毕业设计（三）

这次我们分析SVM.h和USEsvm.h

在开头我想放一篇参考文献点击打开链接

<strong>#ifndef _LIBSVM_H //条件编译指令#define _LIBSVM_H#define LIBSVM_VERSION 289 //定义libsvm版本2.89#ifdef __cplusplusextern "C" {#endifextern int libsvm_version;struct svm_node{int index;  //</strong>索引值<strong>double value; //</strong>定义一个值<strong>};struct svm_problem //</strong><span style="color: rgb(51, 51, 51);font-size:12px; line-height: 26px; font-family: 宋体;">其中“</span><span style="color: rgb(51, 51, 51); font-family: Arial;font-size:12px; line-height: 26px;"><span style="font-family: 'Times New Roman';">l</span></span><span style="color: rgb(51, 51, 51);font-size:12px; line-height: 26px; font-family: 宋体;">”表示训练数据的实例数，而“</span><span style="color: rgb(51, 51, 51); font-family: Arial;font-size:12px; line-height: 26px;"><span style="font-family: 'Times New Roman';">y</span></span><span style="color: rgb(51, 51, 51);font-size:12px; line-height: 26px; font-family: 宋体;">”是一个数组，用于存放它们的目标值。（类型值用整型数据，回归值用实数）“                                 </span><span style="color: rgb(51, 51, 51); font-family: Arial;font-size:12px; line-height: 26px;"><span style="font-family: 'Times New Roman';">x</span></span><span style="color: rgb(51, 51, 51);font-size:12px; line-height: 26px; font-family: 宋体;">”是一个数组指针，每一个指针指向一个稀疏的训练向量（即一个</span><span style="color: rgb(51, 51, 51); font-family: Arial;font-size:12px; line-height: 26px;"><span style="font-family: 'Times New Roman';">svm_node</span></span><span style="color: rgb(51, 51, 51);font-size:12px; line-height: 26px; font-family: 宋体;">数组）。</span><strong>{int l;double *y;struct svm_node **x;};// Added by Jianxin Wu for AUC <a target=_blank href="http://http://www.cnblogs.com/lixiaolun/p/4053499.html">点击打开链接</a>struct RECORD{    int y;     double v;};int compare(const void* a,const void* b); //比较double ComputeAUC(struct RECORD* record,const int tcount); //计算AUC，需要了解的话，可以查看上面的超链接// End of AUCenum { C_SVC, NU_SVC, ONE_CLASS, EPSILON_SVR, NU_SVR };/* svm_type */ //枚举类/* The enum value "HIK" is added by Jianxin Wu, for histogram intersection kernel */enum { LINEAR, POLY, RBF, SIGMOID, PRECOMPUTED, HIK }; /* kernel_type */struct svm_parameter{int svm_type;int kernel_type;int degree;/* for poly */double gamma;/* for poly/rbf/sigmoid */double coef0;/* for poly/sigmoid *//* these are for training only */double cache_size; /* in MB */double eps;/* stopping criteria */double C;/* for C_SVC, EPSILON_SVR and NU_SVR */int nr_weight;/* for C_SVC */int *weight_label;/* for C_SVC */double* weight;/* for C_SVC */double nu;/* for NU_SVC, ONE_CLASS, and NU_SVR */double p;/* for EPSILON_SVR */int shrinking;/* use the shrinking heuristics */int probability; /* do probability estimates */};// This is moved from svm.cpp by Jianxin Wu//// svm_model//struct svm_model{svm_parameter param;// parameterint nr_class;// number of classes, = 2 in regression/one class svmint l;// total #SVsvm_node **SV;// SVs (SV[l])double **sv_coef;// coefficients for SVs in decision functions (sv_coef[k-1][l])double *rho;// constants in decision functions (rho[k*(k-1)/2])double *probA;// pariwise probability informationdouble *probB;// for classification onlyint *label;// label of each class (label[k])int *nSV;// number of SVs for each class (nSV[k])// nSV[0] + nSV[1] + ... + nSV[k-1] = l// XXXint free_sv;// 1 if svm_model is created by svm_load_model// 0 if svm_model is created by svm_train};struct svm_model *svm_train(const struct svm_problem *prob, const struct svm_parameter *param);void svm_cross_validation(const struct svm_problem *prob, const struct svm_parameter *param, int nr_fold, double *target);int svm_save_model(const char *model_file_name, const struct svm_model *model);struct svm_model *svm_load_model(const char *model_file_name);// This line added by Jianxin Wu for loading BSVM modelstruct svm_model *bsvm_load_model(const char *model_file_name);// Added by Jianxin for computing the positive/negative response separatelydouble kernel_eval_func(const svm_node *x,const svm_node *y,const svm_parameter& param);int svm_get_svm_type(const struct svm_model *model);int svm_get_nr_class(const struct svm_model *model);void svm_get_labels(const struct svm_model *model, int *label);double svm_get_svr_probability(const struct svm_model *model);void svm_predict_values(const struct svm_model *model, const struct svm_node *x, double* dec_values);double svm_predict(const struct svm_model *model, const struct svm_node *x);double svm_predict_probability(const struct svm_model *model, const struct svm_node *x, double* prob_estimates);void svm_destroy_model(struct svm_model *model);void svm_destroy_param(struct svm_parameter *param);const char *svm_check_parameter(const struct svm_problem *prob, const struct svm_parameter *param);int svm_check_probability_model(const struct svm_model *model);extern void (*svm_print_string) (const char *);#ifdef __cplusplus}#endif#endif /* _LIBSVM_H */</strong>

