE,IDXTYPE,INTERVALCONTAINER>,Data_Accessor_Splitting_Mem<DATATYPE,IDXTYPE,INTERVALCONTAINER>,CLONE_INHERIT,CLONE_WEAK_SHARING,CLONE_INHERIT>
{
        public:
                typedef Data_Accessor_Splitting_Mem<DATATYPE,IDXTYPE,INTERVALCONTAINER> DASM; 
                typedef Clonable_Impl<Data_Accessor_Splitting_MemCSV,DASM,CLONE_INHERIT,CLONE_WEAK_SHARING,CLONE_INHERIT> parent_impl;
                typedef std::shared_ptr<Data_Scaler<DATATYPE> > PScaler; 
                typedef typename DASM::PSplitters PSplitters; 
                Data_Accessor_Splitting_MemCSV(const std::string _filename, const Data_File_CSV_Options &_opts, const PSplitters _dsp, const PScaler _dsc) : parent_impl(_filename, _dsp, _dsc), opts(_opts) {notify("Data_Accessor_Splitting_MemCSV constructor.");}
                virtual ~Data_Accessor_Splitting_MemCSV(){notify("Data_Accessor_Splitting_MemCSV destructor.");}
 
                virtual std::ostream& print(std::ostream& os) const override;
        protected:
                friend parent_impl; 
                Data_Accessor_Splitting_MemCSV(const Data_Accessor_Splitting_MemCSV &damt, int x) : parent_impl(damt, x), opts(damt.opts), clsCount(damt.clsCount), featureCount(damt.featureCount), clsSize(damt.clsSize) {};
        protected:
                std::unique_ptr<Data_File_CSV> CSVFile;  
                Data_File_CSV_Options opts;  
 
                unsigned int clsCount;      
                unsigned int featureCount;  
                std::shared_ptr<IDXTYPE> clsSize;  
 
                virtual void initial_data_read() override ;    
                virtual void initial_file_prepare() override; 
 
    public:
                virtual unsigned int file_getNoOfClasses() const override {return clsCount; } 
                virtual unsigned int file_getNoOfFeatures() const override {return featureCount; } 
                virtual IDXTYPE file_getClassSize(unsigned int cls) const override {return clsSize.get()[cls]; } 
};
 
template<typename DATATYPE, typename IDXTYPE, class INTERVALCONTAINER>
void Data_Accessor_Splitting_MemCSV<DATATYPE,IDXTYPE,INTERVALCONTAINER>::initial_file_prepare()
{
        if(Clonable::is_sharing_clone()) throw fst_error("Data_Accessor_Splitting_MemCSV()::initial_file_prepare() called from shared_clone instance.");
        CSVFile.reset(new Data_File_CSV(this->filename, opts));
        CSVFile->prepareFile();
        CSVFile->sortRecordsByClass();
 
        clsCount = CSVFile->getNoOfClasses();
        featureCount = CSVFile->getNoOfFeatures();
        clsSize.reset(new IDXTYPE[clsCount], std::default_delete<IDXTYPE[]>());
        for (unsigned int i=0;i<clsCount; i++) clsSize.get()[i] = CSVFile->getClassSize(i);
}
 
template<typename DATATYPE, typename IDXTYPE, class INTERVALCONTAINER>
void Data_Accessor_Splitting_MemCSV<DATATYPE,IDXTYPE,INTERVALCONTAINER>::initial_data_read()
{
        if(Clonable::is_sharing_clone()) throw fst_error("Data_Accessor_Splitting_MemCSV()::initial_data_read() called from shared_clone instance.");
        {std::ostringstream sos; sos << "Reading data to memory..."; syncout::print(std::cout,sos);}
        IDXTYPE idx=0;
        for(unsigned int p=0;p<CSVFile->getTotalSize();p++)
        {
                for(unsigned int f=0;f<CSVFile->getNoOfFeatures();f++) {
                        this->data.get()[idx++]=(DATATYPE) CSVFile->getFeatureValue(p,f);
                }
        }
        CSVFile.reset();
        {std::ostringstream sos; sos << "done."<<std::endl; syncout::print(std::cout,sos);}
}
 
 
 
template<typename DATATYPE, typename IDXTYPE, class INTERVALCONTAINER>
std::ostream& Data_Accessor_Splitting_MemCSV<DATATYPE,IDXTYPE,INTERVALCONTAINER>::print(std::ostream& os) const
{
        DASM::print(os);
        os << std::endl << "Data_Accessor_Splitting_MemCSV()";
        return os;
}
 
} // namespace
#endif // FSTDATAACCESSORSPLITTINGMEMCSV_H ///:~