Hitachi Vantara Pentaho Community Wiki
Child pages
  • MultiClassClassifierUpdateable
Skip to end of metadata
Go to start of metadata

Package

weka.classifiers.meta

Synopsis

A metaclassifier for handling multi-class datasets with 2-class classifiers. This classifier is also capable of applying error correcting output codes for increased accuracy. The base classifier must be an updateable classifier.

From Weka 3.7.5.

Options

The table below describes the options available for MultiClassClassifierUpdateable.

Option

Description

classifier

The base classifier to be used.

debug

If set to true, classifier may output additional info to the console.

method

Sets the method to use for transforming the multi-class problem into several 2-class ones.

randomWidthFactor

Sets the width multiplier when using random codes. The number of codes generated will be thus number multiplied by the number of classes.

seed

The random number seed to be used.

usePairwiseCoupling

Use pairwise coupling (only has an effect for 1-against-1).

Capabilities

The table below describes the capabilities of MultiClassClassifierUpdateable.

Capability

Supported

Class

Nominal class, Missing class values, Binary class

Attributes

Unary attributes, Empty nominal attributes, Date attributes, Nominal attributes, Binary attributes, Missing values, Numeric attributes

Min # of instances

1

  • No labels