Extended WEKA including Ensembles of Hierarchically Nested Dichotomies

Overview for extended WEKA including Ensembles of Hierarchically Nested Dichotomies.

See:
          Description

Packages
weka.associations  
weka.associations.tertius  
weka.attributeSelection  
weka.classifiers  
weka.classifiers.bayes  
weka.classifiers.evaluation  
weka.classifiers.functions  
weka.classifiers.functions.neural  
weka.classifiers.functions.pace  
weka.classifiers.functions.supportVector  
weka.classifiers.lazy  
weka.classifiers.lazy.kstar  
weka.classifiers.meta  
weka.classifiers.misc  
weka.classifiers.rules  
weka.classifiers.rules.part  
weka.classifiers.trees  
weka.classifiers.trees.adtree  
weka.classifiers.trees.j48  
weka.classifiers.trees.lmt  
weka.classifiers.trees.m5  
weka.clusterers  
weka.core  
weka.core.converters  
weka.datagenerators  
weka.estimators  
weka.experiment  
weka.filters  
weka.filters.supervised.attribute  
weka.filters.supervised.instance  
weka.filters.unsupervised.attribute  
weka.filters.unsupervised.instance  
weka.gui  
weka.gui.beans  
weka.gui.boundaryvisualizer  
weka.gui.experiment  
weka.gui.explorer  
weka.gui.graphvisualizer  
weka.gui.streams  
weka.gui.treevisualizer  
weka.gui.visualize  

 

Overview for extended WEKA including Ensembles of Hierarchically Nested Dichotomies.

The extensions for EHNDs are based on WEKA version 3-4-1 (March 2004) and the classes weka.classifiers.meta.END and weka.classifiers.meta.ND as provided by Eibe Frank.

Newly incorporated classes for covering EHNDs

Changes in original WEKA classes, END, and ND for incorporating EHNDs

Usage

Currently neither END, nor ND or HND are enabled to run with graphical user interface. For usage of EHNDs in command-line interface call weka.classifiers.meta.END with the respective parameters, weka.classifiers.meta.HND as base learner.

Planned changes for incorporation into a future WEKA distribution

In theory HND provides the means to run a hierarchical classification with any base classifier. We propose to generalize the class to handle any base learner, and to incorporate it as an independent meta schema.

Currently the hierarchy can be encoded in an arff file as comment. Thus the hierarchy will get lost if a respective new file is created after filtering. Perhaps it could be possible to incorporate a new (optional) key-word to the arff-format denoting a line that provides an encoded hierarchy.

Furthermore, by omitting the call of setHashtable(), END become a merely arbitrary ensemble method, that is not realy specialized to run with ND or HND as base learner only. Thus the restriction by requiring a base learner implementing the marker interface weka.classifiers.meta.NestedDichotomy could eventually be removed. The same effect, however, could perhaps be achieved using RandomCommittee, so END might become somewhat redundant.