source: trunk/src/WeNNI.cc @ 233

// $Id: WeNNI.cc 233 2005-02-21 14:52:30Z peter $

#include "WeNNI.h"

#include <algorithm>
#include <cmath>
#include <fstream>

#include "stl_utility.h"

namespace theplu {
namespace cpptools {


  WeNNI::WeNNI(const gslapi::matrix& matrix,const gslapi::matrix& flag,
               const u_int neighbours)
    : NNI(matrix,flag,neighbours), imputed_data_raw_(matrix)
  {
    //estimate();
  }



  // \hat{x_{ij}}=\frac{ \sum_{k=1,N} \frac{w_{kj}*x_{kj}}{d_{ki}} }
  //                   { \sum_{k=1,N} \frac{w_{kj}       }{d_{ki}} }
  // where N is defined in the paper cited in the NNI class definition
  // documentation.
  u_int WeNNI::estimate(void)
  {
    using namespace std;
    for (unsigned int i=0; i<data_.rows(); i++) {
      // Jari, avoid copying in next line
      vector<pair<u_int,double> > distance=calculate_distances(i);
      sort(distance.begin(),distance.end(),
                pair_value_compare<u_int,double>());
      bool row_imputed=true;
      for (unsigned int j=0; j<data_.columns(); j++) {
        vector<u_int> knn=nearest_neighbours(j,distance);
        double new_value=0.0;
        double norm=0.0;
        for (vector<u_int>::const_iterator k=knn.begin(); k!=knn.end(); k++) {
          // Jari, a small number needed here, use something standardized.
          // Avoid division with zero (perfect match vectors)
          double d=(distance[*k].second ? distance[*k].second : 1e-10);
          new_value+=(weight_(distance[*k].first,j) *
                      data_(distance[*k].first,j)/d);
          norm+=weight_(distance[*k].first,j)/d;
        }
        // No impute if no contributions from neighbours.
        if (norm){
          imputed_data_raw_(i,j) = new_value/norm;
          imputed_data_(i,j)=
            weight_(i,j)*data_(i,j) + (1-weight_(i,j))* imputed_data_raw_(i,j);
        }
        else
          row_imputed=false;
      }
      if (!row_imputed)
        not_imputed_.push_back(i);
    }
    return not_imputed_.size();
  }


}} // of namespace cpptools and namespace theplu