Package weka.classifiers.evaluation

Class NumericPrediction

java.lang.Object
weka.classifiers.evaluation.NumericPrediction
All Implemented Interfaces:
Serializable, Prediction, RevisionHandler
public class NumericPrediction extends Object implements Prediction, Serializable, RevisionHandler
Encapsulates an evaluatable numeric prediction: the predicted class value plus the actual class value.
Version:
$Revision: 8034 $
Author:
Len Trigg (len@reeltwo.com)
See Also:

  • Field Summary

    Fields inherited from interface weka.classifiers.evaluation.Prediction

    MISSING_VALUE

  • Constructor Summary

    Constructors
    Constructor
    Description
    NumericPrediction(double actual, double predicted)
    Creates the NumericPrediction object with a default weight of 1.0.
    NumericPrediction(double actual, double predicted, double weight)
    Creates the NumericPrediction object.
    NumericPrediction(double actual, double predicted, double weight, double[][] predInt)
    Creates the NumericPrediction object.

  • Method Summary

    Modifier and Type
    Method
    Description
    double
    actual()
    Gets the actual class value.
    double
    error()
    Calculates the prediction error.
    String
    getRevision()
    Returns the revision string.
    double
    predicted()
    Gets the predicted class value.
    double[][]
    predictionIntervals()
    Returns the predictions intervals.
    void
    setPredictionIntervals(double[][] predInt)
    Sets the prediction intervals for this prediction.
    String
    toString()
    Gets a human readable representation of this prediction.
    double
    weight()
    Gets the weight assigned to this prediction.

    Methods inherited from class java.lang.Object

    equals, getClass, hashCode, notify, notifyAll, wait, wait, wait

  • Constructor Details

    • NumericPrediction

      public NumericPrediction(double actual, double predicted)
      Creates the NumericPrediction object with a default weight of 1.0.
      Parameters:
      actual - the actual value, or MISSING_VALUE.
      predicted - the predicted value, or MISSING_VALUE.

    • NumericPrediction

      public NumericPrediction(double actual, double predicted, double weight)
      Creates the NumericPrediction object.
      Parameters:
      actual - the actual value, or MISSING_VALUE.
      predicted - the predicted value, or MISSING_VALUE.
      weight - the weight assigned to the prediction.

    • NumericPrediction

      public NumericPrediction(double actual, double predicted, double weight, double[][] predInt)
      Creates the NumericPrediction object.
      Parameters:
      actual - the actual value, or MISSING_VALUE.
      predicted - the predicted value, or MISSING_VALUE.
      weight - the weight assigned to the prediction.
      predInt - the prediction intervals from classifiers implementing the IntervalEstimator interface.
      See Also:

  • Method Details

    • actual

      public double actual()
      Gets the actual class value.
      Specified by:
      actual in interface Prediction
      Returns:
      the actual class value, or MISSING_VALUE if no prediction was made.

    • predicted

      public double predicted()
      Gets the predicted class value.
      Specified by:
      predicted in interface Prediction
      Returns:
      the predicted class value, or MISSING_VALUE if no prediction was made.

    • weight

      public double weight()
      Gets the weight assigned to this prediction. This is typically the weight of the test instance the prediction was made for.
      Specified by:
      weight in interface Prediction
      Returns:
      the weight assigned to this prediction.

    • error

      public double error()
      Calculates the prediction error. This is defined as the predicted value minus the actual value.
      Returns:
      the error for this prediction, or MISSING_VALUE if either the actual or predicted value is missing.

    • setPredictionIntervals

      public void setPredictionIntervals(double[][] predInt)
      Sets the prediction intervals for this prediction.
      Parameters:
      predInt - the prediction intervals

    • predictionIntervals

      public double[][] predictionIntervals()
      Returns the predictions intervals. Only classifiers implementing the IntervalEstimator interface.
      Returns:
      the prediction intervals.
      See Also:

    • toString

      public String toString()
      Gets a human readable representation of this prediction.
      Overrides:
      toString in class Object
      Returns:
      a human readable representation of this prediction.

    • getRevision

      public String getRevision()
      Returns the revision string.
      Specified by:
      getRevision in interface RevisionHandler
      Returns:
      the revision