knn_classifier.h

Go to the documentation of this file.

/***************************************************************************
 *
 * Authors:     Vahid Abrishami (vabrishami@cnb.csic.es)
 *
 * Unidad de  Bioinformatica of Centro Nacional de Biotecnologia , CSIC
 *
 * This program 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.
 *
 * This program 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
 *
 *  All comments concerning this program package may be sent to the
 *  e-mail address 'xmipp@cnb.csic.es'
 ***************************************************************************/

#ifndef KNN_CLASSIFIER_HH
#define KNN_CLASSIFIER_HH

/* Includes-----------------------------------------------------------------*/
#include <core/multidim_array.h>

class KNN
{
public:
    typedef enum { EUCLIDEAN = 0, CITYBLOCK = 1} distType;

    KNN(int k);

    void train(MultidimArray<double> &dataset,MultidimArray<double> &dataLabel,
               MultidimArray<double> &labelset);

    int predict(MultidimArray<double> &sample,double &score);

    void KNearestNeighbors(MultidimArray<double> &sample);

#ifdef UNUSED // detected as unused 29.6.2018
    void saveModel(const FileName &fn);

    void loadModel(const FileName &fn);
#endif

    void setK(int k);

private:
    double euclideanDistance(MultidimArray<double> &sample,int index,double maximumDist);

#ifdef UNUSED // detected as unused 29.6.2018
    double cityBlockDistance(MultidimArray<double> &sample,int index,double maximumDist);
#endif

    int findMaxIndex(MultidimArray<double> &inputArray);

    int findMinIndex(MultidimArray<double> &inputArray);

private:
    int K;

    MultidimArray<double>  __dataset;

    MultidimArray<double>  __dataLabel;

    MultidimArray<double> __labelSet;

    MultidimArray<int> neighborsIndex;

    MultidimArray<double> maxDist;
};
#endif