GaussianNaiveBayes.h

Go to the documentation of this file.

/*
 * 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 3 of the License, or
 * (at your option) any later version.
 *
 * Written (W) 2011 Sergey Lisitsyn
 * Copyright (C) 2011 Berlin Institute of Technology and Max-Planck-Society
 */

#ifndef GAUSSIANNAIVEBAYES_H_
#define GAUSSIANNAIVEBAYES_H_

#include <shogun/machine/Machine.h>
#include <shogun/features/DotFeatures.h>

namespace shogun {

class CLabels;
class CDotFeatures;
class CFeatures;

class CGaussianNaiveBayes : public CMachine
{

public:
    CGaussianNaiveBayes();

    CGaussianNaiveBayes(CFeatures* train_examples, CLabels* train_labels);

    virtual ~CGaussianNaiveBayes();

    virtual inline void set_features(CDotFeatures* features)
    {
         SG_UNREF(m_features);
         SG_REF(features);
         m_features = features;
    }

    virtual inline CDotFeatures* get_features()
    {
        SG_REF(m_features);
        return m_features;
    }

    virtual bool train(CFeatures* data = NULL);

    virtual CLabels* apply();

    virtual CLabels* apply(CFeatures* data);

    virtual float64_t apply(int32_t idx);

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

    virtual inline EClassifierType get_classifier_type() { return CT_GAUSSIANNAIVEBAYES; };

protected:

    CDotFeatures* m_features;

    int32_t m_min_label;

    int32_t m_num_classes;

    int32_t m_dim;

    SGVector<float64_t> m_means;

    SGVector<float64_t> m_variances;

    SGVector<float64_t> m_label_prob;

    float64_t inline normal_exp(float64_t x, int32_t l_idx, int32_t f_idx)
    {
        return CMath::exp(-CMath::sq(x-m_means.vector[m_dim*l_idx+f_idx])/(2*m_variances.vector[m_dim*l_idx+f_idx]));
    }

    SGVector<float64_t> m_rates;
};

}

#endif /* GAUSSIANNAIVEBAYES_H_ */