上面是svm，在开头的超链接中的文章已经讲得很清楚了

#ifndef __USE_SVM__#define __USE_SVM__#include <set>#include <string>#include "svm.h"// LIBSVM的接口函数// 给SVM设置默认参数值// 在调用该函数后，你需要改变某些参数的值void UseSVM_Init(svm_parameter& param,svm_problem& prob,svm_node* &x_space);// 清空SVM相关的数据，结构体。为下一次使用void UseSVM_CleanUp(svm_model* &model,svm_parameter& param,svm_problem& prob,svm_node* &x_space);// 转换一个二维矩阵// 函数定义在后面的.H文件中template<class T>int UseSVM_BuildProblem(                        Array2d<T> data, // 数据                        const int* labels, // 数据点标签                        std::set<int>& choose, // 指定分级                        svm_problem& prob, // 输出问题，在调用之前，需要清空数据                        svm_node* &x_space, // 在函数调用前需要设置为NULL                        const bool oneclass, // 是否我们想要训练一级？                        const int maxElement = -1 // constrain SVM problem size to 'maxElement' if it is >0                       );// Data structure for fast computing of several histogram kernel discrimination functions (\phi(x) \dotproduct w) - \rho// return value is -1.0*\rho// for use in visual codebook onlydouble UseSVM_Histogram_FastEvaluationStructure(                        const svm_model& model, // one SVM trained model                        const int m, // length of feature vector                        const int upper_bound, // maximum feature value can only be upper_bound - 1（最大为最大值减一）                        Array2d<double>& eval, // fast data structure                        const int index // which discrimination function is this? (or, which visual code word?)                                               );// Convert a HIK libsvm model into 'eval' so that testing is fast（加速测试）double UseSVM_Histogram_FastEvaluationStructure(const svm_model& model,const int m,const int upper_bound,Array2dC<double>& eval,const bool normalize);// Load libsvm model from file and convert to 'eval'（加载到矩阵Array2dC中）// If pmodel==NULL, then the loaded libsvm model is destroyed immediately, otherwise it is returned by pmodel -- you need to destroy itdouble UseSVM_Histogram_FastEvaluationStructure(const char* modelfile,const int m,const int upper_bound,Array2dC<double>& eval,svm_model** pmodel=NULL,const bool normalize=true);// Convert a HIK bsvm model into 'eval' so that testing is fast（和上面的一样）double UseSVM_Histogram_FastEvaluationStructure(const char* modelfile,const int m,const int upper_bound,Array2dC<double>& eval,svm_model** pmodel,const bool normalize);// Load bsvm model from file and convert to 'eval'// If pmodel==NULL, then the loaded libsvm model is destroyed immediately, otherwise it is returned by pmodel -- you need to destroy it// For the Crammer-Sinnger (-s 2) and HIK (-t 5) only（这个是什么鬼）double UseSVM_CS_Histogram_FastEvaluationStructure(const char* modelfile,const int m,const int upper_bound,Array2dC<double>& eval,svm_model** pmodel);// Data structure for fast computing of several linear kernel discrimination functions (\phi(x) \dotproduct w) - \rho// return value is -1.0*\rhodouble UseSVM_Linear_FastEvaluationStructure(                        const svm_model& model, // one SVM trained model                        const int m, // length of feature vector                        Array2d<double>& result, // fast data structure                        const int index // which discrimination function is this?                                             );double UseSVM_Linear_FastEvaluationStructure(const svm_model& model,const int m,Array2dC<double>& eval);double UseSVM_Linear_FastEvaluationStructure(const char* modelfile,const int m,Array2dC<double>& result);// save a data set in the sparse SVM format to 'filename' with class labels in 'labels' and data in 'features' (1 row <==> a data point)// NOTE that feature index will start from 1, not 0void UseSVM_SaveSparse(const std::string& filename,const int* labels,Array2d<double>& features);// 'split' should have same length as labels, and a point i is saved only if split[i]==valuevoid UseSVM_SaveSparse(const std::string& filename,const int* labels,Array2d<double>& features,const int* split,const int value);

（目前还是看不懂，先放着赶进度，后面再来看）template<class T>int UseSVM_BuildProblem(Array2d<T> data,const int* labels,std::set<int>& choose,svm_problem& prob,svm_node* &x_space,const bool oneclass,const int maxElement){    assert(prob.l==0 && prob.y==NULL && prob.x==NULL && x_space==NULL);    int size = 0;    for(int i=0;i<data.nrow;i++) 

      if(choose.find(labels[i])!=choose.end()) size++;    if(size==0) return 0;    if(maxElement>0 && size>maxElement) size = maxElement;    prob.l = size;    prob.y = new double[prob.l]; assert(prob.y!=NULL);    prob.x = new svm_node*[prob.l]; assert(prob.x!=NULL);    int totalfeatures = 0;    int added_points = 0;    for(int i=0;i<data.nrow;i++)    {        if(choose.find(labels[i])==choose.end()) continue;        for(int j=0;j<data.ncol;j++) if(data.p[i][j]!=0) totalfeatures++;        added_points++;        if(maxElement>0 && added_points>=maxElement) break;    }    x_space = new svm_node[totalfeatures+prob.l]; assert(x_space!=NULL);    added_points=0;    int added_features=0;    for(int i=0;i<data.nrow;i++)    {        if(choose.find(labels[i])==choose.end()) continue;        if(oneclass)            prob.y[added_points] = 1;        else            prob.y[added_points] = labels[i];        prob.x[added_points] = &x_space[added_features];        for(int j=0;j<data.ncol;j++)        {            if(data.p[i][j]==0) continue;            x_space[added_features].index = j + 1;            x_space[added_features].value = data.p[i][j];            added_features++;        }        x_space[added_features].index = -1;        added_features++;        added_points++;        if(maxElement>0 && added_points>=maxElement) break;    }    assert(added_points==size);    assert(added_features==totalfeatures+prob.l);    return size;}#endif // __USE_SVM__