costSensitiveAttributeSelection: Two meta attribute selection evaluators (one attribute-based and the other subset-based) for performing cost-sensitive attribute selection.

URL:http://weka.sourceforge.net/doc.packages/costSensitiveAttributeSelection
Author:Mark Hall
Maintainer:Weka team <wekalist{[at]}list.scms.waikato.ac.nz>

This package provides two meta attribute selection evaluators - one for performing cost-sensitive attribute evaluation (CostSensitiveAttributeEval) and a second for performing cost-sensitive subset evaluation (CostSensitiveSubsetEval). Both methods take a cost matrix and a base evaluator. If the base evaluator can handle instance weights, then the training data is weighted according to the cost matrix, otherwise the training data is sampled according to the cost matrix.

All available versions:
Latest
1.0.3
1.0.1
1.0.0