org.apache.mahout.clustering

Class RunningSumsGaussianAccumulator

java.lang.Object

org.apache.mahout.clustering.RunningSumsGaussianAccumulator

All Implemented Interfaces:

GaussianAccumulator

public class RunningSumsGaussianAccumulator
extends Object
implements GaussianAccumulator

An online Gaussian accumulator that uses a running power sums approach as reported on http://en.wikipedia.org/wiki/Standard_deviation Suffers from overflow, underflow and roundoff error but has minimal observe-time overhead

Constructor Summary

Constructors

Constructor and Description
RunningSumsGaussianAccumulator()

Method Summary

Methods

Modifier and Type	Method and Description
void	compute() Compute the mean, variance and standard deviation
double	getAverageStd()
Vector	getMean()
double	getN()
Vector	getStd()
Vector	getVariance()
void	observe(Vector x, double weight) Observe the vector

Methods inherited from class java.lang.Object

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

Constructor Detail

RunningSumsGaussianAccumulator

public RunningSumsGaussianAccumulator()

Method Detail

getN

public double getN()

Specified by:

getN in interface GaussianAccumulator

Returns:

the number of observations

getMean

public Vector getMean()

Specified by:

getMean in interface GaussianAccumulator

Returns:

the mean of the observations

getStd

public Vector getStd()

Specified by:

getStd in interface GaussianAccumulator

Returns:

the std of the observations

getAverageStd

public double getAverageStd()

Specified by:

getAverageStd in interface GaussianAccumulator

Returns:

the average of the vector std elements

getVariance

public Vector getVariance()

Specified by:

getVariance in interface GaussianAccumulator

Returns:

the variance of the observations

observe

public void observe(Vector x,
           double weight)

Description copied from interface: GaussianAccumulator

Observe the vector

Specified by:

observe in interface GaussianAccumulator

Parameters:

x - a Vector

weight - the double observation weight (usually 1.0)

compute

public void compute()

Description copied from interface: GaussianAccumulator

Compute the mean, variance and standard deviation

Specified by:

compute in interface GaussianAccumulator