STK_Stat_Multivariate.h

Go to the documentation of this file.

/*--------------------------------------------------------------------*/
/*     Copyright (C) 2004-2016  Serge Iovleff, Université Lille 1, Inria
 
    This program is free software; you can redistribute it and/or modify
    it under the terms of the GNU Lesser General Public License as
    published by the Free Software Foundation; either version 2 of the
    License, or (at your option) any later version.
 
    This program 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 Lesser General Public License for more details.
 
    You should have received a copy of the GNU Lesser General Public
    License along with this program; if not, write to the
    Free Software Foundation, Inc.,
    59 Temple Place,
    Suite 330,
    Boston, MA 02111-1307
    USA
 
    Contact : S..._Dot_I..._At_stkpp_Dot_org (see copyright for ...)
*/
 
/*
 * Project:  stkpp::StatistiK::StatDesc
 * Purpose:  Compute multivariate elementary statistics for a 2D container.
 * Author:   Serge Iovleff, S..._Dot_I..._At_stkpp_Dot_org (see copyright for ...)
 **/
 
#ifndef STK_STAT_MULTIVARIATE_H
#define STK_STAT_MULTIVARIATE_H
 
#include <Sdk.h>
 
#include "Arrays/include/STK_Array2DVector.h"
 
namespace STK
{
namespace Stat
{
template < class Array, class WColVector, typename Type =  typename Array::Type >
class Multivariate: public IRunnerUnsupervised< Array, WColVector>
{
  public:
    typedef IRunnerUnsupervised< Array, WColVector> Runner2D;
    Multivariate( Array const* p_data)
                : Runner2D(p_data)
                , nbSamples_(0)
                , nbVar_(0)
                , nbMiss_()
    {}
 
    Multivariate( Array const& data)
                : Runner2D(data)
                , nbSamples_()
                , nbVar_()
                , nbMiss_()
    {}
    virtual ~Multivariate() {}
    inline int nbSamples() const {return nbSamples_;}
    inline int nbVariable() const {return nbVar_;}
    inline Array1D<int> const& nbMissingSamples() const {return nbMiss_;}
    inline Array1D<int> const& nbAvailableSamples() const {return nbAvailable_;}
 
    virtual bool run()
    {
      if (!this->p_data_)
      { this->msg_error_ = STKERROR_NO_ARG(Multivariate<Array>::run(),data are not set);
        return false;
      }
      nbSamples_ = this->p_data_->sizeRows();
      nbVar_     = this->p_data_->sizeCols();
      nbMiss_.resize(this->p_data_->cols());
      nbAvailable_.resize(this->p_data_->cols());
      // for each variables
      for (int j= this->p_data_->beginCols(); j<= this->p_data_->lastIdxCols(); j++)
      {
        // number of observations
        int nobs = nbSamples_;
        // compute the mean
        for (int i= this->p_data_->beginRows(); i<= this->p_data_->lastIdxRows(); i++)
        {  if (!Arithmetic<Type>::isFinite((*this->p_data_)(i,j))) nobs--;}
        nbAvailable_[j] = nobs;
        nbMiss_[j] = nbSamples_ - nobs;
      }
      return true;
    }
    virtual bool run( WColVector const& weights)
    {
      if (!this->p_data_)
      { this->msg_error_ = STKERROR_NO_ARG(Multivariate<Array>::run(),data are not set);
        return false;
      }
      return run();
    }
 
  protected:
    int nbSamples_;
    int nbVar_;
    Array1D<int> nbMiss_;
    Array1D<int> nbAvailable_;
};
 
}  // namespace Stat
 
}  // namespace STK
 
#endif /*STK_STAT_MULTIVARIATE_H*/