Package adams.flow.transformer

Class MOARegressorEvaluation

  • All Implemented Interfaces:
    adams.core.AdditionalInformationHandler, adams.core.CleanUpHandler, adams.core.Destroyable, adams.core.GlobalInfoSupporter, adams.core.logging.LoggingLevelHandler, adams.core.logging.LoggingSupporter, adams.core.option.OptionHandler, adams.core.QuickInfoSupporter, adams.core.ShallowCopySupporter<adams.flow.core.Actor>, adams.core.SizeOfHandler, adams.core.Stoppable, adams.core.StoppableWithFeedback, adams.core.VariablesInspectionHandler, adams.event.VariableChangeListener, adams.flow.core.Actor, adams.flow.core.ErrorHandler, adams.flow.core.InputConsumer, adams.flow.core.OutputProducer, Serializable, Comparable
    public class MOARegressorEvaluation
extends adams.flow.transformer.AbstractTransformer
    Evaluates a MOA regressor using prequential evaluation. With each incoming instance, the regressor is first evaluated, then trained.

    Input/output:
    - accepts:
       com.yahoo.labs.samoa.instances.Instance
       com.yahoo.labs.samoa.instances.Instances
    - generates:
       moa.core.Measurement[]


    -logging-level <OFF|SEVERE|WARNING|INFO|CONFIG|FINE|FINER|FINEST> (property: loggingLevel)
    The logging level for outputting errors and debugging output.
    default: WARNING
 
    -name <java.lang.String> (property: name)
    The name of the actor.
    default: MOARegressorEvaluation
 
    -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
 
    -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
 
    -regressor <adams.flow.core.CallableActorReference> (property: regressor)
    The name of the callable MOA regressor to train/evaluate.
    default: MOARegressor
 
    -evaluator <moa.options.ClassOption> (property: evaluator)
    The MOA evaluator to use for evaluating a trained MOA regressor.
    default: BasicRegressionPerformanceEvaluator
 
    -output-interval <int> (property: outputInterval)
    The number of tokens to skip before evaluating the regressor stored in the
    token (only used when receiving Instance objects).
    default: 1
    minimum: 1
    Author:
    fracpete (fracpete at waikato dot ac dot nz)
    See Also:
    Serialized Form

    • Field Summary

      Fields 
      Modifier and Type Field Description
      static String BACKUP_REGRESSOR
      the key for storing the current regressor in the backup.
      protected moa.evaluation.RegressionPerformanceEvaluator m_ActualEvaluator
      the actual evaluator to use.
      protected moa.classifiers.AbstractClassifier m_ActualRegressor
      the model to use for prediction/training.
      protected int m_Count
      the current count of tokens that have passed through this actor.
      protected moa.options.ClassOption m_Evaluator
      the evaluation to use.
      protected int m_OutputInterval
      the output interval.
      protected adams.flow.core.CallableActorReference m_Regressor
      the name of the callable regressor to use.

      • Fields inherited from class adams.flow.transformer.AbstractTransformer

        BACKUP_INPUT, BACKUP_OUTPUT, m_InputToken, m_OutputToken

      • Fields inherited from class adams.flow.core.AbstractActor

        m_Annotations, m_BackupState, m_DetectedObjectVariables, m_DetectedVariables, m_ErrorHandler, m_Executed, m_Executing, m_ExecutionListeningSupporter, m_FullName, m_LoggingPrefix, m_Name, m_Parent, m_ScopeHandler, m_Self, m_Silent, m_Skip, m_StopFlowOnError, m_StopMessage, m_Stopped, m_StorageHandler, m_VariablesUpdated

