Synopsis
A simple validation method to check the performance of a feature weighting or selection wrapper.
Description
This operator evaluates the performance of feature weighting algorithms including feature selection. The first inner operator is the weighting algorithm to be evaluated itself. It must return an attribute weights vector which is applied on the data. Then a new model is created using the second inner operator and a performance is retrieved using the third inner operator. This performance vector serves as a performance indicator for the actual algorithm. This implementation is described for the RandomSplitValidationChain.
Input
- example set in:
Output
- performance vector out:
- attribute weights out:
Parameters
- split ratio: Relative size of the training set
- sampling type: Defines the sampling type of the cross validation (linear = consecutive subsets, shuffled = random subsets, stratified = random subsets with class distribution kept constant)
- use local random seed: Indicates if a local random seed should be used.
- local random seed: Specifies the local random seed