xmmKMeans.hpp

Go to the documentation of this file.

/*
 * xmmKMeans.hpp
 *
 * K-Means clustering
 *
 * Contact:
 * - Jules Francoise <jules.francoise@ircam.fr>
 *
 * This code has been initially authored by Jules Francoise
 * <http://julesfrancoise.com> during his PhD thesis, supervised by Frederic
 * Bevilacqua <href="http://frederic-bevilacqua.net>, in the Sound Music
 * Movement Interaction team <http://ismm.ircam.fr> of the
 * STMS Lab - IRCAM, CNRS, UPMC (2011-2015).
 *
 * Copyright (C) 2015 UPMC, Ircam-Centre Pompidou.
 *
 * This File is part of XMM.
 *
 * XMM 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 3 of the License, or
 * (at your option) any later version.
 *
 * XMM 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 XMM.  If not, see <http://www.gnu.org/licenses/>.
 */

#ifndef xmmKMeans_h
#define xmmKMeans_h

#include "../../core/model/xmmModelConfiguration.hpp"
#include "../../core/model/xmmModelSingleClass.hpp"
#include "xmmKMeansParameters.hpp"
#include "xmmKMeansResults.hpp"

namespace xmm {
class KMeans : public Writable {
  public:
    static const unsigned int DEFAULT_MAX_ITERATIONS = 50;
    static const float DEFAULT_RELATIVE_VARIATION_THRESHOLD() { return 1e-20; }

    enum class InitializationMode {
        Random,

        Biased
    };

    KMeans(unsigned int clusters = 1);

    KMeans(KMeans const& src);

    KMeans& operator=(KMeans const& src);

    void train(TrainingSet* trainingSet);

    void reset();

    void filter(std::vector<float> const& observation);


    Json::Value toJson() const;

    void fromJson(Json::Value const& root);


    std::shared_ptr<SharedParameters> shared_parameters;

    Configuration<KMeans> configuration;

    Results<KMeans> results;

    std::vector<float> centers;

    KMeans::InitializationMode initialization_mode;

  protected:
    void randomizeClusters(std::vector<float> const& trainingSetVariance);

    void initClustersWithFirstPhrase(std::shared_ptr<Phrase> phrase);

    void updateCenters(std::vector<float>& previous_centers,
                       TrainingSet* trainingSet);
};

template <typename T>
T euclidean_distance(const T* vector1, const T* vector2, unsigned int dimension);
}

#endif