OligoStringKernel.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) 2008 Christian Igel, Tobias Glasmachers
 * Copyright (C) 2008 Christian Igel, Tobias Glasmachers
 *
 * Shogun adjustments (W) 2008-2009,2013 Soeren Sonnenburg
 * Copyright (C) 2008-2009 Fraunhofer Institute FIRST and Max-Planck-Society
 * Copyright (C) 2013 Soeren Sonnenburg
 */
#ifndef _OLIGOSTRINGKERNEL_H_
#define _OLIGOSTRINGKERNEL_H_

#include <shogun/kernel/string/StringKernel.h>

#include <vector>
#include <string>

namespace shogun
{
class COligoStringKernel : public CStringKernel<char>
{
    public:
        COligoStringKernel();

        COligoStringKernel(int32_t cache_size, int32_t k, float64_t width);

        COligoStringKernel(
                CStringFeatures<char>* l, CStringFeatures<char>* r,
                int32_t k, float64_t width);

        virtual ~COligoStringKernel();

        virtual bool init(CFeatures* l, CFeatures* r);

        virtual EKernelType get_kernel_type() { return K_OLIGO; }

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


        virtual float64_t compute(int32_t x, int32_t y);

        virtual void cleanup();

    protected:
        static void encodeOligo(
            const std::string& sequence, uint32_t k_mer_length,
            const std::string& allowed_characters,
            std::vector< std::pair<int32_t, float64_t> >&   values);

        static void getSequences(
            const std::vector<std::string>& sequences,
            uint32_t k_mer_length, const std::string& allowed_characters,
            std::vector< std::vector< std::pair<int32_t, float64_t> > >& encoded_sequences);

        float64_t kernelOligoFast(
            const std::vector< std::pair<int32_t, float64_t> >& x,
            const std::vector< std::pair<int32_t, float64_t> >& y,
            int32_t max_distance = -1);

        float64_t kernelOligo(
                const std::vector< std::pair<int32_t, float64_t> >& x, 
                const std::vector< std::pair<int32_t, float64_t> >& y);


    private:
        void getExpFunctionCache(uint32_t sequence_length);

        static inline bool cmpOligos_(std::pair<int32_t, float64_t> a,
                std::pair<int32_t, float64_t> b )
        {
            return (a.second < b.second);
        }

        void init();

    protected:
        int32_t k;
        float64_t width;
        SGVector<float64_t> gauss_table;
};
}
#endif // _OLIGOSTRINGKERNEL_H_