de.lmu.ifi.dbs.elki.math.statistics

Class KernelDensityEstimator

java.lang.Object

de.lmu.ifi.dbs.elki.math.statistics.KernelDensityEstimator

public class KernelDensityEstimator
extends java.lang.Object

Estimate density given an array of points. Estimates a density using a variable width kernel density estimation.

Since:

0.2

Author:

Erich Schubert

Field Summary

Fields

Modifier and Type	Field and Description
private double[]	dens Result storage: density
private double[]	var Result storage: variance / quality

Constructor Summary

Constructors

Constructor and Description
KernelDensityEstimator(double[] data, double min, double max, KernelDensityFunction kernel, int window, double epsilon) Initialize and execute kernel density estimation.
KernelDensityEstimator(double[] data, KernelDensityFunction kernel, double epsilon) Process an array of data

Method Summary

Modifier and Type	Method and Description
double[]	getDensity() Retrieve density array (NO copy)
double[]	getVariance() Retrieve variance/quality array (NO copy)
private void	process(double[] data, double min, double max, KernelDensityFunction kernel, int window, double epsilon) Process a new array

Methods inherited from class java.lang.Object

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

Field Detail

dens

private double[] dens

Result storage: density

var

private double[] var

Result storage: variance / quality

Constructor Detail

KernelDensityEstimator

public KernelDensityEstimator(double[] data,
                              double min,
                              double max,
                              KernelDensityFunction kernel,
                              int window,
                              double epsilon)

Initialize and execute kernel density estimation.

Parameters:

data - data to use (must be sorted!)

min - minimum value

max - maximum value

kernel - Kernel function to use

window - window size

epsilon - Precision threshold

KernelDensityEstimator

public KernelDensityEstimator(double[] data,
                              KernelDensityFunction kernel,
                              double epsilon)

Process an array of data

Parameters:

data - data to process

kernel - Kernel function to use.

epsilon - Precision threshold

Method Detail

process

private void process(double[] data,
                     double min,
                     double max,
                     KernelDensityFunction kernel,
                     int window,
                     double epsilon)

Process a new array

Parameters:

data - data to use (must be sorted!)

min - minimum value

max - maximum value

kernel - Kernel function to use

window - window size

epsilon - Precision threshold

getDensity

public double[] getDensity()

Retrieve density array (NO copy)

Returns:

density array

getVariance

public double[] getVariance()

Retrieve variance/quality array (NO copy)

Returns:

variance array