A partial interface to SVM-light [svmlight.joachims.org/] using it you can:

• Load an existent model (pre-created with svm_learn) from a file and using it for classification.

• Train a new classification SVM using linear kernels only (more kernels and SVM types to come) 100% form Ruby.

As of now it’s know to work with SVM 6.02.

Make sure to build the libsvmlight.o version of svmlight by using

“make libsvmlight_hideo”.

Make sure the .h files in the svmlight distribution are in your include path, inside a subdirectory called svm_light, and the object code for the library is in your include path (/usr/lib for instance).

The Document class is a ruby representation of the DOC struct in svmlight, in order to create a Document the feature vectors should be represented as a Hash (or array of arrays) where the keys are the feature numbers and the values the feature weight.

Document.new({1 => 0.5, 100 => 0.7}, :docnum => 1, :costfactor => 0.3)

The Model class is a ruby representation of the MODEL struct in svmlight.

Take a look at the examples directory for a quick usage overview.

• Check out the latest master to make sure the feature hasn’t been implemented or the bug hasn’t been fixed yet

• Check out the issue tracker to make sure someone already hasn’t requested it and/or contributed it

• Fork the project

• Start a feature/bugfix branch

• Commit and push until you are happy with your contribution

• Make sure to add tests for it. This is important so I don’t break it in a future version unintentionally.

• Please try not to mess with the Rakefile, version, or history. If you want to have your own version, or is otherwise necessary, that is fine, but please isolate to its own commit so I can cherry-pick around it.

Copyright © 2011 Camilo Lopez. See LICENSE.txt for further details.