StochasticGBMachine.h

Go to the documentation of this file.

/*
 * Copyright (c) The Shogun Machine Learning Toolbox
 * Written (w) 2014 Parijat Mazumdar
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 * 1. Redistributions of source code must retain the above copyright notice, this
 * list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright notice,
 * this list of conditions and the following disclaimer in the documentation
 * and/or other materials provided with the distribution.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
 * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
 * ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
 * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
 * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 *
 * The views and conclusions contained in the software and documentation are those
 * of the authors and should not be interpreted as representing official policies,
 * either expressed or implied, of the Shogun Development Team.
 */

#ifndef _StochasticGBMachine_H__
#define _StochasticGBMachine_H__


#include <shogun/lib/config.h>

#include <shogun/machine/Machine.h>
#include <shogun/loss/LossFunction.h>
#include <shogun/features/DenseFeatures.h>

namespace shogun
{

class CStochasticGBMachine : public CMachine
{
public:
    CStochasticGBMachine(CMachine* machine=NULL, CLossFunction* loss=NULL, int32_t num_iterations=100,
                        float64_t learning_rate=1.0, float64_t subset_fraction=0.6);

    virtual ~CStochasticGBMachine();

    virtual const char* get_name() const { return "StochasticGBMachine"; }

    void set_machine(CMachine* machine);

    CMachine* get_machine() const;

    virtual void set_loss_function(CLossFunction* f);

    virtual CLossFunction* get_loss_function() const;

    void set_num_iterations(int32_t iter);

    int32_t get_num_iterations() const;

    void set_subset_fraction(float64_t frac);

    float64_t get_subset_fraction() const;

    void set_learning_rate(float64_t lr);

    float64_t get_learning_rate() const;

    virtual CRegressionLabels* apply_regression(CFeatures* data=NULL);

protected:
    virtual bool train_machine(CFeatures* data=NULL);

    float64_t compute_multiplier(CRegressionLabels* f, CRegressionLabels* hm);

    CMachine* fit_model(CDenseFeatures<float64_t>* feats, CRegressionLabels* labels);

    CRegressionLabels* compute_pseudo_residuals(CRegressionLabels* inter_f);

    void apply_subset(CDenseFeatures<float64_t>* f, CLabels* interf);

    void initialize_learners();

    float64_t get_gamma(void* instance);

    static float64_t lbfgs_evaluate(void *obj, const float64_t *parameters, float64_t *gradient, const int dim, const float64_t step);

    void init();

protected:
    CMachine* m_machine;

    CLossFunction* m_loss;

    int32_t m_num_iter;

    float64_t m_subset_frac;

    float64_t m_learning_rate;

    CDynamicObjectArray* m_weak_learners;

    CDynamicArray<float64_t>* m_gamma;
};
}/* shogun */

#endif /* _StochasticGBMachine_H__ */