org.hawkular.datamining.forecast

Class AutomaticForecaster.PeriodicIntervalStrategy

java.lang.Object

org.hawkular.datamining.forecast.AutomaticForecaster.ConceptDriftStrategy

org.hawkular.datamining.forecast.AutomaticForecaster.PeriodicIntervalStrategy

Enclosing class:

AutomaticForecaster

public static class AutomaticForecaster.PeriodicIntervalStrategy
extends AutomaticForecaster.ConceptDriftStrategy

The best model is periodically selected after each x learned points.

Field Summary

Fields inherited from class org.hawkular.datamining.forecast.AutomaticForecaster.ConceptDriftStrategy

forecaster

Constructor Summary

Constructors

Constructor and Description
PeriodicIntervalStrategy(int period)

Method Summary

Modifier and Type	Method and Description
boolean	equals(Object o)
int	getPeriod()
int	hashCode()
boolean	shouldSelectNewModel(int learnSize)

Methods inherited from class java.lang.Object

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

Constructor Detail

PeriodicIntervalStrategy

public PeriodicIntervalStrategy(int period)

Parameters:

period - number of learning points after which the best model is selected

Method Detail

shouldSelectNewModel

public boolean shouldSelectNewModel(int learnSize)

Specified by:

shouldSelectNewModel in class AutomaticForecaster.ConceptDriftStrategy

Parameters:

learnSize - size of dataSet from learn method

Returns:

true if model should be selected - concept drift is present

getPeriod

public int getPeriod()

equals

public boolean equals(Object o)

Overrides:

equals in class Object

hashCode

public int hashCode()

Overrides:

hashCode in class Object