source: trunk/c++_tools/statistics/tScore.cc @ 616

// $Id: tScore.cc 616 2006-08-31 08:52:02Z jari $

// System includes
#include <cassert>
#include <cmath>

// Thep C++ Tools
#include <c++_tools/statistics/tScore.h>
#include <c++_tools/statistics/Averager.h>
#include <c++_tools/statistics/AveragerWeighted.h>
#include <c++_tools/classifier/Target.h>

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 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