org.processmining.nlplogutils.algorithms.analysis.adaptive

Class InstanceLabeler

java.lang.Object

org.processmining.nlplogutils.algorithms.analysis.adaptive.InstanceLabeler

public class InstanceLabeler
extends java.lang.Object

Used to add a label to an instance and prepare for the learner to know which clustering is most appropriate. It tries for each event, all method configurations, and checks, which one yields the best original event labels back It uses purity to find the best technique in the cohort and uses that to label the instance. Actually, multiple labels can yield optimal clustering. Created by andreas on 2/22/17.

Constructor Summary

Constructors

Constructor and Description
InstanceLabeler()

Method Summary

Modifier and Type	Method and Description
java.util.Map<java.lang.String,TrainingInstance>	getInstances(org.deckfour.xes.model.XLog log, java.util.Map<java.lang.String,ContextFeatures> instancesWithoutLabel, NLPLogUtilsParameters nlpParameters, java.lang.String logName)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

InstanceLabeler

public InstanceLabeler()

Method Detail

getInstances

public java.util.Map<java.lang.String,TrainingInstance> getInstances(org.deckfour.xes.model.XLog log,
                                                                     java.util.Map<java.lang.String,ContextFeatures> instancesWithoutLabel,
                                                                     NLPLogUtilsParameters nlpParameters,
                                                                     java.lang.String logName)