source: trunk/test/feature_selection_test.cc @ 865

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

/*
  Copyright (C) 2006 Jari Häkkinen, 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/classifier/DataLookupWeighted1D.h"
#include "yat/classifier/FeatureSelectorIR.h"
#include "yat/classifier/FeatureSelectorRandom.h"
#include "yat/classifier/MatrixLookupWeighted.h"
#include "yat/classifier/Target.h"
#include "yat/statistics/SNRScore.h"

#include "yat/utility/matrix.h"

#include <algorithm>
#include <cmath>
#include <fstream>
#include <iterator>
#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 feature_selection" << std::endl;
  bool ok = true;

  statistics::SNRScore snr;
  classifier::FeatureSelectorIR f(snr, 12);
  classifier::FeatureSelectorRandom f2(12);

  *error << "Reading in Sorlie data to identify top gene ..." << std::endl;
  std::ifstream is("data/sorlie_centroid_data.txt");
  utility::matrix data(is,'\t');
  is.close();

  is.open("data/sorlie_centroid_classes.txt");
  classifier::Target targets(is);
  is.close();

  *error << "... done" << std::endl;

  // Generate weight matrix with 0 for missing values and 1 for others.
  utility::matrix weights(data.rows(),data.columns(),0.0);
  for(size_t i=0;i<data.rows();++i)
    for(size_t j=0;j<data.columns();++j)
      if(!std::isnan(data(i,j)))
        weights(i,j)=1.0;
  
  classifier::MatrixLookupWeighted dataviewweighted(data,weights);
  
  f2.update(dataviewweighted,targets);
  *error << "\nRandomly ordered features (top 12):\n";
  std::vector<size_t> features=f2.features();
  std::copy(features.begin(),features.end(),
            std::ostream_iterator<size_t>(*error," ")); 
  *error << std::endl;

  f.update(dataviewweighted,targets);
  *error << "\nSNR ordered ordered features (top 12):\n";
  features=f.features();
  std::copy(features.begin(),features.end(),
            std::ostream_iterator<size_t>(*error," ")); 
  *error << std::endl;

  size_t best_feature=features[0];
  if(best_feature!=69) {
    *error << "\nERROR: Incorrect best feature found!\n" << std::endl;
    ok=0;
  }

  classifier::DataLookupWeighted1D row(dataviewweighted,best_feature,true);
  double score_diff=fabs(snr.score(targets,row)-1.47804);
  if(score_diff>0.00001) {
    *error << "\nERROR: Best score not what expected!\n" << std::endl;
    ok=0;
  }
  
  // Re-rank the best features 
  classifier::MatrixLookupWeighted ranked=f.get(dataviewweighted);
  f.update(ranked,targets);
  features=f.features();
  for(size_t i=0;i<features.size();i++) {
    if(features[i]!=i) {
      ok=0;
      *error << "ERROR: Problem with top-ranked feature" << std::endl;
    }
  }

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