Class UnivariateKernelEstimator

java.lang.Object
weka.estimators.UnivariateKernelEstimator
All Implemented Interfaces:
Serializable, RevisionHandler, UnivariateDensityEstimator, UnivariateIntervalEstimator, UnivariateQuantileEstimator

Simple weighted kernel density estimator.
Version:
$Revision: 11318 $
Author:
Eibe Frank (eibe@cs.waikato.ac.nz)
See Also:
  • Field Summary

    Fields
    Modifier and Type
    Field
    Description
    static final double
    Constant for Gaussian density.
  • Constructor Summary

    Constructors
    Constructor
    Description
     
  • Method Summary

    Modifier and Type
    Method
    Description
    void
    addValue(double value, double weight)
    Adds a value to the density estimator.
    Returns the revision string.
    Returns a string describing the estimator.
    double
    logDensity(double value)
    Returns the natural logarithm of the density estimate at the given point.
    static void
    main(String[] args)
    Main method, used for testing this class.
    double[][]
    predictIntervals(double conf)
    Returns the interval for the given confidence value.
    double
    predictQuantile(double percentage)
    Returns the quantile for the given percentage.
    Returns textual description of this estimator.
    void
    Updates bandwidth: the sample standard deviation is multiplied by the total weight to the power of the given exponent.

    Methods inherited from class java.lang.Object

    equals, getClass, hashCode, notify, notifyAll, wait, wait, wait
  • Field Details

    • CONST

      public static final double CONST
      Constant for Gaussian density.
  • Constructor Details

    • UnivariateKernelEstimator

      public UnivariateKernelEstimator()
  • Method Details

    • globalInfo

      public String globalInfo()
      Returns a string describing the estimator.
    • addValue

      public void addValue(double value, double weight)
      Adds a value to the density estimator.
      Specified by:
      addValue in interface UnivariateDensityEstimator
      Specified by:
      addValue in interface UnivariateIntervalEstimator
      Specified by:
      addValue in interface UnivariateQuantileEstimator
      Parameters:
      value - the value to add
      weight - the weight of the value
    • updateWidth

      public void updateWidth()
      Updates bandwidth: the sample standard deviation is multiplied by the total weight to the power of the given exponent. If the total weight is not greater than zero, the width is set to Double.MAX_VALUE. If that is not the case, but the width becomes smaller than m_MinWidth, the width is set to the value of m_MinWidth.
    • predictIntervals

      public double[][] predictIntervals(double conf)
      Returns the interval for the given confidence value.
      Specified by:
      predictIntervals in interface UnivariateIntervalEstimator
      Parameters:
      conf - the confidence value in the interval [0, 1]
      Returns:
      the interval
    • predictQuantile

      public double predictQuantile(double percentage)
      Returns the quantile for the given percentage.
      Specified by:
      predictQuantile in interface UnivariateQuantileEstimator
      Parameters:
      percentage - the percentage
      Returns:
      the quantile
    • logDensity

      public double logDensity(double value)
      Returns the natural logarithm of the density estimate at the given point.
      Specified by:
      logDensity in interface UnivariateDensityEstimator
      Parameters:
      value - the value at which to evaluate
      Returns:
      the natural logarithm of the density estimate at the given value
    • toString

      public String toString()
      Returns textual description of this estimator.
      Overrides:
      toString in class Object
    • getRevision

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

      public static void main(String[] args)
      Main method, used for testing this class.