MatchWordStringKernel.cpp

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  * Copyright (C) 1999-2009 Fraunhofer Institute FIRST and Max-Planck-Society
00009  */
00010 
00011 #include "lib/common.h"
00012 #include "lib/Mathematics.h"
00013 #include "lib/io.h"
00014 #include "kernel/MatchWordStringKernel.h"
00015 #include "kernel/AvgDiagKernelNormalizer.h"
00016 #include "features/StringFeatures.h"
00017 
00018 CMatchWordStringKernel::CMatchWordStringKernel(int32_t size, int32_t d)
00019 : CStringKernel<uint16_t>(size), degree(d)
00020 {
00021     set_normalizer(new CAvgDiagKernelNormalizer());
00022 }
00023 
00024 CMatchWordStringKernel::CMatchWordStringKernel(CStringFeatures<uint16_t>* l, CStringFeatures<uint16_t>* r, int32_t d)
00025 : CStringKernel<uint16_t>(10), degree(d)
00026 {
00027     set_normalizer(new CAvgDiagKernelNormalizer());
00028     init(l, r);
00029 }
00030 
00031 CMatchWordStringKernel::~CMatchWordStringKernel()
00032 {
00033     cleanup();
00034 }
00035 
00036 bool CMatchWordStringKernel::init(CFeatures* l, CFeatures* r)
00037 {
00038     CStringKernel<uint16_t>::init(l, r);
00039     return init_normalizer();
00040 }
00041 
00042 bool CMatchWordStringKernel::load_init(FILE* src)
00043 {
00044     return false;
00045 }
00046 
00047 bool CMatchWordStringKernel::save_init(FILE* dest)
00048 {
00049     return false;
00050 }
00051   
00052 float64_t CMatchWordStringKernel::compute(int32_t idx_a, int32_t idx_b)
00053 {
00054     int32_t alen, blen;
00055 
00056     uint16_t* avec=((CStringFeatures<uint16_t>*) lhs)->get_feature_vector(idx_a, alen);
00057     uint16_t* bvec=((CStringFeatures<uint16_t>*) rhs)->get_feature_vector(idx_b, blen);
00058     // can only deal with strings of same length
00059     ASSERT(alen==blen);
00060 
00061     float64_t sum=0;
00062     for (int32_t i=0; i<alen; i++)
00063         sum+= (avec[i]==bvec[i]) ? 1 : 0;
00064 
00065     return CMath::pow(sum, degree);
00066 }

SHOGUN Machine Learning Toolbox - Documentation