This RapidMiner-plugin consists of operators for feature selection and classification - mainly on high-dimensional (microarray-) data - and some helper-classes/operators.
The most recent release and source code can be found on the project page at Sourceforge: https://sourceforge.net/projects/rm-featselext.
Please note, the this is just experimental software and might contain bugs or unfinished operators. Contact me, if you have any questions or just found it useful :-)
This version 1.0.6 offers
Meta-Operators:
- EnsembleFeatureSelection
- WindowedWeighting
- RecursiveFeatureElimination
Feature selection and -weighting:
- MaximumRelevanceWeighting
- MRMRFeatureSelection
- CorrelationBasedWeakAssociations
- SAMWeighting
- ExonWelchTest
- RecursiveFeatureEliminationSVM
- FeatureQuantileFilter
- MRMRFeatureSetEvaluator
Classification:
- Least Angle Regression (LASSO / LARS)
- SAM
Helper:
- TopK
- MakePerformanceLoggable
- ValueReplenishmentWithOffset
- Selection2Ranking
- Weights2Ranking