研究libsvm 直到能够将其 纳为己用
大部分代码来自libsvm压缩包里的文件，通过分析里面的代码得出其用法。
Title 1—svm_parameter参数的设置：
svm_parameter 该类用来设置libsvm的一些配置参数，参数有点多，具体的参数说明如下:
private static void exit_with_help()
{
System.out.print(
"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"
);
System.exit(1);
}也可以使用默认的参数，默认的参数为: 需要注意的是为gamma参数为1/num_features而不是0
// default values
param.svm_type = svm_parameter.C_SVC;
param.kernel_type = svm_parameter.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 = new int[0];
param.weight = new double[0];
cross_validation = 0;完整参考代码如下 ：
private void parse_command_line(String argv[])
{
int i;
svm_print_interface print_func = null; // default printing to stdout
param = new svm_parameter();
// default values
param.svm_type = svm_parameter.C_SVC;
param.kernel_type = svm_parameter.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 = new int[0];
param.weight = new double[0];
cross_validation = 0;
// parse options
for(i=0;i<argv.length;i++)
{
if(argv[i].charAt(0) != '-') break;
if(++i>=argv.length)
exit_with_help();
switch(argv[i-1].charAt(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 = svm_print_null;
i--;
break;
case 'v':
cross_validation = 1;
nr_fold = atoi(argv[i]);
if(nr_fold < 2)
{
System.err.print("n-fold cross validation: n must >= 2\n");
exit_with_help();
}
break;
case 'w':
++param.nr_weight;
{
int[] old = param.weight_label;
param.weight_label = new int[param.nr_weight];
System.arraycopy(old,0,param.weight_label,0,param.nr_weight-1);
}
{
double[] old = param.weight;
param.weight = new double[param.nr_weight];
System.arraycopy(old,0,param.weight,0,param.nr_weight-1);
}
param.weight_label[param.nr_weight-1] = atoi(argv[i-1].substring(2));
param.weight[param.nr_weight-1] = atof(argv[i]);
break;
default:
System.err.print("Unknown option: " + argv[i-1] + "\n");
exit_with_help();
}
}
svm.svm_set_print_string_function(print_func);
// determine filenames
if(i>=argv.length)
exit_with_help();
input_file_name = argv[i];
if(i<argv.length-1)
model_file_name = argv[i+1];
else
{
int p = argv[i].lastIndexOf('/');
++p; // whew...
model_file_name = argv[i].substring(p)+".model";
}
}Title 2 : svm_problem 用来保存样本实例的
prob.l l用来保存样本的数量
prob.x x是一个svm_node类型的二维数组，每一行代表一个样本，svm_node实例里的value代表属性值，index代表属性的序号。
prob.y y是一个double类型的一维数组，用来保存样本的类别标签。
prob.y[i] 与 prob.x[i][]构成了一个完整的样本，一个保存类别标签，一个保存属性值。
private void read_problem() throws IOException
{
BufferedReader fp = new BufferedReader(new FileReader(input_file_name));
Vector<Double> vy = new Vector<Double>();
Vector<svm_node[]> vx = new Vector<svm_node[]>();
int max_index = 0;
while(true)
{
String line = fp.readLine();
if(line == null) break;
StringTokenizer st = new StringTokenizer(line," \t\n\r\f:");
vy.addElement(atof(st.nextToken()));
int m = st.countTokens()/2;
svm_node[] x = new svm_node[m];
for(int j=0;j<m;j++)
{
x[j] = new svm_node();
x[j].index = atoi(st.nextToken());
x[j].value = atof(st.nextToken());
}
if(m>0) max_index = Math.max(max_index, x[m-1].index);
vx.addElement(x);
}
prob = new svm_problem();
prob.l = vy.size();
prob.x = new svm_node[prob.l][];
for(int i=0;i<prob.l;i++)
prob.x[i] = vx.elementAt(i);
prob.y = new double[prob.l];
for(int i=0;i<prob.l;i++)
prob.y[i] = vy.elementAt(i);
if(param.gamma == 0 && max_index > 0)
param.gamma = 1.0/max_index;
if(param.kernel_type == svm_parameter.PRECOMPUTED)
for(int i=0;i<prob.l;i++)
{
if (prob.x[i][0].index != 0)
{
System.err.print("Wrong kernel matrix: first column must be 0:sample_serial_number\n");
System.exit(1);
}
if ((int)prob.x[i][0].value <= 0 || (int)prob.x[i][0].value > max_index)
{
System.err.print("Wrong input format: sample_serial_number out of range\n");
System.exit(1);
}
}
fp.close();
}一般的分类步骤如下:
利用训练样本生成一个分类模型，然后利用该分类模型对待分类的样本进行分类
我需要的libsvm的使用步骤：
step 1:设置svm_parameter (注，gamma参数 的使用是在 readproblem函数里面使用的以及当kernel_type == PRECOMPUTED的时候也是在readproblem里面生效的,etc...)
step 2:将自己的样本存储到svm_problem对象中
step 3:利用svm_problem和svm_paramter通过svm.svm_train函数可以训练出一个svm_model
public static svm_model svm_train(svm_problem prob, svm_parameter param)
svm.java里面的参考代码 svm_model submodel = svm_train(subprob,param);
step 4:有了模型之后我们就可以进行分类了:
根据参数的不同调用的分类函数有所不同，但是主要有两个成员函数可以使用 svm_predict_probalility以及svm_predict 返回值就是分类的结果
public static double svm_predict_values(svm_model model, svm_node[] x, double[] dec_values)
public static double svm_predict(svm_model model, svm_node[] x)
参考代码如下
if(param.probability==1 &&
(param.svm_type == svm_parameter.C_SVC ||
param.svm_type == svm_parameter.NU_SVC))
{
double[] prob_estimates= new double[svm_get_nr_class(submodel)];
for(j=begin;j<end;j++)
target[perm[j]] = svm_predict_probability(submodel,prob.x[perm[j]],prob_estimates);
}
else
for(j=begin;j<end;j++)
target[perm[j]] = svm_predict(submodel,prob.x[perm[j]]);svm.java 源码里的开放接口 从字面意义上可以看出点门路...应该有相关文档吧 没去找哈- -以后有需要再去研究
public static svm_model svm_train(svm_problem prob, svm_parameter param)
public static void svm_cross_validation(svm_problem prob, svm_parameter param, int nr_fold, double[] target)
public static int svm_get_svm_type(svm_model model)
public static int svm_get_nr_class(svm_model model)
public static void svm_get_labels(svm_model model, int[] label)
public static void svm_get_sv_indices(svm_model model, int[] indices)
public static int svm_get_nr_sv(svm_model model)
public static double svm_get_svr_probability(svm_model model)
public static double svm_predict_values(svm_model model, svm_node[] x, double[] dec_values)
public static double svm_predict(svm_model model, svm_node[] x)
public static double svm_predict_probability(svm_model model, svm_node[] x, double[] prob_estimates)
public static void svm_save_model(String model_file_name, svm_model model) throws IOException
public static svm_model svm_load_model(String model_file_name) throws IOException
public static svm_model svm_load_model(BufferedReader fp) throws IOException
public static String svm_check_parameter(svm_problem prob, svm_parameter param)
public static int svm_check_probability_model(svm_model model)
public static void svm_set_print_string_function(svm_print_interface print_func)