SNPFeatures.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 _SNPFEATURES_H___
#define _SNPFEATURES_H___

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

namespace shogun
{
template <class ST> class CStringFeatures;

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

        CSNPFeatures(CStringFeatures<uint8_t>* str);

        CSNPFeatures(const CSNPFeatures & orig);

        virtual ~CSNPFeatures();

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

        virtual inline int32_t get_nnz_features_for_vector(int32_t num)
        {
            return w_dim/3;
        }

        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 CFeatures* duplicate() const;

        inline virtual EFeatureType get_feature_type()
        {
            return F_UNKNOWN;
        }

        inline virtual EFeatureClass get_feature_class()
        {
            return C_WD;
        }

        inline virtual int32_t get_num_vectors() const
        {
            return num_strings;
        }

        inline virtual int32_t get_size()
        {
            return sizeof(float64_t);
        }

        void set_normalization_const(float64_t n=0);

        inline float64_t get_normalization_const()
        {
            return normalization_const;
        }

        void set_minor_base_string(const char* str)
        {
            m_str_min=(uint8_t*) strdup(str);
        }


        void set_major_base_string(const char* str)
        {
            m_str_maj=(uint8_t*) strdup(str);
        }


        char* get_minor_base_string()
        {
            return (char*) m_str_min;
        }


        char* get_major_base_string()
        {
            return (char*) m_str_maj;
        }

        void obtain_base_strings(CSNPFeatures* snp=NULL);

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

        virtual SGMatrix<float64_t> get_histogram(bool normalize=true);

        static SGMatrix<float64_t> get_2x3_table(CSNPFeatures* pos, CSNPFeatures* neg);

    private:
        void find_minor_major_strings(uint8_t* minor, uint8_t* major);

    protected:
        CStringFeatures<uint8_t>* strings;

        int32_t string_length;
        int32_t num_strings;
        int32_t w_dim;

        float64_t normalization_const;

        uint8_t* m_str_min;
        uint8_t* m_str_maj;

};
}
#endif // _SNPFEATURES_H___