Performs a principal components analysis and transformation of the data. Use in conjunction with a Ranker search. Dimensionality reduction is accomplished by choosing enough eigenvectors to account for some percentage of the variance in the original data---default 0.95 (95%). Attribute noise can be filtered by transforming to the PC space, eliminating some of the worst eigenvectors, and then transforming back to the original space.
The table below describes the options available for PrincipalComponents.
The maximum number of attributes to include in transformed attribute names.
Normalize input data.
Transform through the PC space and back to the original space. If only the best n PCs are retained (by setting varianceCovered < 1) then this option will give a dataset in the original space but with less attribute noise.
Retain enough PC attributes to account for this proportion of variance.
The table below describes the capabilites of PrincipalComponents.
Date class, Numeric class, Binary class, Nominal class, Missing class values, No class
Numeric attributes, Nominal attributes, Binary attributes, Missing values, Date attributes, Empty nominal attributes, Unary attributes
Min # of instances