source: trunk/test/subset_generator_test.cc @ 722

// $Id: subset_generator_test.cc 722 2006-12-27 20:49:11Z markus $

/*
  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/CrossValidationSampler.h"
#include "yat/classifier/EnsembleBuilder.h"
#include "yat/classifier/FeatureSelectorIR.h"
#include "yat/classifier/Kernel_SEV.h"
#include "yat/classifier/KernelLookup.h"
#include "yat/classifier/MatrixLookup.h"
#include "yat/classifier/PolynomialKernelFunction.h"
#include "yat/classifier/SubsetGenerator.h"
#include "yat/classifier/SVM.h"
#include "yat/classifier/NCC.h"
#include "yat/statistics/ROC.h"
#include "yat/statistics/PearsonDistance.h"
#include "yat/utility/matrix.h"

#include <fstream>
#include <iostream>
#include <string>

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


  std::ifstream is("data/nm_target_bin.txt");
  *error << "loading target " << std::endl;
  classifier::Target target(is);
  is.close();
  *error << "number of targets: " << target.size() << std::endl;
  *error << "number of classes: " << target.nof_classes() << std::endl;
  is.open("data/nm_data_centralized.txt");
  *error << "loading data " << std::endl;
  utility::matrix m(is);
  is.close();
  classifier::MatrixLookup data(m);
  *error << "number of samples: " << data.columns() << std::endl;
  *error << "number of features: " << data.rows() << std::endl;
  assert(data.columns()==target.size());

  *error << "building kernel" << std::endl;
  classifier::PolynomialKernelFunction kf(1);
  classifier::Kernel_SEV kernel_core(data,kf);
  classifier::KernelLookup kernel(kernel_core);
  *error << "building Sampler" << std::endl;
  classifier::CrossValidationSampler sampler(target, 30, 3);

  statistics::ROC score;
  classifier::FeatureSelectorIR fs(score, 96, 0);
  *error << "building SubsetGenerator" << std::endl;
  classifier::SubsetGenerator subset_data(sampler, data, fs);
  classifier::SubsetGenerator subset_kernel(sampler, kernel, fs);

  classifier::SVM svm(kernel,target);
  statistics::PearsonDistance distance;
  classifier::NCC ncc(data,target,distance);
  *error << "building Ensemble" << std::endl;
  //  classifier::EnsembleBuilder ensemble_ncc(ncc,subset_data);
  //ensemble_ncc.build();
  classifier::EnsembleBuilder ensemble_svm(svm,sampler);
  ensemble_svm.build();
  
  utility::vector out(target.size(),0);
  for (size_t i = 0; i<out.size(); ++i)
    out(i)=ensemble_svm.validate()[0][i].mean();
  statistics::ROC roc;
  *error << roc.score(target,out) << std::endl;

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