HashedSparseFeatures.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) 2013 Evangelos Anagnostopoulos
 * Copyright (C) 2013 Evangelos Anagnostopoulos
 */

#ifndef _HASHED_SPARSEFEATURES_H__
#define _HASHED_SPARSEFEATURES_H__

#include <shogun/features/SparseFeatures.h>
#include <shogun/features/DotFeatures.h>
#include <shogun/lib/SGSparseVector.h>

namespace shogun
{
template <class ST> class CSparseFeatures;
template <class ST> class SGSparseVector;
class CDotFeatures;

template <class ST> class CHashedSparseFeatures  : public CDotFeatures
{
public:

    CHashedSparseFeatures(int32_t size=0, bool use_quadr = false, bool keep_lin_terms = true);

    CHashedSparseFeatures(CSparseFeatures<ST>* feats, int32_t d, bool use_quadr = false,
            bool keep_lin_terms = true);

    CHashedSparseFeatures(SGSparseMatrix<ST> matrix, int32_t d, bool use_quadr = false,
            bool keep_lin_terms = true);

    CHashedSparseFeatures(CFile* loader, int32_t d, bool use_quadr = false,
            bool keep_lin_terms = true);
    
    CHashedSparseFeatures(const CHashedSparseFeatures & orig);

    virtual CFeatures* duplicate() const;

    virtual ~CHashedSparseFeatures();

    virtual int32_t get_dim_feature_space() const;

    virtual float64_t dot(int32_t vec_idx1, CDotFeatures* df,
            int32_t vec_idx2);

    virtual float64_t dense_dot(int32_t vec_idx1, const float64_t* vec2,
            int32_t vec2_len);

    virtual void add_to_dense_vec(float64_t alpha, int32_t vec_idx1,
            float64_t* vec2, int32_t vec2_len, bool abs_val = false);

    virtual int32_t get_nnz_features_for_vector(int32_t num);

    virtual void* get_feature_iterator(int32_t vector_index);

    virtual bool get_next_feature(int32_t& index, float64_t& value,
            void* iterator);

    virtual void free_feature_iterator(void* iterator);

    virtual const char* get_name() const;

    virtual EFeatureType get_feature_type() const;

    virtual EFeatureClass get_feature_class() const;

    virtual int32_t get_num_vectors() const;    

    SGSparseVector<ST> get_hashed_feature_vector(int32_t vec_idx) const;

    static SGSparseVector<ST> hash_vector(SGVector<ST> vec, int32_t dim,
        bool use_quadratic = false, bool keep_linear_terms = true);


    static SGSparseVector<ST> hash_vector(SGSparseVector<ST> vec, int32_t dim,
        bool use_quadratic = false, bool keep_linear_terms = true);

private:
    void init(CSparseFeatures<ST>* feats, int32_t d, bool use_quadr, bool keep_lin_terms);

protected:

    CSparseFeatures<ST>* sparse_feats;

    int32_t dim;

    bool use_quadratic;

    bool keep_linear_terms;
};
}

#endif // _HASHED_SPARSEFEATURES_H__