Name | Modified | Size | Downloads / Week |
---|---|---|---|
releases | 2011-07-15 | ||
Slides-FeatureSelectionforHighDimensionalDatawithRapidMiner.pdf | 2011-06-22 | 1.0 MB | |
VERSION | 2011-03-14 | 2.1 kB | |
README | 2010-12-14 | 2.2 kB | |
Totals: 4 Items | 1.0 MB | 0 |
### RapidMiner Feature Selection Extension ### This extension to RapidMiner 5.x provides further feature selection and classification algorithms well suited for high dimensional data. You will find the latest release at http://sourceforge.net/projects/rm-featselext and some information at the previous project site http://www-ai.cs.tu-dortmund.de/SOFTWARE/MFSPLUGIN/index.html Please note, the this is just experimental software and might contain bugs or unfinished operators. If you have any questions, drop me a line. You can find me at: http://www-ai.cs.tu-dortmund.de/PERSONAL/schowe.html ### Installation ### Just copy the file "rapidminer-Feature-Selection-Extension-1.0.x.jar" to the /lib/plugins folder of your RapidMiner 5 installation. For windows users thight could be "C:\Program Files\RapidMiner\lib\plugins" or similar. ### Operators ### In the current version (1.0.3) the extension contains the following operators: Attribute Selection - Meta-Operators: - Ensemble Feature Selection - Windowed Weighting - Recursive Feature Elimination (RFE) - Feautre Selection Stability Evaluation Attribute Selection: - Select by SVM-RFE - Select by MRMR / CFS - Select by Feature Quantile Filter - Performance (MRMR) Attribute weighting: - Weight by Correlation based associations - Weight by Maximum Relevance - Weight by Welch-test - Weight by SAM Classification: - Least Angle Regression (LASSO / LARS) - Change LARS Model Parameters - SAM Utiliy: - Select top k features - ValueReplenishmentWithOffset - Selection2Ranking - Weights2Ranking - MRMR Cache Creator ### Building ### Prerequisites: You need a recent version of the RapidMiner 5.x source code. It should be located at "../RapidMiner_Vega" relative to this directory. If this does not apply, change the "rm.dir" property in the build.xml file. Go for it: Just type ant for building the plugin. If you want it packaged, type ant createJar and if you are running RapidMiner from your RapidMiner_Vega source directory you can also type ant installJar which packages the plugin and places it in "RapidMiner_Vega/lib/plugins". [Then start RapidMiner.] That's it. Enjoy, Ben