The basic use of the libsvm support vector machine algorithm package. What is demonstrated here is the support vector regression machine.
Copy the code code as follows:
import java.io.BufferedReader;
import java.io.File;
import java.io.FileReader;
import java.util.ArrayList;
import java.util.List;
import libsvm.svm;
import libsvm.svm_model;
import libsvm.svm_node;
import libsvm.svm_parameter;
import libsvm.svm_problem;
public class SVM {
public static void main(String[] args) {
// Define the training set point a{10.0, 10.0} and point b{-10.0, -10.0}, and the corresponding lable is {1.0, -1.0}
List<Double> label = new ArrayList<Double>();
List<svm_node[]> nodeSet = new ArrayList<svm_node[]>();
getData(nodeSet, label, "file/train.txt");
int dataRange=nodeSet.get(0).length;
svm_node[][] datas = new svm_node[nodeSet.size()][dataRange]; // Vector table of training set
for (int i = 0; i < datas.length; i++) {
for (int j = 0; j < dataRange; j++) {
datas[i][j] = nodeSet.get(i)[j];
}
}
double[] labels = new double[label.size()]; // labels corresponding to a,b
for (int i = 0; i < labels.length; i++) {
labels[i] = label.get(i);
}
//Define svm_problem object
svm_problem problem = new svm_problem();
problem.l = nodeSet.size(); // Number of vectors
problem.x = datas; //Training set vector table
problem.y = lables; // Corresponding lable array
//Define svm_parameter object
svm_parameter param = new svm_parameter();
param.svm_type = svm_parameter.EPSILON_SVR;
param.kernel_type = svm_parameter.LINEAR;
param.cache_size = 100;
param.eps = 0.00001;
param.C = 1.9;
//Train SVM classification model
System.out.println(svm.svm_check_parameter(problem, param));
// If there is no problem with the parameters, the svm.svm_check_parameter() function returns null, otherwise it returns an error description.
svm_model model = svm.svm_train(problem, param);
// svm.svm_train() trains the SVM classification model
// Get test data
List<Double> testlabel = new ArrayList<Double>();
List<svm_node[]> testnodeSet = new ArrayList<svm_node[]>();
getData(testnodeSet, testlabel, "file/test.txt");
svm_node[][] testdatas = new svm_node[testnodeSet.size()][dataRange]; // Vector table of training set
for (int i = 0; i < testdatas.length; i++) {
for (int j = 0; j < dataRange; j++) {
testdatas[i][j] = testnodeSet.get(i)[j];
}
}
double[] testlables = new double[testlabel.size()]; // labels corresponding to a,b
for (int i = 0; i < testlables.length; i++) {
testlabels[i] = testlabel.get(i);
}
// Label for predicting test data
double err = 0.0;
for (int i = 0; i < testdatas.length; i++) {
double truevalue = testlables[i];
System.out.print(truevalue + " ");
double predictValue = svm.svm_predict(model, testdatas[i]);
System.out.println(predictValue);
err += Math.abs(predictValue - truevalue);
}
System.out.println("err=" + err / datas.length);
}
public static void getData(List<svm_node[]> nodeSet, List<Double> label,
String filename) {
try {
FileReader fr = new FileReader(new File(filename));
BufferedReader br = new BufferedReader(fr);
String line = null;
while ((line = br.readLine()) != null) {
String[] datas = line.split(",");
svm_node[] vector = new svm_node[datas.length - 1];
for (int i = 0; i < datas.length - 1; i++) {
svm_node node = new svm_node();
node.index = i + 1;
node.value = Double.parseDouble(datas[i]);
vector[i] = node;
}
nodeSet.add(vector);
double lablevalue = Double.parseDouble(datas[datas.length - 1]);
label.add(lablevalue);
}
} catch (Exception e) {
e.printStackTrace();
}
}
}
Training data, the last column is the target value
Copy the code code as follows:
17.6,17.7,17.7,17.7,17.8
17.7,17.7,17.7,17.8,17.8
17.7,17.7,17.8,17.8,17.9
17.7,17.8,17.8,17.9,18
17.8,17.8,17.9,18,18.1
17.8,17.9,18,18.1,18.2
17.9,18,18.1,18.2,18.4
18,18.1,18.2,18.4,18.6
18.1,18.2,18.4,18.6,18.7
18.2,18.4,18.6,18.7,18.9
18.4,18.6,18.7,18.9,19.1
18.6,18.7,18.9,19.1,19.3
test data
Copy the code code as follows:
18.7,18.9,19.1,19.3,19.6
18.9,19.1,19.3,19.6,19.9
19.1,19.3,19.6,19.9,20.2
19.3,19.6,19.9,20.2,20.6
19.6,19.9,20.2,20.6,21
19.9,20.2,20.6,21,21.5
20.2,20.6,21,21.5,22