SpectrumMismatchRBFKernel.h

Go to the documentation of this file.
00001 /*
00002  * This program is free software; you can redistribute it and/or modify
00003  * it under the terms of the GNU General Public License as published by
00004  * the Free Software Foundation; either version 3 of the License, or
00005  * (at your option) any later version.
00006  *
00007  * Written (W) 1999-2009 Soeren Sonnenburg
00008  * Written (W) 1999-2008 Gunnar Raetsch
00009  * Copyright (C) 1999-2009 Fraunhofer Institute FIRST and Max-Planck-Society
00010  */
00011 
00012 #ifndef _SPECTRUMMISMATCHRBFKERNEL_H___
00013 #define _SPECTRUMMISMATCHRBFKERNEL_H___
00014 
00015 #include <shogun/lib/common.h>
00016 #include <shogun/lib/Trie.h>
00017 #include <shogun/kernel/StringKernel.h>
00018 #include <shogun/features/StringFeatures.h>
00019 
00020 
00021 #include <shogun/lib/Array.h>
00022 #include <shogun/lib/Array2.h>
00023 #include <string>
00024 
00025 namespace shogun
00026 {
00027 
00028 #ifndef DOXYGEN_SHOULD_SKIP_THIS
00029 
00030 struct joint_list_struct
00031 {
00033     unsigned int ex_index;
00035     unsigned int index;
00037     unsigned int mismatch;
00038 };
00039 #endif
00040 
00042 class CSpectrumMismatchRBFKernel: public CStringKernel<char>
00043 {
00044     public:
00046         CSpectrumMismatchRBFKernel();
00047 
00058         CSpectrumMismatchRBFKernel(int32_t size, float64_t* AA_matrix_, int32_t nr_, int32_t nc_, int32_t degree, int32_t max_mismatch, float64_t width);
00059 
00072         CSpectrumMismatchRBFKernel(
00073                                    CStringFeatures<char>* l, CStringFeatures<char>* r, 
00074                            int32_t size, float64_t* AA_matrix_, int32_t nr_, 
00075                            int32_t nc_, int32_t degree, int32_t max_mismatch, float64_t width);
00076 
00078         virtual ~CSpectrumMismatchRBFKernel();
00079 
00086         virtual bool init(CFeatures* l, CFeatures* r);
00087 
00089         virtual void cleanup();
00090 
00095         virtual EKernelType get_kernel_type() { return K_SPECTRUMMISMATCHRBF; }
00096 
00101         virtual const char* get_name() const { return "SpectrumMismatchRBFKernel"; }
00102 
00108         bool set_max_mismatch(int32_t max);
00109 
00114         inline int32_t get_max_mismatch() const { return max_mismatch; }
00115 
00121         inline bool set_degree(int32_t deg) { degree=deg; return true; }
00122 
00127         inline int32_t get_degree() const { return degree; }
00128 
00135         bool set_AA_matrix(float64_t* AA_matrix_=NULL, int32_t nr=128, int32_t nc=128);
00136 
00137     protected:
00138 
00145         float64_t AA_helper(std::string &path, const char* joint_seq, unsigned int index);
00146 
00156         float64_t compute_helper(const char* joint_seq, 
00157                                  std::vector<unsigned int> joint_index, std::vector<unsigned int> joint_mismatch, 
00158                                  std::string path, unsigned int d, 
00159                                  const int & alen) ;
00160 
00168         void compute_helper_all(const char* joint_seq, 
00169                                 std::vector<struct joint_list_struct> & joint_list,
00170                                 std::string path, unsigned int d);
00171 
00173         void compute_all();
00174 
00183         float64_t compute(int32_t idx_a, int32_t idx_b);
00184 
00186         virtual void remove_lhs();
00189         virtual void register_params();
00192         void register_alphabet();
00193 
00194 
00195     protected:
00197         CAlphabet* alphabet;
00199         int32_t degree;
00201         int32_t max_mismatch;
00203         float64_t* AA_matrix;
00205         int32_t AA_matrix_length;
00207         float64_t width;
00208 
00210         bool initialized;
00211 
00213         CArray2<float64_t> kernel_matrix ;
00215         int32_t kernel_matrix_length;
00217         int32_t target_letter_0;
00218     
00219     private:
00220         void init();
00221 };
00222 
00223 }
00224 
00225 #endif /* _SPECTRUMMISMATCHRBFKERNEL_H__ */
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines

SHOGUN Machine Learning Toolbox - Documentation