Parameters for Feature Selection

Description

Collects and checks necessary parameters required for feature selection. The empty constructor is provided for convenience.

Constructor

SelectParams() Creates a default SelectParams object. This uses a limma t-test and tries the top 10 to top 100 features in increments of 10, and picks the number of features with the best resubstitution balanced error rate. Users should create an appropriate SelectParams object for the characteristics of their data, once they are familiar with this software.

SelectParams(featureSelection, selectionName, minPresence = 1, intermediate = character(0),
          subsetToSelections = TRUE, ...)

Creates a SelectParams object which stores the function which will do the selection and parameters that the function will use.

featureSelection

Either a function which will do the selection or a list of such functions. For a particular function, the first argument must be an DataFrame object. The function's return value must be a SelectResult object.

selectionName

A name to identify this selection method by.

minPresence

If a list of functions was provided, how many of those must a feature have been selected by to be used in classification. 1 is equivalent to a set union and a number the same length as featureSelection is equivalent to set intersection.

intermediate

Character vector. Names of any variables created in prior stages by runTest that need to be passed to a feature selection function.

subsetToSelections

Whether to subset the data table(s), after feature selection has been done.

...

Other named parameters which will be used by the selection function. If featureSelection was a list of functions, this must be a list of lists, as long as featureSelection.

Author(s)

Dario Strbenac

Examples

  #if(require(sparsediscrim))
  #{
    SelectParams(limmaSelection, "t-test",
                 trainParams = TrainParams(), predictParams = PredictParams(),
                 resubstituteParams = ResubstituteParams())
    
    # For pamr shrinkage selection.
    SelectParams(NSCselectionInterface, datasetName = "Cancer",
                 intermediate = "trained", subsetToSelections = FALSE)
  #}