最新SVM实现（C++,java,python）

【实例简介】libsvm是由台湾大学林智仁(Lin Chih-Jen)教授开发的一款简单易用、快速有效的SVM模式识别与回归的软件包。这套库运算速度还是挺快的，可以很方便的对数据做分类或回归。由于libSVM程序小，运用灵活，输入参数少，并且是开源的，易于扩展，因此成为目前国内应用最多的SVM的库。
libsvm不但提供了编译好的可在Windows系列系统的执行文件，还提供了源代码，方便改进、修改以及在其它操作系统上应用；libsvm对SVM所涉及的参数调节相对比较少，提供了很多的默认参数，利用这些默认参数可以解决很多问题；并提供了交互检验(Cross Validation)的功能，可以解决C-SVM、ν-SVM、ε-SVR和ν-SVR等问题，包括基于一对一算法的多类模式识别问题。
为了方便大家体验，多多小编为大家提供最新版的libsvm程序下载，该软件包以源代码和可执行文件两种方式给出的。如果是Windows系列操作系统，可以直接使用软件包提供的程序，也可以进行修改编译；如果是Unix类系统，必须自己编译，软件包中提供了编译格式文件，在SGI工作站（操作系统IRⅨ6.5）上，使用免费编译器GNU C 3.3编译通过，有需求的朋友请下载使用。下载软件压缩包，解压，可以看到libsvm可分为5个文件夹和一些c 源码文件，其详细说明如下：
1、Java——主要是应用于java平台；
2、Python——是用来参数优选的工具，稍后介绍；
3、svm-toy——一个可视化的工具，用来展示训练数据和分类界面，里面是源码，其编译后的程序在windows文件夹下；
4、tools——主要包含四个python文件，用来数据集抽样(subset)，参数优选（grid），集成测试(easy),数据检查(checkdata)；
5、windows——包含libSVM四个exe程序包，我们所用的库就是他们，里面还有个heart_scale，是一个样本文件，可以用记事本打开，用来测试用的。
6、其他.h和.cpp文件都是程序的源码，可以编译出相应的.exe文件。其中，最重要的是svm.h和svm.cpp文件，svm-predict.c、svm-scale.c和svm-train.c（还有一个svm-toy.c在svm-toy文件夹中）都是调用的这个文件中的接口函数，编译后就是windows下相应的四个exe程序。
7、另外，里面的 README 跟 FAQ也是很好的文件，对于初学者如果E文过得去，可以看一下。

【实例截图】

【核心代码】#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include <errno.h>
#include "svm.h"
#define Malloc(type,n) (type *)malloc((n)*sizeof(type))

void print_null(const char *s) {}

void exit_with_help()
{
printf(
"Usage: svm-train [options] training_set_file [model_file]\n"
"options:\n"
"-s svm_type : set type of SVM (default 0)\n"
" 0 -- C-SVC (multi-class classification)\n"
" 1 -- nu-SVC (multi-class classification)\n"
" 2 -- one-class SVM\n"
" 3 -- epsilon-SVR (regression)\n"
" 4 -- nu-SVR (regression)\n"
"-t kernel_type : set type of kernel function (default 2)\n"
" 0 -- linear: u'*v\n"
" 1 -- polynomial: (gamma*u'*v coef0)^degree\n"
" 2 -- radial basis function: exp(-gamma*|u-v|^2)\n"
" 3 -- sigmoid: tanh(gamma*u'*v coef0)\n"
" 4 -- precomputed kernel (kernel values in training_set_file)\n"
"-d degree : set degree in kernel function (default 3)\n"
"-g gamma : set gamma in kernel function (default 1/num_features)\n"
"-r coef0 : set coef0 in kernel function (default 0)\n"
"-c cost : set the parameter C of C-SVC, epsilon-SVR, and nu-SVR (default 1)\n"
"-n nu : set the parameter nu of nu-SVC, one-class SVM, and nu-SVR (default 0.5)\n"
"-p epsilon : set the epsilon in loss function of epsilon-SVR (default 0.1)\n"
"-m cachesize : set cache memory size in MB (default 100)\n"
"-e epsilon : set tolerance of termination criterion (default 0.001)\n"
"-h shrinking : whether to use the shrinking heuristics, 0 or 1 (default 1)\n"
"-b probability_estimates : whether to train a SVC or SVR model for probability estimates, 0 or 1 (default 0)\n"
"-wi weight : set the parameter C of class i to weight*C, for C-SVC (default 1)\n"
"-v n: n-fold cross validation mode\n"
"-q : quiet mode (no outputs)\n"
);
exit(1);
}

