HashedWDFeaturesTransposed.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) 2010 Soeren Sonnenburg
 * Copyright (C) 2010 Berlin Institute of Technology
 */

#ifndef _HASHEDWDFEATURESTRANSPOSED_H___
#define _HASHEDWDFEATURESTRANSPOSED_H___

#include <shogun/lib/common.h>
#include <shogun/features/DotFeatures.h>
#include <shogun/features/StringFeatures.h>
#include <shogun/lib/Hash.h>

namespace shogun
{
template <class ST> class CStringFeatures;

class CHashedWDFeaturesTransposed : public CDotFeatures
{
    public:
        CHashedWDFeaturesTransposed();

        CHashedWDFeaturesTransposed(CStringFeatures<uint8_t>* str, int32_t start_order,
                int32_t order,  int32_t from_order, int32_t hash_bits=12);

        CHashedWDFeaturesTransposed(const CHashedWDFeaturesTransposed & orig);

        virtual ~CHashedWDFeaturesTransposed();

        virtual int32_t get_dim_feature_space() const
        {
            return w_dim;
        }

        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 dense_dot_range(float64_t* output, int32_t start, int32_t stop, float64_t* alphas, float64_t* vec, int32_t dim, float64_t b);

        virtual void dense_dot_range_subset(int32_t* sub_index, int32_t num, float64_t* output, float64_t* alphas, float64_t* vec, int32_t dim, float64_t b);


        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)
        {
            return w_dim/alphabet_size;
        }

        virtual CFeatures* duplicate() const;

        virtual EFeatureType get_feature_type() const
        {
            return F_UNKNOWN;
        }

        virtual EFeatureClass get_feature_class() const
        {
            return C_WD;
        }

        virtual int32_t get_num_vectors() const
        {
            return num_strings;
        }

        void set_normalization_const(float64_t n=0);

        inline float64_t get_normalization_const()
        {
            return normalization_const;
        }

        #ifndef DOXYGEN_SHOULD_SKIP_THIS

        struct hashed_wd_transposed_feature_iterator
        {
            uint16_t* vec;
            int32_t vidx;
            int32_t vlen;
            bool vfree;

            int32_t index;

        };
        #endif

        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 { return "HashedWDFeaturesTransposed"; }

    protected:

        void set_wd_weights();
        static void* dense_dot_range_helper(void* p);

    protected:
        CStringFeatures<uint8_t>* strings;

        SGString<uint8_t>* transposed_strings;

        int32_t degree;
        int32_t start_degree;
        int32_t from_degree;
        int32_t string_length;
        int32_t num_strings;
        int32_t alphabet_size;
        int32_t w_dim;
        int32_t partial_w_dim;
        float64_t* wd_weights;
        uint32_t mask;
        int32_t m_hash_bits;

        float64_t normalization_const;
};
}
#endif // _HASHEDWDFEATURESTRANSPOSED_H___