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

Synopsis

A filter for adding the classification, the class distribution and an error flag to a dataset with a classifier. The classifier is either trained on the data itself or provided as serialized model.

Options

The table below describes the options available for AddClassification.

Option

Description

classifier

The classifier to use for classification.

debug

Turns on output of debugging information.

outputClassification

Whether to add an attribute with the actual classification.

outputDistribution

Whether to add attributes with the distribution for all classes (for numeric classes this will be identical to the attribute output with 'outputClassification').

outputErrorFlag

Whether to add an attribute indicating whether the classifier output a wrong classification (for numeric classes this is the numeric difference).

removeOldClass

Whether to remove the old class attribute.

serializedClassifierFile

A file containing the serialized model of a trained classifier.

Capabilities

The table below describes the capabilites of AddClassification.

Capability

Supported

Class

Date class, Missing class values, Binary class, Numeric class, Nominal class

Attributes

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

Min # of instances

0

  • No labels