FEATSEL

Fixed mapping for selecting given features

    [W,V] = FEATSEL(K,J)
     B = A*FEATSEL(J)
     C = A*FEATSEL(J,true)

Input
K	Input dimensionality
J	Index vector of features to be selected
A	Dataset

Output
W	Mapping performing the feature selection
V	Mapping selecting the complementing features
B	Dataset, A(J,:)
C	Dataset, A with features J removed

Description

This is a simple support routine that writes feature selection  in terms of a mapping. If A is a K-dimensional dataset and J are  the feature indices to be selected, then B = A*W does the same as  B = A(:,J).

The use of this routine is a mapping V computed for a lower dimensional  subspace defined by J can now be defined by W = FEATSEL(K,J)*V as a  mapping in the original K-dimensional space.

The selected features can be retrieved by W.DATA or by +W.  See below for various methods to perform feature selection.

See also

mappings, datasets, feateval, featself, featsellr, featselo, featselb, featseli, featselp, featselm,