void exit_input_error(int line_num)
{
fprintf(stderr,"Wrong input format at line %d\n", line_num);
exit(1);
}

void parse_command_line(int argc, char **argv, char *input_file_name, char *model_file_name);
void read_problem(const char *filename);
void do_cross_validation();

struct svm_parameter param; // set by parse_command_line
struct svm_problem prob; // set by read_problem
struct svm_model *model;
struct svm_node *x_space;
int cross_validation;
int nr_fold;

static char *line = NULL;
static int max_line_len;

static char* readline(FILE *input)
{
int len;

if(fgets(line,max_line_len,input) == NULL)
return NULL;

while(strrchr(line,'\n') == NULL)
{
max_line_len *= 2;
line = (char *) realloc(line,max_line_len);
len = (int) strlen(line);
if(fgets(line len,max_line_len-len,input) == NULL)
break;
}
return line;
}

int main(int argc, char **argv)
{
char input_file_name[1024];
char model_file_name[1024];
const char *error_msg;

parse_command_line(argc, argv, input_file_name, model_file_name);
read_problem(input_file_name);
error_msg = svm_check_parameter(&prob,&param);

if(error_msg)
{
fprintf(stderr,"ERROR: %s\n",error_msg);
exit(1);
}

if(cross_validation)
{
do_cross_validation();
}
else
{
model = svm_train(&prob,&param);
if(svm_save_model(model_file_name,model))
{
fprintf(stderr, "can't save model to file %s\n", model_file_name);
exit(1);
}
svm_free_and_destroy_model(&model);
}
svm_destroy_param(&param);
free(prob.y);
free(prob.x);
free(x_space);
free(line);

return 0;
}

void do_cross_validation()
{
int i;
int total_correct = 0;
double total_error = 0;
double sumv = 0, sumy = 0, sumvv = 0, sumyy = 0, sumvy = 0;
double *target = Malloc(double,prob.l);

svm_cross_validation(&prob,&param,nr_fold,target);
if(param.svm_type == EPSILON_SVR ||
   param.svm_type == NU_SVR)
{
for(i=0;i<prob.l;i )
{
double y = prob.y[i];
double v = target[i];
total_error = (v-y)*(v-y);
sumv = v;
sumy = y;
sumvv = v*v;
sumyy = y*y;
sumvy = v*y;
}
printf("Cross Validation Mean squared error = %g\n",total_error/prob.l);
printf("Cross Validation Squared correlation coefficient = %g\n",
((prob.l*sumvy-sumv*sumy)*(prob.l*sumvy-sumv*sumy))/
((prob.l*sumvv-sumv*sumv)*(prob.l*sumyy-sumy*sumy))
);
}
else
{
for(i=0;i<prob.l;i )
if(target[i] == prob.y[i])
total_correct;
printf("Cross Validation Accuracy = %g%%\n",100.0*total_correct/prob.l);
}
free(target);
}

void parse_command_line(int argc, char **argv, char *input_file_name, char *model_file_name)
{
int i;
void (*print_func)(const char*) = NULL; // default printing to stdout

// default values
param.svm_type = C_SVC;
param.kernel_type = RBF;
param.degree = 3;
param.gamma = 0; // 1/num_features
param.coef0 = 0;
param.nu = 0.5;
param.cache_size = 100;
param.C = 1;
param.eps = 1e-3;
param.p = 0.1;
param.shrinking = 1;
param.probability = 0;
param.nr_weight = 0;
param.weight_label = NULL;
param.weight = NULL;
cross_validation = 0;

