FeatureSelection.h

Go to the documentation of this file.

/*
 * Copyright (c) The Shogun Machine Learning Toolbox
 * Written (w) 2014 Soumyajit De
 * 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 FEATURE_SELECTION_H__
#define FEATURE_SELECTION_H__

#include <shogun/lib/config.h>
#include <shogun/preprocessor/Preprocessor.h>

namespace shogun
{

class CFeatures;
class CLabels;
class CSubsetStack;

enum EFeatureSelectionAlgorithm
{
    BACKWARD_ELIMINATION,
    FORWARD_SELECTION
};

enum EFeatureRemovalPolicy
{
    N_SMALLEST,
    PERCENTILE_SMALLEST,
    N_LARGEST,
    PERCENTILE_LARGEST
};

template <class ST> class CFeatureSelection : public CPreprocessor
{
public:
    CFeatureSelection();

    virtual ~CFeatureSelection();

    virtual CFeatures* apply(CFeatures* features);

    virtual float64_t compute_measures(CFeatures* features, index_t idx)=0;

    virtual CFeatures* remove_feats(CFeatures* features,
            SGVector<index_t> argsorted)=0;

    SGVector<index_t> get_selected_feats();

    virtual EFeatureClass get_feature_class();

    virtual EFeatureType get_feature_type();

    virtual EPreprocessorType get_type() const;

    void set_target_dim(index_t target_dim);

    index_t get_target_dim() const;

    virtual void set_algorithm(EFeatureSelectionAlgorithm algorithm)=0;

    EFeatureSelectionAlgorithm get_algorithm() const;

    virtual void set_policy(EFeatureRemovalPolicy policy)=0;

    EFeatureRemovalPolicy get_policy() const;

    void set_num_remove(index_t num_remove);

    index_t get_num_remove() const;

    virtual void set_labels(CLabels* labels);

    CLabels* get_labels() const;

    virtual void cleanup();

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

protected:
    virtual CFeatures* apply_backward_elimination(CFeatures* features);

    virtual void precompute();

    virtual void adapt_params(CFeatures* features);

    index_t get_num_features(CFeatures* features) const;

    index_t m_target_dim;

    EFeatureSelectionAlgorithm m_algorithm;

    EFeatureRemovalPolicy m_policy;

    index_t m_num_remove;

    CLabels* m_labels;

    CSubsetStack* m_subset;

private:
    void initialize_parameters();

};

}
#endif // FEATURE_SELECTION_H__