      • Fields inherited from class adams.core.option.AbstractOptionHandler

        m_OptionManager

      • Fields inherited from class adams.core.logging.LoggingObject

        m_Logger, m_LoggingIsEnabled, m_LoggingLevel

      • Fields inherited from interface adams.flow.core.Actor

        FILE_EXTENSION, FILE_EXTENSION_GZ

    • Method Summary

      All Methods Instance Methods Concrete Methods 
      Modifier and Type Method Description
      Class[] accepts()
      Returns the class that the consumer accepts.
      protected Hashtable<String,​Object> backupState()
      Backs up the current state of the actor before update the variables.
      void defineOptions()
      Adds options to the internal list of options.
      protected String doExecute()
      Executes the flow item.
      String evaluatorTipText()
      Returns the tip text for this property.
      Class[] generates()
      Returns the class of objects that it generates.
      protected moa.evaluation.RegressionPerformanceEvaluator getCurrentEvaluator()
      Returns the current evaluator, based on the class option.
      protected moa.evaluation.RegressionPerformanceEvaluator getDefaultEvaluator()
      Returns the default evaluator.
      protected moa.options.ClassOption getDefaultOption()
      Returns the default class option.
      moa.options.ClassOption getEvaluator()
      Returns the evaluator in use.
      int getOutputInterval()
      Returns the number of tokens after which to evaluate the regressor.
      String getQuickInfo()
      Returns a quick info about the actor, which will be displayed in the GUI.
      adams.flow.core.CallableActorReference getRegressor()
      Returns the callable regressor to use.
      protected moa.classifiers.AbstractClassifier getRegressorInstance()
      Returns an instance of the callable regressor.
      String globalInfo()
      Returns a string describing the object.
      protected void initialize()
      Initializes the members.
      String outputIntervalTipText()
      Returns the tip text for this property.
      protected void pruneBackup()
      Removes entries from the backup.
      String regressorTipText()
      Returns the tip text for this property.
      protected void reset()
      Initializes the members.
      protected void restoreState​(Hashtable<String,​Object> state)
      Restores the state of the actor before the variables got updated.
      void setEvaluator​(moa.options.ClassOption value)
      Sets the evaluator to use.
      void setOutputInterval​(int value)
      Sets the number of tokens after which to evaluate the regressor.
      void setRegressor​(adams.flow.core.CallableActorReference value)
      Sets the callable regressor to use.
      void wrapUp()
      Cleans up after the execution has finished.

      • Methods inherited from class adams.flow.transformer.AbstractTransformer

        currentInput, execute, hasInput, hasPendingOutput, input, output, postExecute

      • Methods inherited from class adams.flow.core.AbstractActor

        annotationsTipText, canInspectOptions, canPerformSetUpCheck, cleanUp, compareTo, configureLogger, destroy, equals, finalUpdateVariables, findVariables, findVariables, forceVariables, forCommandLine, forName, forName, getAdditionalInformation, getAnnotations, getDefaultName, getDetectedVariables, getErrorHandler, getFlowActors, getFlowExecutionListeningSupporter, getFullName, getName, getNextSibling, getParent, getParentComponent, getPreviousSibling, getRoot, getScopeHandler, getSilent, getSkip, getStopFlowOnError, getStopMessage, getStorageHandler, getVariables, handleError, handleException, hasErrorHandler, hasStopMessage, index, isBackedUp, isExecuted, isExecuting, isFinished, isHeadless, isStopped, nameTipText, performSetUpChecks, performVariableChecks, preExecute, pruneBackup, setAnnotations, setErrorHandler, setName, setParent, setSilent, setSkip, setStopFlowOnError, setUp, setVariables, shallowCopy, shallowCopy, silentTipText, sizeOf, skipTipText, stopExecution, stopExecution, stopFlowOnErrorTipText, updateDetectedVariables, updatePrefix, updateVariables, variableChanged

      • Methods inherited from class adams.core.option.AbstractOptionHandler

        cleanUpOptions, finishInit, getDefaultLoggingLevel, getOptionManager, loggingLevelTipText, newOptionManager, setLoggingLevel, toCommandLine, toString

      • Methods inherited from class adams.core.logging.LoggingObject

        getLogger, getLoggingLevel, initializeLogging, isLoggingEnabled

      • Methods inherited from interface adams.flow.core.Actor

        cleanUp, compareTo, destroy, equals, findVariables, getAnnotations, getDefaultName, getDetectedVariables, getErrorHandler, getFlowExecutionListeningSupporter, getFullName, getName, getNextSibling, getParent, getParentComponent, getPreviousSibling, getRoot, getScopeHandler, getSilent, getSkip, getStopFlowOnError, getStopMessage, getStorageHandler, getVariables, handleError, hasErrorHandler, hasStopMessage, index, isExecuted, isFinished, isHeadless, isStopped, setAnnotations, setErrorHandler, setName, setParent, setSilent, setSkip, setStopFlowOnError, setUp, setVariables, shallowCopy, shallowCopy, sizeOf, stopExecution, stopExecution, toCommandLine, variableChanged

      • Methods inherited from interface adams.core.AdditionalInformationHandler

        getAdditionalInformation

      • Methods inherited from interface adams.core.logging.LoggingLevelHandler

        getLoggingLevel, setLoggingLevel

      • Methods inherited from interface adams.core.logging.LoggingSupporter

        getLogger, isLoggingEnabled

      • Methods inherited from interface adams.core.option.OptionHandler

        cleanUpOptions, getOptionManager

      • Methods inherited from interface adams.core.VariablesInspectionHandler

        canInspectOptions

    • Field Detail

      • BACKUP_REGRESSOR

        public static final String BACKUP_REGRESSOR
        the key for storing the current regressor in the backup.
        See Also:
        Constant Field Values

      • m_Regressor

        protected adams.flow.core.CallableActorReference m_Regressor
        the name of the callable regressor to use.

      • m_ActualRegressor

        protected moa.classifiers.AbstractClassifier m_ActualRegressor
        the model to use for prediction/training.

      • m_Evaluator

        protected moa.options.ClassOption m_Evaluator
        the evaluation to use.

      • m_ActualEvaluator

        protected moa.evaluation.RegressionPerformanceEvaluator m_ActualEvaluator
        the actual evaluator to use.

      • m_OutputInterval

        protected int m_OutputInterval
        the output interval.

