SVMlight is an implementation of the Support Vector Machine providing methods for efficient estimation methods for both error rate and precision/recall. SVMlight exploits that the results of most leave-one-outs (often more than 99%) are predetermined and need not be computed. Further more it can also train SVMs with cost models. Many tasks have the property of sparse instance vectors. This implementation makes use of this property which leads to a very compact and efficient representation.
The binaries need to be downloaded here and placed into the PATH of the user. Here for example the binaries are placed into the bin folder of the user.
$ cp ~/Downloads/svm_light_osx.8.4_i7.tar.gz ~/bin/ $ tar xfz svm_light_osx.8.4_i7.tar.gz $ cd ~/Downloads/ $ mkdir svm_light $ mv svm_learn svm_classify svm_light/
Add last we need to add the svm_learn and svm_classify to the PATH of the user.
$ export PATH=$PATH:/Users/hkropp/bin/svm_light
Running the example:
> install.packages('klaR') > library('klaR') > data(iris) > x <- svmlight(Species ~ ., data = iris)