调用libsvm.jar
import java.io.IOException;
public class Tlibsvm {
public static void main(String[] args) throws IOException { // svm_problem
String[] arg = {
"D:\\2_1500_rfinish\\TextCategorization_2_1500_10\\data\\test.libsvm",
"D:\\2_1500_rfinish\\TextCategorization_2_1500_10\\data\\model" };
String[] parg = {
"D:\\2_1500_rfinish\\TextCategorization_2_1500_10\\data\\train.libsvm",
"D:\\2_1500_rfinish\\TextCategorization_2_1500_10\\data\\model",
"D:\\2_1500_rfinish\\TextCategorization_2_1500_10\\data\\ouput" };
//svm_train t = new svm_train();
//svm_predict p = new svm_predict();
try {
svm_train.main(arg);
svm_predict.main(parg);
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
预测类别：
import java.io.IOException;
import libsvm.svm;
import libsvm.svm_model;
import libsvm.svm_node;
public class Tlibsvm {
public static double predictPerRecord(double[] record, svm_model model) {
svm_node[] x = new svm_node[record.length];
for (int i = 0; i < record.length; i++) {
svm_node node = new svm_node();
node.index = i;
node.value = record[i];
x[i] = node;
}
double v = svm.svm_predict(model, x);
return v;
}
public static void main(String[] args) throws IOException { // svm_problem
/*
* String[] arg = {
* "D:\\2_1500_rfinish\\TextCategorization_2_1500_10\\data\\test.libsvm"
* , "D:\\2_1500_rfinish\\TextCategorization_2_1500_10\\data\\model" };
* String[] parg = {
* "D:\\2_1500_rfinish\\TextCategorization_2_1500_10\\data\\train.libsvm"
* , "D:\\2_1500_rfinish\\TextCategorization_2_1500_10\\data\\model",
* "D:\\2_1500_rfinish\\TextCategorization_2_1500_10\\data\\ouput" };
*
* //svm_train t = new svm_train(); //svm_predict p = new svm_predict();
*
* try { svm_train.main(arg); svm_predict.main(parg); } catch
* (IOException e) { // TODO Auto-generated catch block
* e.printStackTrace(); }
*/
double[] record = { 5.872288, 7.133121, 7.133121, 8.188928, 6.971858,
6.971858, 5.442672, 5.693101, 5.693101, 5.693101, 5.693101 };
svm_model model = svm
.svm_load_model("D:\\2_1500_rfinish\\TextCategorization_2_1500_10\\data\\model");
double c = Tlibsvm.predictPerRecord(record, model);
System.out.println(c);
}
}
cmd:
java -classpath libsvm.jar svm_train <arguments>
java -classpath libsvm.jar svm_predict <arguments>
java -classpath libsvm.jar svm_toy
java -classpath libsvm.jar svm_scale <arguments>
`svm-train' Usage
=================
Usage: svm-train [options] training_set_file [model_file]
options:
-s svm_type : set type of SVM (default 0)
0 -- C-SVC
1 -- nu-SVC
2 -- one-class SVM
3 -- epsilon-SVR
4 -- nu-SVR
-t kernel_type : set type of kernel function (default 2)
0 -- linear: u'*v
1 -- polynomial: (gamma*u'*v + coef0)^degree
2 -- radial basis function: exp(-gamma*|u-v|^2)
3 -- sigmoid: tanh(gamma*u'*v + coef0)
4 -- precomputed kernel (kernel values in training_set_file)
-d degree : set degree in kernel function (default 3)
-g gamma : set gamma in kernel function (default 1/num_features)
-r coef0 : set coef0 in kernel function (default 0)
-c cost : set the parameter C of C-SVC, epsilon-SVR, and nu-SVR (default 1)
-n nu : set the parameter nu of nu-SVC, one-class SVM, and nu-SVR (default 0.5)
-p epsilon : set the epsilon in loss function of epsilon-SVR (default 0.1)
-m cachesize : set cache memory size in MB (default 100)
-e epsilon : set tolerance of termination criterion (default 0.001)
-h shrinking : whether to use the shrinking heuristics, 0 or 1 (default 1)
-b probability_estimates : whether to train a SVC or SVR model for probability estimates, 0 or 1 (default 0)
-wi weight : set the parameter C of class i to weight*C, for C-SVC (default 1)
-v n: n-fold cross validation mode
-q : quiet mode (no outputs)
The k in the -g option means the number of attributes in the input data.
option -v randomly splits the data into n parts and calculates cross
validation accuracy/mean squared error on them.
See libsvm FAQ for the meaning of outputs.
`svm-predict' Usage
===================
Usage: svm-predict [options] test_file model_file output_file
options:
-b probability_estimates: whether to predict probability estimates, 0 or 1 (default 0); for one-class SVM only 0 is supported
model_file is the model file generated by svm-train.
test_file is the test data you want to predict.
svm-predict will produce output in the output_file.
`svm-scale' Usage
=================
Usage: svm-scale [options] data_filename
options:
-l lower : x scaling lower limit (default -1)
-u upper : x scaling upper limit (default +1)
-y y_lower y_upper : y scaling limits (default: no y scaling)
-s save_filename : save scaling parameters to save_filename
-r restore_filename : restore scaling parameters from restore_filename
Tips on Practical Use
=====================
* Scale your data. For example, scale each attribute to [0,1] or [-1,+1].
* For C-SVC, consider using the model selection tool in the tools directory.
* nu in nu-SVC/one-class-SVM/nu-SVR approximates the fraction of training
errors and support vectors.
* If data for classification are unbalanced (e.g. many positive and
few negative), try different penalty parameters C by -wi (see
examples below).
* Specify larger cache size (i.e., larger -m) for huge problems.
Examples
========
> svm-scale -l -1 -u 1 -s range train > train.scale
> svm-scale -r range test > test.scale
Scale each feature of the training data to be in [-1,1]. Scaling
factors are stored in the file range and then used for scaling the
test data.
> svm-train -s 0 -c 5 -t 2 -g 0.5 -e 0.1 data_file
Train a classifier with RBF kernel exp(-0.5|u-v|^2), C=10, and
stopping tolerance 0.1.
> svm-train -s 3 -p 0.1 -t 0 data_file
Solve SVM regression with linear kernel u'v and epsilon=0.1
in the loss function.
> svm-train -c 10 -w1 1 -w2 5 -w4 2 data_file
Train a classifier with penalty 10 = 1 * 10 for class 1, penalty 50 =
5 * 10 for class 2, and penalty 20 = 2 * 10 for class 4.
> svm-train -s 0 -c 100 -g 0.1 -v 5 data_file
Do five-fold cross validation for the classifier using
the parameters C = 100 and gamma = 0.1
> svm-train -s 0 -b 1 data_file
> svm-predict -b 1 test_file data_file.model output_file
Obtain a model with probability information and predict test data with
probability estimates