ROC.h

#ifndef _theplu_yat_statistics_roc_ 
#define _theplu_yat_statistics_roc_ 

// $Id: ROC.h 2624 2011-11-07 22:02:28Z peter $

/*
  Copyright (C) 2004 Peter Johansson
  Copyright (C) 2005, 2006, 2007, 2008 Jari Häkkinen, Peter Johansson
  Copyright (C) 2011 Peter Johansson

  This file is part of the yat library, http://dev.thep.lu.se/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 3 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 yat. If not, see <http://www.gnu.org/licenses/>.
*/

#include <gsl/gsl_randist.h>

#include <map>
#include <utility>

namespace theplu {
namespace yat {
namespace statistics {  

  class ROC
  {
  
  public:
    ROC(void);
         
    void add(double value, bool target, double weight=1.0);

    double area(void);

    unsigned int& minimum_size(void);

    const unsigned int& minimum_size(void) const;

    double n(void) const;

    double n_neg(void) const;

    double n_pos(void) const;

    double p_value_one_sided(void) const;
    
    double p_value(void) const;

    void reset(void);

  private:
    typedef std::multimap<double, std::pair<bool, double> > Map;
    
    double get_p_approx(double) const;

    /*
     */
    template<typename ForwardIterator>
    double p_exact_with_ties(ForwardIterator first, ForwardIterator last,
                             double block, double pos, double neg) const;

    double p_exact(double area) const;

    bool use_exact_method(void) const;

    double area_;
    bool has_ties_;
    unsigned int minimum_size_;
    double w_neg_;
    double w_pos_;
    Map multimap_;
  };

  template<typename ForwardIterator>
  double 
  ROC::p_exact_with_ties(ForwardIterator begin, ForwardIterator end,
                         double block, double pos, double neg) const
  {
    if (block <= 0)
      return 1.0;
    if (block > pos*neg)
      return 0.0;

    ForwardIterator iter(begin);
    size_t n=0;
    while (iter!=end && iter->first == begin->first) {
      ++iter;
      ++n;
    }
    double result = 0;
    for (size_t i=0; i<=n; ++i) {
      double pos1 = i;
      double neg1 = n-i;
      double pos2 = pos-pos1;
      double neg2 = neg-neg1;
      result += gsl_ran_hypergeometric_pdf(i, static_cast<unsigned int>(pos), 
                                           static_cast<unsigned int>(neg), n)
        * p_exact_with_ties(iter, end, 
                            block - pos2*neg1 - 0.5*pos1*neg1, 
                            pos2, neg2);
    }
    return result;
  }

}}} // of namespace statistics, yat, and theplu

#endif