NEW RELEASEWe (Viswanath S. and I) have been busy implementing new operators and overhauling some of the old ones.
The new release 1.1.3 has some sweet new operators:
- RCCW - Recursive Conditional Correlation Weighting - FAST AS HELL. A more fiiting name would be Blockwise Conditional Independenc Selectio, because that's what it does. Anyway,it's a very fast feature subset selection method.
- FCBF - Fast Correlation Based Feature Selection
- PAM - Classification by Shrunken Centroids
- BAHSIC - Backward Feature Selection via Hilbert-Schmidt information criterion
- t-Test - Computes a p-Value for the difference of the mean values between two classes
- Test Significance - Assumes normal distribution, then checks for equal class variances via F-test and afterwards computes p-Value via t-Test or Welch-test
- Benjamini-Hochberg-Correction - Performs the correction for FDR on significance values in an AttributeWeights object
Furthermore the Welch-test was accelerated and the Top-K operator was reworked to behave like "Select by Weights"-operator.
The new version is available on our SourceForge-site
https://sourceforge.net/projects/rm-featselext/ and via the brandnew RapidMiner-Marketplace
http://rapidupdate.de:8180 .
Enjoy,
Ben
