source: trunk/c++_tools/statistics/tScore.cc @ 675

// $Id: tScore.cc 675 2006-10-10 12:08:45Z jari $

/*
  Copyright (C) The authors contributing to this file.

  This file is part of the yat library, http://lev.thep.lu.se/trac/yat

  The yat library is free software; you can redistribute it and/or
  modify it under the terms of the GNU General Public License as
  published by the Free Software Foundation; either version 2 of the
  License, or (at your option) any later version.

  The yat library 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
  General Public License for more details.

  You should have received a copy of the GNU 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.
*/

#include "c++_tools/statistics/tScore.h"
#include "c++_tools/statistics/Averager.h"
#include "c++_tools/statistics/AveragerWeighted.h"
#include "c++_tools/classifier/DataLookupWeighted1D.h"
#include "c++_tools/classifier/Target.h"

#include <cassert>
#include <cmath>


namespace theplu {
namespace statistics {  

  tScore::tScore(bool b) 
    : Score(b),  t_(0)
  {
  }

  double tScore::score(const classifier::Target& target, 
                       const utility::vector& value)
  {
    weighted_=false;
    statistics::Averager positive;
    statistics::Averager negative;
    for(size_t i=0; i<target.size(); i++){
      if (target.binary(i))
        positive.add(value(i));
      else
        negative.add(value(i));
    }
    double diff = positive.mean() - negative.mean();
    dof_=positive.n()+negative.n()-2;
    double s2=(positive.sum_xx_centered()+negative.sum_xx_centered())/dof_;

    t_=diff/sqrt(s2/positive.n()+s2/negative.n());
    if (t_<0 && absolute_)
      t_=-t_;
     
    return t_;
  }


  double tScore::score(const classifier::Target& target, 
                       const classifier::DataLookupWeighted1D& value)
  {
    weighted_=true;

    statistics::AveragerWeighted positive;
    statistics::AveragerWeighted negative;
    for(size_t i=0; i<target.size(); i++){
      if (target.binary(i))
        positive.add(value.data(i),value.weight(i));
      else
        negative.add(value.data(i),value.weight(i));
    }
    double diff = positive.mean() - negative.mean();
    dof_=positive.n()+negative.n()-2;
    double s2=(positive.sum_xx_centered()+negative.sum_xx_centered())/dof_;
    t_=diff/sqrt(s2/positive.n()+s2/(negative.n()));
    if (t_<0 && absolute_)
      t_=-t_;

    if(positive.sum_w()==0 || negative.sum_w()==0)
      t_=0;
    return t_;
  }


  double tScore::score(const classifier::Target& target, 
                       const utility::vector& value,
                       const utility::vector& weight)
  {
    weighted_=true;

    statistics::AveragerWeighted positive;
    statistics::AveragerWeighted negative;
    for(size_t i=0; i<target.size(); i++){
      if (target.binary(i))
        positive.add(value(i),weight(i));
      else
        negative.add(value(i),weight(i));
    }
    double diff = positive.mean() - negative.mean();
    dof_=positive.n()+negative.n()-2;
    double s2=(positive.sum_xx_centered()+negative.sum_xx_centered())/dof_;
    t_=diff/sqrt(s2/positive.n()+s2/(negative.n()));
    if (t_<0 && absolute_)
      t_=-t_;

    if(positive.sum_w()==0 || negative.sum_w()==0)
      t_=0;
    return t_;
  }

  double tScore::p_value(void) const
  {
    double p = gsl_cdf_tdist_Q(t_, dof_);
    return (dof_ > 0 && !weighted_) ? p : 1;
  }



}} // of namespace statistics and namespace theplu