source: trunk/test/ensemble_test.cc @ 865

// $Id: ensemble_test.cc 865 2007-09-10 19:41:04Z peter $

/*
  Copyright (C) 2006 Jari Häkkinen, Markus Ringnér, Peter Johansson
  Copyright (C) 2007 Peter Johansson

  This file is part of the yat library, http://trac.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/utility/matrix.h"
#include "yat/classifier/SubsetGenerator.h"
#include "yat/classifier/CrossValidationSampler.h"
#include "yat/classifier/EnsembleBuilder.h"
#include "yat/classifier/Kernel.h"
#include "yat/classifier/KernelLookup.h"
#include "yat/classifier/Kernel_SEV.h"
#include "yat/classifier/Kernel_MEV.h"
#include "yat/classifier/MatrixLookup.h"
#include "yat/classifier/NCC.h"
#include "yat/statistics/PearsonDistance.h"
#include "yat/classifier/PolynomialKernelFunction.h"
#include "yat/classifier/SVM.h"
#include "yat/statistics/AUC.h"

#include <cassert>
#include <fstream>
#include <iostream>
#include <cstdlib>
#include <limits>


int main(const int argc,const char* argv[])
{  
  using namespace theplu::yat;

  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 << "ensemble_test -v : for printing extra information\n";
  }
  *error << "testing ensemble" << std::endl;
  bool ok = true;

  *error << "loading data" << std::endl;
  std::ifstream is("data/nm_data_centralized.txt");
  utility::matrix data_core(is);
  is.close();

  *error << "create MatrixLookup" << std::endl;
  classifier::MatrixLookup data(data_core);
  classifier::KernelFunction* kf = new classifier::PolynomialKernelFunction(); 
  *error << "Building kernel" << std::endl;
  classifier::Kernel_SEV kernel(data,*kf);


  *error << "load target" << std::endl;
  is.open("data/nm_target_bin.txt");
  classifier::Target target(is);
  is.close();
  assert(data.columns()==target.size());

  *error << "create KernelLookup" << std::endl;
  classifier::KernelLookup kernel_lookup(kernel);
  *error << "create svm" << std::endl;
  classifier::SVM svm(kernel_lookup, target);
  *error << "create Subsets" << std::endl;
  classifier::CrossValidationSampler sampler(target,3,3);
  classifier::SubsetGenerator cv(sampler,kernel_lookup);
  *error << "create ensemble" << std::endl;
  classifier::EnsembleBuilder ensemble(svm,sampler);
  *error << "build ensemble" << std::endl;
  ensemble.build();
  
  utility::vector out(target.size(),0);
  for (size_t i = 0; i<out.size(); ++i)
    out(i)=ensemble.validate()[0][i].mean(); 
  statistics::AUC roc;
  *error << roc.score(target,out) << std::endl;

  delete kf;

  if (error!=&std::cerr)
    delete error;

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