source: trunk/test/score_test.cc @ 747

// $Id: score_test.cc 747 2007-02-11 13:26:41Z peter $

/*
  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 "yat/classifier/Target.h"
#include "yat/statistics/FoldChange.h"
#include "yat/statistics/Pearson.h"
#include "yat/statistics/ROC.h"
#include "yat/statistics/SAM.h"
#include "yat/statistics/tScore.h"
#include "yat/statistics/WilcoxonFoldChange.h"
#include "yat/utility/matrix.h"
#include "yat/utility/vector.h"

#include <cmath>
#include <fstream>
#include <iostream>


using namespace theplu::yat;

int main(const int argc,const char* argv[])
{  
  std::ostream* error;
  if (argc>1 && argv[1]==std::string("-v"))
    error = &std::cerr;
  else {
    error = new std::ofstream("/dev/null");
    if (argc>1)
      std::cout << "score_test -v : for printing extra information\n";
  }
  *error << "testing score classes" << std::endl;
  bool ok = true;

  *error << "testing ROC" << std::endl;
  utility::vector value(31);
  std::vector<std::string> label(31,"negative");
  for (size_t i=0; i<16; i++) 
    label[i] = "positive";
  classifier::Target target(label);
  for (size_t i=0; i<value.size(); i++) 
    value(i)=i;
  statistics::ROC roc;
  double area = roc.score(target, value);
  if (area!=1.0){
    *error << "test_roc: area is " << area << " should be 1.0" 
           << std::endl;
    ok = false;
  }
  target.set_binary(0,false);
  target.set_binary(1,true);
  area = roc.score(target, value);
  if (area!=1.0){
    *error << "test_roc: area is " << area << " should be 1.0" 
           << std::endl;
    ok = false;
  }
  
  double p = roc.p_value();
  double p_matlab = 0.00000115;
  if (p/p_matlab > 1.01 | p/p_matlab < 0.99){
    *error << "get_p_approx: p-value not correct" << std::endl;
    ok = false;
  }
  roc.minimum_size() = 20;
  p = roc.p_value();
  if (p > pow(10, -8.0) | p < pow(10, -9.0)){
    *error << "get_p_exact: p-value not correct" << std::endl;
    ok = false;
  }
  
  std::ifstream is("data/rank_data.txt");
  utility::matrix data(is);
  is.close();

  is.open("data/rank_target.txt");
  classifier::Target target2(is);
  is.close();
  
  utility::vector correct_area(3);
  correct_area(0)=8.0/9.0;
  correct_area(1)=6.0/9.0;
  correct_area(2)=1.0;

  const double tol = 0.001;
  for (size_t i=0; i<data.rows(); i++){
    utility::vector vec(data,i);
    if (vec.size()!=target2.size()){
      *error << "vec.size() is " << vec.size() << " and target2.size() is " 
             << target2.size() << ". Should be equal." << std::endl; 
      ok=false;
    }
    area = roc.score(target2,vec);
    if (area<correct_area(i)-tol || area>correct_area(i)+tol){
      *error << "test_roc: area is " << area << " should be " 
             << correct_area(i) << std::endl;
      ok=false;
    }
  }

  utility::vector weight(target2.size(),1);
  for (size_t i=0; i<data.rows(); i++){
    utility::vector vec(data,i);
    area = roc.score(target2, vec, weight);
    if (area<correct_area(i)-tol || area>correct_area(i)+tol){
      *error << "test_roc: weighted area is " << area << " should be " 
             << correct_area(i) << std::endl;
      ok=false;
    }
  }

  *error << "testing FoldChange" << std::endl;
  statistics::FoldChange fold_change(true);

  *error << "testing tScore" << std::endl;
  statistics::tScore t_score(true);

  *error << "testing Pearson" << std::endl;
  statistics::Pearson pearson(true);

  *error << "testing WilcoxonFoldChange" << std::endl;
  statistics::WilcoxonFoldChange wfc(true);

  *error << "testing SAM" << std::endl;
  statistics::SAM sam(1.0,true);


  if (ok)
    return 0;
  return -1;
}