Feature Selection Package - Algorithms - Relief-F
Description
Relief-F is a feature selection strategy that chooses instances randomly,
and changed the weights of the feature relevance based on the nearest neighbor.
By its merits, Relief-F is one of the most successful strategies in feature selection.
Usage
Method Signature:
[out] = fsReliefF(X, Y,
k, m)
Output:
out:
A struct containing the following fields:
- W - a list containing the information gain of each feature
when matched with fList.
- fList - the list of features ranked by their ability to classify
the data. fList(1) is the least important feature.
- prf - will always be 1. This means the greater the feature weight,
the less relevant the feature.
Input:
X:
The features on current trunk, each column is a feature vector on all
instances, and each row is a part of the instance.
Y:
The label of instances, in single column form: 1 2 3 4 5 ...
k:
The size of the neighborhood you wish to evaluate.
m:
How many samples you want to try.
Code Example
% Using the wine.dat data set, which can be found at
% [fspackage_location]/classifiers/knn/wine.mat
fsReliefF(X,Y,178,178);
Keyword in Evaluator Framework
relieff
Paper
BibTex entry for:
Computational Methods of Feature Selection by Huan Liu and Hiroshi Motoda.
@book{liu2008,
title = {Computational Methods of Feature Selection},
editor = {Liu, H. and Motoda, H.},
publisher = {Chapman & Hall},
year = {2008}
}