Package adams.flow.transformer

Class WekaTrainClusterer

  • All Implemented Interfaces:
    AdditionalInformationHandler, CleanUpHandler, Destroyable, GlobalInfoSupporter, LoggingLevelHandler, LoggingSupporter, OptionHandler, QuickInfoSupporter, ShallowCopySupporter<Actor>, SizeOfHandler, Stoppable, StoppableWithFeedback, VariablesInspectionHandler, VariableChangeListener, Actor, ErrorHandler, InputConsumer, OutputProducer, JobRunnerSupporter, Serializable, Comparable
    public class WekaTrainClusterer
extends AbstractTransformer
implements JobRunnerSupporter
    Trains a clusterer based on the incoming dataset and output the built clusterer alongside the training header (in a model container).
    Incremental training is performed, if the input are weka.core.Instance objects and the clusterer implements weka.clusterers.UpdateableClusterer.

    Input/output:
    - accepts:
       weka.core.Instances
       weka.core.Instance
    - generates:
       adams.flow.container.WekaModelContainer


    Container information:
    - adams.flow.container.WekaModelContainer: Model, Header, Dataset 

    -logging-level <OFF|SEVERE|WARNING|INFO|CONFIG|FINE|FINER|FINEST> (property: loggingLevel)
    The logging level for outputting errors and debugging output.
    default: WARNING
    min-user-mode: Expert
 
    -name <java.lang.String> (property: name)
    The name of the actor.
    default: WekaTrainClusterer
 
    -annotation <adams.core.base.BaseAnnotation> (property: annotations)
    The annotations to attach to this actor.
    default:
 
    -skip <boolean> (property: skip)
    If set to true, transformation is skipped and the input token is just forwarded
    as it is.
    default: false
 
    -stop-flow-on-error <boolean> (property: stopFlowOnError)
    If set to true, the flow execution at this level gets stopped in case this
    actor encounters an error; the error gets propagated; useful for critical
    actors.
    default: false
    min-user-mode: Expert
 
    -silent <boolean> (property: silent)
    If enabled, then no errors are output in the console; Note: the enclosing
    actor handler must have this enabled as well.
    default: false
    min-user-mode: Expert
 
    -clusterer <adams.flow.core.CallableActorReference> (property: clusterer)
    The Weka clusterer to build on the input data.
    default: WekaClustererSetup
 
    -post-processor <adams.flow.transformer.wekaclusterer.AbstractClustererPostProcessor> (property: postProcessor)
    The post-processor to use on model containers.
    default: adams.flow.transformer.wekaclusterer.PassThrough
 
    -prefer-jobrunner <boolean> (property: preferJobRunner)
    If enabled, tries to offload the processing onto a adams.flow.standalone.JobRunnerInstance;
     applies only to batch training.
    default: false
    Author:
    fracpete (fracpete at waikato dot ac dot nz)
    See Also:
    Serialized Form

    • Field Detail

      • BACKUP_INCREMENTALCLUSTERER

        public static final String BACKUP_INCREMENTALCLUSTERER
        the key for storing the current incremental clusterer in the backup.
        See Also:
        Constant Field Values

      • m_ActualClusterer

        protected weka.clusterers.Clusterer m_ActualClusterer
        the weka clusterer.

      • m_IncrementalClusterer

        protected weka.clusterers.Clusterer m_IncrementalClusterer
        the clusterer used when training incrementally.

      • m_PreferJobRunner

        protected boolean m_PreferJobRunner
        whether to offload training into a JobRunnerInstance.

      • m_JobRunnerInstance

        protected transient JobRunnerInstance m_JobRunnerInstance
        the JobRunnerInstance to use.

    • Constructor Detail

      • WekaTrainClusterer

        public WekaTrainClusterer()