ClassOrder

Package

weka.filters.supervised.attribute

Synopsis

Changes the order of the classes so that the class values are no longer of in the order specified in the header. The values will be in the order specified by the user – it could be either in ascending/descending order by the class frequency or in random order. Note that this filter currently does not change the header, only the class values of the instances, so there is not much point in using it in conjunction with the FilteredClassifier. The value can also be converted back using 'originalValue(double value)' procedure.

Options

The table below describes the options available for ClassOrder.

Option

Description

classOrder

Specify the class order after the filtering

seed

Specify the seed of randomization of the class order

Capabilities

The table below describes the capabilites of ClassOrder.

Capability

Supported

Class

Nominal class, Binary class

Attributes

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

Min # of instances

0