This is a more complex example of how to code with JKernelMachines than can be used as a stand-alone program.
It reads data from an input file in the libsvm format, and performs a cross-validation evaluation. Optional parameters include the number of test to perform, the percentage of data to keep from training, the type of kernel, and the svm algorithm. Launch without argument to get the following help:
CrossValidationExample -f file [-p percent] [-n nbtests] [-k kernel] [-a algorithm] [-pca type] [-vvv]
- -f file: the data file in libsvm format
- -p percent: the percent of data to keep for training
- -n nbtests: the number of test to perform during crossvalidation
- -k kernel: the type of kernel (linear or gauss, default gauss)
- -a algorithm: type of SVM algorithm(lasvm, lasvmi, smo, nlssvm default lasvm)
- -pca type: perform a PCA as preprocessing (no, yes, white, default no)
- -v: verbose (v few, vv lot, vvv insane, default none)
@author David Picard