// parse options
for(i=1;i<argc;i )
{
if(argv[i][0] != '-') break;
if( i>=argc)
exit_with_help();
switch(argv[i-1][1])
{
case 's':
param.svm_type = atoi(argv[i]);
break;
case 't':
param.kernel_type = atoi(argv[i]);
break;
case 'd':
param.degree = atoi(argv[i]);
break;
case 'g':
param.gamma = atof(argv[i]);
break;
case 'r':
param.coef0 = atof(argv[i]);
break;
case 'n':
param.nu = atof(argv[i]);
break;
case 'm':
param.cache_size = atof(argv[i]);
break;
case 'c':
param.C = atof(argv[i]);
break;
case 'e':
param.eps = atof(argv[i]);
break;
case 'p':
param.p = atof(argv[i]);
break;
case 'h':
param.shrinking = atoi(argv[i]);
break;
case 'b':
param.probability = atoi(argv[i]);
break;
case 'q':
print_func = &print_null;
i--;
break;
case 'v':
cross_validation = 1;
nr_fold = atoi(argv[i]);
if(nr_fold < 2)
{
fprintf(stderr,"n-fold cross validation: n must >= 2\n");
exit_with_help();
}
break;
case 'w':
param.nr_weight;
param.weight_label = (int *)realloc(param.weight_label,sizeof(int)*param.nr_weight);
param.weight = (double *)realloc(param.weight,sizeof(double)*param.nr_weight);
param.weight_label[param.nr_weight-1] = atoi(&argv[i-1][2]);
param.weight[param.nr_weight-1] = atof(argv[i]);
break;
default:
fprintf(stderr,"Unknown option: -%c\n", argv[i-1][1]);
exit_with_help();
}
}

svm_set_print_string_function(print_func);

// determine filenames

if(i>=argc)
exit_with_help();

strcpy(input_file_name, argv[i]);

if(i<argc-1)
strcpy(model_file_name,argv[i 1]);
else
{
char *p = strrchr(argv[i],'/');
if(p==NULL)
p = argv[i];
else
p;
sprintf(model_file_name,"%s.model",p);
}
}

// read in a problem (in svmlight format)

void read_problem(const char *filename)
{
int elements, max_index, inst_max_index, i, j;
FILE *fp = fopen(filename,"r");
char *endptr;
char *idx, *val, *label;

if(fp == NULL)
{
fprintf(stderr,"can't open input file %s\n",filename);
exit(1);
}

prob.l = 0;
elements = 0;

max_line_len = 1024;
line = Malloc(char,max_line_len);
while(readline(fp)!=NULL)
{
char *p = strtok(line," \t"); // label

// features
while(1)
{
p = strtok(NULL," \t");
if(p == NULL || *p == '\n') // check '\n' as ' ' may be after the last feature
break;
elements;
}
elements;
prob.l;
}
rewind(fp);

prob.y = Malloc(double,prob.l);
prob.x = Malloc(struct svm_node *,prob.l);
x_space = Malloc(struct svm_node,elements);

max_index = 0;
j=0;
for(i=0;i<prob.l;i )
{
inst_max_index = -1; // strtol gives 0 if wrong format, and precomputed kernel has <index> start from 0
readline(fp);
prob.x[i] = &x_space[j];
label = strtok(line," \t\n");
if(label == NULL) // empty line
exit_input_error(i 1);

prob.y[i] = strtod(label,&endptr);
if(endptr == label || *endptr != '\0')
exit_input_error(i 1);

while(1)
{
idx = strtok(NULL,":");
val = strtok(NULL," \t");

if(val == NULL)
break;

errno = 0;
x_space[j].index = (int) strtol(idx,&endptr,10);
if(endptr == idx || errno != 0 || *endptr != '\0' || x_space[j].index <= inst_max_index)
exit_input_error(i 1);
else
inst_max_index = x_space[j].index;

errno = 0;
x_space[j].value = strtod(val,&endptr);
if(endptr == val || errno != 0 || (*endptr != '\0' && !isspace(*endptr)))
exit_input_error(i 1);

j;
}

if(inst_max_index > max_index)
max_index = inst_max_index;
x_space[j ].index = -1;
}

if(param.gamma == 0 && max_index > 0)
param.gamma = 1.0/max_index;

if(param.kernel_type == PRECOMPUTED)
for(i=0;i<prob.l;i )
{
if (prob.x[i][0].index != 0)
{
fprintf(stderr,"Wrong input format: first column must be 0:sample_serial_number\n");
exit(1);
}
if ((int)prob.x[i][0].value <= 0 || (int)prob.x[i][0].value > max_index)
{
fprintf(stderr,"Wrong input format: sample_serial_number out of range\n");
exit(1);
}
}

fclose(fp);
}