com.github.chen0040.libsvm.svm_train Maven / Gradle / Ivy
package com.github.chen0040.libsvm;
/**
* Created by xschen on 16/8/15.
*/
import java.io.BufferedReader;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.StringTokenizer;
import java.util.Vector;
class svm_train {
private svm_parameter param; // set by parse_command_line
private svm_problem prob; // set by read_problem
private svm_model model;
private String input_file_name; // set by parse_command_line
private String model_file_name; // set by parse_command_line
private String error_msg;
private int cross_validation;
private int nr_fold;
private static svm_print_interface svm_print_null = new svm_print_interface()
{
public void print(String s) {}
};
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);
}
private 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 = new double[prob.l];
SupportVectorMachine.svm_cross_validation(prob,param,nr_fold,target);
if(param.svm_type == svm_parameter.EPSILON_SVR ||
param.svm_type == svm_parameter.NU_SVR)
{
for(i=0;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();
}
}
SupportVectorMachine.svm_set_print_string_function(print_func);
// determine filenames
if(i>=argv.length)
exit_with_help();
input_file_name = argv[i];
if(i vy = new Vector();
Vector vx = new Vector();
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;
SupportVectorMachineNode[] x = new SupportVectorMachineNode[m];
for(int j=0;j0) max_index = Math.max(max_index, x[m-1].index);
vx.addElement(x);
}
fp.close();
prob = new svm_problem();
prob.l = vy.size();
prob.x = new SupportVectorMachineNode[prob.l][];
for(int i=0;i 0)
param.gamma = 1.0/max_index;
if(param.kernel_type == svm_parameter.PRECOMPUTED)
for(int i=0;i max_index)
{
System.err.print("Wrong input format: sample_serial_number out of range\n");
throw new RuntimeException("Wrong input format: sample_serial_number out of range");
}
}
fp.close();
}
}