| PRTools contents |
FEATSELI
[W,R] = FEATSELI(A,CRIT,K,T)
| Input | |
| A | Training dataset |
| CRIT | Name of the criterion or untrained mapping (default: 'NN', i.e. the 1-Nearest Neighbor error) |
| K | Number of features to select (default: sort all features) |
| T | Tuning dataset (optional) |
| Output | |
| W | Feature selection mapping |
| R | Matrix with criterion values |
Individual selection of K features using the dataset A. CRIT sets the criterion used by the feature evaluation routine FEATEVAL. If the dataset T is given, it is used as test set for FEATEVAL. For K = 0 all features are selected, but reordered according to the criterion. The result W can be used for selecting features using B*W. The selected features are stored in W.DATA and can be found by +W. In R, the search is reported step by step as
R(:,1) : number of features
R(:,2) : criterion value
R(:,3) : added / deleted feature
mappings, datasets, feateval, featselo, featselb, featself,
| FEATSEL, | FEATSELP, FEATSELM |
| PRTools contents |