Documentation for libsvm in python

If you have already downloaded libSVM you will find some "usefull" documentation inside two files:

• ./libsvm-3.xx/README file in the top directory which covers the C/C++ API and also documentation about the binary executables svm-predict, svm-scale and svm-train

• ./libsvm-3.xx/python/README which deals with the Python interfaces (svm and svmutil), which I think is what you are looking for. However the example is quite naive although is a good beginning.

Let me suggest you that if you want to work with libSVM in Python, the scikit-learn package implements SVM using libSVM underneath, it much more easy, better documented and let's you control the same parameters of libSVM.

I think you might be approaching this the wrong way. You seem to be expecting to use LIBSVM as if it was ls: just do man ls to get the parameters and view the results. SVMs are more complicated than that.

The authors of LIBSVM publish a document (not a scientific paper!) called: A Practical Guide to Support Vector Classification. You need to read and understand all that the authors explain there. The appendix to that guide gives multiple examples on many datasets and how to train and how to search for parameters (all things that are very important).

There is a README file in the python directory of the LIBSVM distribution. If you understand python and you read the practical guide you should be able to use it. If not you should probably start from the command line examples to learn SVM or start with somthing easier(not SVMs!) to learn python. After reading and understanding that you should be able to read use all the examples from the appendix and invoke them from python.

Once you've tried this you should be up and running in no time. If not, this is a great place to ask specific questions about problems you run into.