Package org.pentaho.di.forecasting

Class WekaForecastingModel

java.lang.Object
org.pentaho.di.forecasting.WekaForecastingModel
All Implemented Interfaces:
Serializable
public class WekaForecastingModel extends Object implements Serializable
Abstract wrapper class for a Weka Forecaster.
Version:
$Revision$
Author:
Mark Hall (mhall{[at]}pentaho{[dot]}com)
See Also:

  • Field Summary

    Fields
    Modifier and Type
    Field
    Description
    protected weka.classifiers.timeseries.TSForecaster
    m_model
     

  • Constructor Summary

    Constructors
    Constructor
    Description
    WekaForecastingModel(weka.classifiers.timeseries.TSForecaster model)
    Creates a new WekaForecastingModel instance.

  • Method Summary

    Modifier and Type
    Method
    Description
    List<String>
    getForecastedFields()
    Get a list of the field names that the encapsulated forecaster can predict.
    weka.core.Instances
    getHeader()
    Get the header of the Instances that was used build this Weka model
    weka.classifiers.timeseries.TSForecaster
    getModel()
    Get the forecasting model
    boolean
    isProducingConfidenceIntervals()
    Returns true if the encapsulated model can and is producing confidence intervals on its forcasted values.
    void
    setHeader(weka.core.Instances header)
    Set the Instances header
    void
    setLog(org.pentaho.di.core.logging.LogChannelInterface log)
    Set the log to pass on to the model.
    void
    setModel(weka.classifiers.timeseries.TSForecaster model)
    Set the forecasting model
    String
    toString()
    Return a textual description of the encapsulated forecasting model

    Methods inherited from class java.lang.Object

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

  • Field Details

    • m_model

      protected weka.classifiers.timeseries.TSForecaster m_model

  • Constructor Details

    • WekaForecastingModel

      public WekaForecastingModel(weka.classifiers.timeseries.TSForecaster model)
      Creates a new WekaForecastingModel instance.
      Parameters:
      model - the actual Weka model to enacpsulate

  • Method Details

    • setLog

      public void setLog(org.pentaho.di.core.logging.LogChannelInterface log)
      Set the log to pass on to the model. require logging.
      Parameters:
      log - the log to use

    • setHeader

      public void setHeader(weka.core.Instances header)
      Set the Instances header
      Parameters:
      header - an Instances value

    • getHeader

      public weka.core.Instances getHeader()
      Get the header of the Instances that was used build this Weka model
      Returns:
      an Instances value

    • setModel

      public void setModel(weka.classifiers.timeseries.TSForecaster model)
      Set the forecasting model
      Parameters:
      model - the forecasting model

    • getModel

      public weka.classifiers.timeseries.TSForecaster getModel()
      Get the forecasting model
      Returns:
      the forecasting model as an object

    • getForecastedFields

      public List<String> getForecastedFields()
      Get a list of the field names that the encapsulated forecaster can predict.
      Returns:
      a list of predicted field names.

    • isProducingConfidenceIntervals

      public boolean isProducingConfidenceIntervals()
      Returns true if the encapsulated model can and is producing confidence intervals on its forcasted values.
      Returns:
      true if the forecaster produces confidence limits for its predicted values

    • toString

      public String toString()
      Return a textual description of the encapsulated forecasting model
      Overrides:
      toString in class Object
      Returns:
      a textual description of the encapsulated forecasting model