svmlight function

Interface to SVMlight

Function to call SVMlight from R for classification. Multiple group classification is done with the one-against-rest partition of data.

svmlight(x, ...)

## Default S3 method:
svmlight(x, grouping, temp.dir = NULL, pathsvm = NULL, 
    del = TRUE, type = "C", class.type = "oaa", svm.options = NULL, 
    prior = NULL, out = FALSE, ...)
## S3 method for class 'data.frame'
svmlight(x, ...)
## S3 method for class 'matrix'
svmlight(x, grouping, ..., subset, na.action = na.fail)
## S3 method for class 'formula'
svmlight(formula, data = NULL, ..., subset, 
    na.action = na.fail)

Arguments

• x: matrix or data frame containing the explanatory variables (required, if formula is not given).

• grouping: factor specifying the class for each observation (required, if formula is not given).

• formula: formula of the form groups ~ x1 + x2 + .... That is, the response is the grouping factor and the right hand side specifies the (non-factor) discriminators.

• data: Data frame from which variables specified in formula are preferentially to be taken.

• temp.dir: directory for temporary files.

• pathsvm: Path to SVMlight binaries (required, if path is unknown by the OS).

• del: Logical: whether to delete temporary files

• type: Perform "C"=Classification or "R"=Regression

• class.type: Multiclass scheme to use. See details.

• svm.options: Optional parameters to SVMlight.

  For further details see: How to use on http://svmlight.joachims.org/.

• prior: A Priori probabilities of classes.

• out: Logical: whether SVMlight output ahouild be printed on console (only for Windows OS.)

• subset: An index vector specifying the cases to be used in the training sample. (Note: If given, this argument must be named.)

• na.action: specify the action to be taken if NAs are found. The default action is for the procedure to fail. An alternative is na.omit, which leads to rejection of cases with missing values on any required variable. (Note: If given, this argument must be named.)

• ...: currently unused

Requirements

SVMlight (http://svmlight.joachims.org/) must be installed before using this interface.

Details

Function to call SVMlight from R for classification (type="C"). SVMlight is an implementation of Vapnik's Support Vector Machine. It is written in C by Thorsten Joachims. On the homepage (see below) the source-code and several binaries for SVMlight are available. If more then two classes are given the SVM is learned by the one-against-all scheme (class.type="oaa"). That means that each class is trained against the other K-1 classes. The class with the highest decision function in the SVM wins. So K SVMs have to be learned. If class.type="oao" each class is tested against every other and the final class is elected by a majority vote.

If type="R" a SVM Regression is performed.

Returns

A list containing the function call and the result of SVMlight.

References

http://svmlight.joachims.org/

Author(s)

Karsten Luebke, karsten.luebke@fom.de , Andrea Preusser

See Also

predict.svmlight,svm,

Examples

## Not run:

## Only works if the svmlight binaries are in the path.
data(iris)
x <- svmlight(Species ~ ., data = iris)
## Using RBF-Kernel with gamma=0.1:
data(B3)
x <- svmlight(PHASEN ~ ., data = B3, svm.options = "-t 2 -g 0.1")
## End(Not run)