NICE_VisLearning/regression/npregression/RegKNN.cpp

/**
* @file RegKNN.cpp
* @brief Implementation of k-Nearest-Neighbor algorithm for regression purposes
* @author Frank Prüfer
* @date 08/29/2013

*/

#ifdef NICE_USELIB_OPENMP
#include <omp.h>
#endif

#include <iostream>

#include "vislearning/regression/npregression/RegKNN.h"

#include "vislearning/math/mathbase/FullVector.h"

using namespace OBJREC;

using namespace std;
using namespace NICE;


RegKNN::RegKNN ( const Config *_conf, NICE::VectorDistance<double> *_distancefunc ) : distancefunc (_distancefunc)
{
    K = _conf->gI("RegKNN", "K", 1 );
    if ( _distancefunc == NULL )
		distancefunc = new EuclidianDistance<double>();
}

RegKNN::~RegKNN()
{
}

void RegKNN::teach ( const NICE::VVector & _dataSet, const NICE::Vector & _labelSet)
{
    fprintf (stderr, "teach using all !\n");
    //NOTE this is crucial if we clear _teachSet afterwards!
    //therefore, take care NOT to call _techSet.clear() somewhere out of this method
    this->dataSet = _dataSet;
    this->labelSet = _labelSet.std_vector();
    
    std::cerr << "number of known training samples: " << this->dataSet.size() << std::endl;   
    
}

void RegKNN::teach ( const NICE::Vector & x, const double & y )
{
    std::cerr << "RegKNN::teach one new example" << std::endl;
    
    for ( size_t i = 0 ; i < x.size() ; i++ )
      if ( isnan(x[i]) ) 
      {
          fprintf (stderr, "There is a NAN value in within this vector: x[%d] = %f\n", (int)i, x[i]);
          cerr << x << endl;
          exit(-1);
      }

    dataSet.push_back ( x );
    
    labelSet.push_back ( y );
    
    std::cerr << "number of known training samples: " << dataSet.size()<< std::endl;
}

double RegKNN::predict ( const NICE::Vector & x )
{
    FullVector distances(dataSet.size());

    if ( dataSet.size() <= 0 ) {
		fprintf (stderr, "RegKNN: please use the train method first\n");
		exit(-1);
    }

#pragma omp parallel for
    for(uint i = 0; i < dataSet.size(); i++){
    
      double distance = distancefunc->calculate (x,dataSet[i]);
      
      if ( isnan(distance) ){
          fprintf (stderr, "RegKNN::predict: NAN value found !!\n");
          cerr << x << endl;
          cerr << dataSet[i] << endl;
      }
// #pragma omp critical      
      distances[i] = distance;     
    }
    
    std::vector<int> ind;
    distances.getSortedIndices(ind);
    
    double response = 0.0;  
    
    if ( dataSet.size() < K ){
      K = dataSet.size();
      cerr<<"RegKNN: Not enough datapoints! Setting K to: "<< K <<endl;
    }
        
    if ( distances[ind[0]] == 0.0 ) {
      cerr<<"RegKNN: Warning: datapoint was already seen during training... using its label as prediction."<<endl;
      return labelSet[ind[0]];  
    }
    
    double maxElement = distances.max();	//normalize distances
    distances.multiply(1.0/maxElement);
    
    double weightSum = 0.0;
    
    for(uint i = 0; i < K; i++){
      response += 1.0/distances[ind[i]] * labelSet[ind[i]];
      weightSum += 1.0/distances[ind[i]];
    }
       
    return ( response / weightSum );
}