CARTree.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 _CARTREE_H__
#define _CARTREE_H__

#include <shogun/lib/config.h>

#include <shogun/multiclass/tree/TreeMachine.h>
#include <shogun/multiclass/tree/CARTreeNodeData.h>
#include <shogun/features/DenseFeatures.h>

namespace shogun
{

class CCARTree : public CTreeMachine<CARTreeNodeData>
{
public:
    CCARTree();

    CCARTree(SGVector<bool> attribute_types, EProblemType prob_type=PT_MULTICLASS);

    CCARTree(SGVector<bool> attribute_types, EProblemType prob_type, int32_t num_folds, bool cv_prune);

    virtual ~CCARTree();

    virtual void set_labels(CLabels* lab);

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

    virtual EProblemType get_machine_problem_type() const { return m_mode; }

    void set_machine_problem_type(EProblemType mode);

    virtual bool is_label_valid(CLabels* lab) const;

    virtual CMulticlassLabels* apply_multiclass(CFeatures* data=NULL);

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

    void prune_using_test_dataset(CDenseFeatures<float64_t>* feats, CLabels* gnd_truth, SGVector<float64_t> weights=SGVector<float64_t>());

    void set_weights(SGVector<float64_t> w);

    SGVector<float64_t> get_weights() const;

    void clear_weights();

    void set_feature_types(SGVector<bool> ft);

    SGVector<bool> get_feature_types() const;

    void clear_feature_types();

    int32_t get_num_folds() const;

    void set_num_folds(int32_t folds);

    int32_t get_max_depth() const;

    void set_max_depth(int32_t depth);

    int32_t get_min_node_size() const;

    void set_min_node_size(int32_t nsize);

    void set_cv_pruning() { m_apply_cv_pruning=true; }

    void unset_cv_pruning() { m_apply_cv_pruning=false; }

     float64_t get_label_epsilon() { return m_label_epsilon; }

     void set_label_epsilon(float64_t epsilon);

    void pre_sort_features(CFeatures* data, SGMatrix<float64_t>& sorted_feats, SGMatrix<index_t>& sorted_indices);
     
    void set_sorted_features(SGMatrix<float64_t>& sorted_feats, SGMatrix<index_t>& sorted_indices);

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

    virtual CBinaryTreeMachineNode<CARTreeNodeData>* CARTtrain(CFeatures* data, SGVector<float64_t> weights, CLabels* labels, int32_t level);

    SGVector<float64_t> get_unique_labels(SGVector<float64_t> labels_vec, int32_t &n_ulabels);

    virtual int32_t compute_best_attribute(const SGMatrix<float64_t>& mat, const SGVector<float64_t>& weights, CLabels* labels,
        SGVector<float64_t>& left, SGVector<float64_t>& right, SGVector<bool>& is_left_final, int32_t &num_missing,
        int32_t &count_left, int32_t &count_right, int32_t subset_size=0, const SGVector<int32_t>& active_indices=SGVector<index_t>());


    SGVector<bool> surrogate_split(SGMatrix<float64_t> data, SGVector<float64_t> weights, SGVector<bool> nm_left, int32_t attr);


    void handle_missing_vecs_for_continuous_surrogate(SGMatrix<float64_t> m, CDynamicArray<int32_t>* missing_vecs,
        CDynamicArray<float64_t>* association_index, CDynamicArray<int32_t>* intersect_vecs, SGVector<bool> is_left,
                                    SGVector<float64_t> weights, float64_t p, int32_t attr);

    void handle_missing_vecs_for_nominal_surrogate(SGMatrix<float64_t> m, CDynamicArray<int32_t>* missing_vecs,
        CDynamicArray<float64_t>* association_index, CDynamicArray<int32_t>* intersect_vecs, SGVector<bool> is_left,
                                    SGVector<float64_t> weights, float64_t p, int32_t attr);

    float64_t gain(SGVector<float64_t> wleft, SGVector<float64_t> wright, SGVector<float64_t> wtotal, SGVector<float64_t> labels);

    float64_t gain(const SGVector<float64_t>& wleft, const SGVector<float64_t>& wright, const SGVector<float64_t>& wtotal);

    float64_t gini_impurity_index(const SGVector<float64_t>& weighted_lab_classes, float64_t &total_weight);

    float64_t least_squares_deviation(const SGVector<float64_t>& labels, const SGVector<float64_t>& weights, float64_t &total_weight);

    CLabels* apply_from_current_node(CDenseFeatures<float64_t>* feats, bnode_t* current);

    void prune_by_cross_validation(CDenseFeatures<float64_t>* data, int32_t folds);

    float64_t compute_error(CLabels* labels, CLabels* reference, SGVector<float64_t> weights);

    CDynamicObjectArray* prune_tree(CTreeMachine<CARTreeNodeData>* tree);

    float64_t find_weakest_alpha(bnode_t* node);

    void cut_weakest_link(bnode_t* node, float64_t alpha);

    void form_t1(bnode_t* node);

    void init();


public:
    static const float64_t MISSING;

    static const float64_t MIN_SPLIT_GAIN;

    static const float64_t EQ_DELTA;

protected:
    float64_t m_label_epsilon;

    SGVector<bool> m_nominal;

    SGVector<float64_t> m_weights;

    SGMatrix<float64_t> m_sorted_features;

    SGMatrix<index_t> m_sorted_indices;

    bool m_pre_sort;

    bool m_types_set;

    bool m_weights_set;

    bool m_apply_cv_pruning;

    int32_t m_folds;

    EProblemType m_mode;

    CDynamicArray<float64_t>* m_alphas;

    int32_t m_max_depth;

    int32_t m_min_node_size;
};
} /* namespace shogun */

#endif /* _CARTREE_H__ */