Package

weka.classifiers.meta

Synopsis

Class for combining classifiers. Different combinations of probability estimates for classification are available.

For more information see:

Ludmila I. Kuncheva (2004). Combining Pattern Classifiers: Methods and Algorithms. John Wiley and Sons, Inc..

J. Kittler, M. Hatef, Robert P.W. Duin, J. Matas (1998). On combining classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence. 20(3):226-239.

Options

The table below describes the options available for Vote.

Option	Description
classifiers	The base classifiers to be used.
combinationRule	The combination rule used.
debug	If set to true, classifier may output additional info to the console.
preBuiltClassifiers	The pre-built serialized classifiers to include. Multiple serialized classifiers can be included alongside those that are built from scratch when this classifier runs. Note that it does not make sense to include pre-built classifiers in a cross-validation since they are static and their models do not change from fold to fold.
seed	The random number seed to be used.

Capabilities

The table below describes the capabilities of Vote.

Capability	Supported
Class	Binary class, Date class, Numeric class, Nominal class, Missing class values
Attributes	Binary attributes, Unary attributes, Missing values, Empty nominal attributes, String attributes, Numeric attributes, Nominal attributes, Relational attributes, Date attributes
Min # of instances	0

Browser not supported