This is documentation for Caché & Ensemble.

For information on converting to InterSystems IRIS, see the InterSystems IRIS Adoption Guide and the InterSystems IRIS In-Place Conversion Guide, both available on the WRC Distributions page (login required).

Home > Class Reference > %SYS namespace > %iKnow.Classification.Methods.naiveBayes

%iKnow.Classification.Methods.naiveBayes

class %iKnow.Classification.Methods.naiveBayes extends %iKnow.Classification.Methods.Base

This classification method relies on the Naive Bayes theorem to calculate the probability a document belongs to a category based on probability scores for the individual terms.

Given this probability-based approach, the document vector local weights and normalization settings are fixed at "binary" and "none" respectively.

Method Inventory

Methods

method %BuildClassificationMethod(ByRef pClassifier As %iKnow.Classification.Definition.Classifier, pVerbose As %Boolean = 1, pIncludeBuilderParams As %Boolean = 1) as %Status

Inherited Members

Inherited Properties

Inherited Methods