Random Jungle on Helix
Random Jungle is a fast implementation of RandomForest(TM) for high dimensional data. It was developed by Leo Breiman and Adele Cutler. In genetics, it can be used for analysing big Genome Wide Association (GWA) data. Random Forests (TM) is a powerful machine learning method. Most interesting features are variable selection, missing value imputation, classifier creation, generalization error estimation and sample proximities between pairs of cases.
Usage
Type 'rjungle' or 'rjunglesparse' to run the programs. Adding the '-h' switch will give a list of the available options.
For large numbers of rjungle jobs (> 3 simultaneous jobs), use Random Jungle on the Biowulf cluster
Documentation