      • m_Count

        protected int m_Count
        the current count of tokens that have passed through this actor.

    • Constructor Detail

      • MOARegressorEvaluation

        public MOARegressorEvaluation()

    • Method Detail

      • globalInfo

        public String globalInfo()
        Returns a string describing the object.
        Specified by:
        globalInfo in interface adams.core.GlobalInfoSupporter
        Specified by:
        globalInfo in class adams.core.option.AbstractOptionHandler
        Returns:
        a description suitable for displaying in the gui

      • defineOptions

        public void defineOptions()
        Adds options to the internal list of options.
        Specified by:
        defineOptions in interface adams.core.option.OptionHandler
        Overrides:
        defineOptions in class adams.flow.core.AbstractActor

      • reset

        protected void reset()
        Initializes the members.
        Overrides:
        reset in class adams.flow.core.AbstractActor

      • initialize

        protected void initialize()
        Initializes the members.
        Overrides:
        initialize in class adams.flow.core.AbstractActor

      • setRegressor

        public void setRegressor​(adams.flow.core.CallableActorReference value)
        Sets the callable regressor to use.
        Parameters:
        value - the regressor name

      • getRegressor

        public adams.flow.core.CallableActorReference getRegressor()
        Returns the callable regressor to use.
        Returns:
        the regressor name

      • regressorTipText

        public String regressorTipText()
        Returns the tip text for this property.
        Returns:
        tip text for this property suitable for displaying in the GUI or for listing the options.

      • getDefaultEvaluator

        protected moa.evaluation.RegressionPerformanceEvaluator getDefaultEvaluator()
        Returns the default evaluator.
        Returns:
        the evaluator

      • getDefaultOption

        protected moa.options.ClassOption getDefaultOption()
        Returns the default class option.
        Returns:
        the option

      • setEvaluator

        public void setEvaluator​(moa.options.ClassOption value)
        Sets the evaluator to use.
        Parameters:
        value - the evaluator

      • getEvaluator

        public moa.options.ClassOption getEvaluator()
        Returns the evaluator in use.
        Returns:
        the evaluator

      • evaluatorTipText

        public String evaluatorTipText()
        Returns the tip text for this property.
        Returns:
        tip text for this property suitable for displaying in the GUI or for listing the options.

      • getCurrentEvaluator

        protected moa.evaluation.RegressionPerformanceEvaluator getCurrentEvaluator()
        Returns the current evaluator, based on the class option.
        Returns:
        the evaluator
        See Also:
        getEvaluator()

      • setOutputInterval

        public void setOutputInterval​(int value)
        Sets the number of tokens after which to evaluate the regressor.
        Parameters:
        value - the interval

      • getOutputInterval

        public int getOutputInterval()
        Returns the number of tokens after which to evaluate the regressor.
        Returns:
        the interval

      • outputIntervalTipText

        public String outputIntervalTipText()
        Returns the tip text for this property.
        Returns:
        tip text for this property suitable for displaying in the GUI or for listing the options.

      • getQuickInfo

        public String getQuickInfo()
        Returns a quick info about the actor, which will be displayed in the GUI.
        Specified by:
        getQuickInfo in interface adams.flow.core.Actor
        Specified by:
        getQuickInfo in interface adams.core.QuickInfoSupporter
        Overrides:
        getQuickInfo in class adams.flow.core.AbstractActor
        Returns:
        null if no info available, otherwise short string

      • accepts

        public Class[] accepts()
        Returns the class that the consumer accepts.
        Returns:
        com.yahoo.labs.samoa.instances.Instance.class, com.yahoo.labs.samoa.instances.Instances.class

      • generates

        public Class[] generates()
        Returns the class of objects that it generates.
        Returns:
        moa.core.Measurement[].class

      • pruneBackup

        protected void pruneBackup()
        Removes entries from the backup.
        Overrides:
        pruneBackup in class adams.flow.core.AbstractActor

      • backupState

        protected Hashtable<String,​Object> backupState()
        Backs up the current state of the actor before update the variables.
        Overrides:
        backupState in class adams.flow.transformer.AbstractTransformer
        Returns:
        the backup

      • restoreState

        protected void restoreState​(Hashtable<String,​Object> state)
        Restores the state of the actor before the variables got updated.
        Overrides:
        restoreState in class adams.flow.transformer.AbstractTransformer
        Parameters:
        state - the backup of the state to restore from

      • getRegressorInstance

        protected moa.classifiers.AbstractClassifier getRegressorInstance()
        Returns an instance of the callable regressor.
        Returns:
        the classifier

      • doExecute

        protected String doExecute()
        Executes the flow item.
        Specified by:
        doExecute in class adams.flow.core.AbstractActor
        Returns:
        null if everything is fine, otherwise error message

      • wrapUp

        public void wrapUp()
        Cleans up after the execution has finished.
        Specified by:
        wrapUp in interface adams.flow.core.Actor
        Overrides:
        wrapUp in class adams.flow.transformer.AbstractTransformer