Package id3

Provides the classes needed for Decision Tree inducers and the MLJ implementation of the ID3 inducer.

See:
Description

Class Summary

AttrCategorizer	The AttrCategorizer categorizes an Instance based on an attribute.
CatGraph	CatGraph is a directed graph whose nodes have references to Categorizers.
CGraph	CGraph is derived from LEDA's CGRAPH This allows us to add functions.
DecisionTree	DecisonTrees are RootedCatGraphs where each node other than the root has exactly one parent.
Driver	Basic Driver class used to interface the ID3Inducer.
DTCategorizer	DTCategorizer performs the same way as a RDGCategorizer, but for the DTCategorizer the associated graph must be a tree.
ID3Inducer	The ID3Class is the Java implementation of the ID3 algorithm.
LeafCategorizer	NodeCategorizer for categorizers that don't need to ask other categorizers for help scoring (i.e.
NodeCategorizer	An abstract base class categorizer for categorizers that may sit in nodes of decision trees, graphs, etc.
NodeInfo	Stores the information in a Graph Node.
NodeLoss	Class used for node accuracies.
RDGCategorizer	Categorizer goes down the RootedCatGraph using the Categorizer at each node until it reaches a node with no children.
RootedCatGraph	RootedCatGraph instances have a specific root node.
TDDTInducer	Top-down decision-tree (TDDT) inducer induces decision trees top-down by building smaller training sets and inducing trees for them recursively.
TDDTOptions	This class stores information about option settings for Top-Down Decision Tree inducers.
ThresholdCategorizer	Categorize an instance by comparing the value of a single attribute to a threshold value.

Package id3 Description

Provides the classes needed for Decision Tree inducers and the MLJ implementation of the ID3 inducer.

Related Documentation

For documentation on the MLC++ library created by Kohavi, et al., see:

• SGI - MLC++: Home Page