org.apache.commons.math.optimization.fitting

Class GaussianFitter

java.lang.Object

org.apache.commons.math.optimization.fitting.GaussianFitter

public class GaussianFitter
extends Object

Fits points to a Gaussian function (that is, a GaussianFunction).

Usage example:

   GaussianFitter fitter = new GaussianFitter(
     new LevenbergMarquardtOptimizer());
   fitter.addObservedPoint(4.0254623,  531026.0);
   fitter.addObservedPoint(4.03128248, 984167.0);
   fitter.addObservedPoint(4.03839603, 1887233.0);
   fitter.addObservedPoint(4.04421621, 2687152.0);
   fitter.addObservedPoint(4.05132976, 3461228.0);
   fitter.addObservedPoint(4.05326982, 3580526.0);
   fitter.addObservedPoint(4.05779662, 3439750.0);
   fitter.addObservedPoint(4.0636168,  2877648.0);
   fitter.addObservedPoint(4.06943698, 2175960.0);
   fitter.addObservedPoint(4.07525716, 1447024.0);
   fitter.addObservedPoint(4.08237071, 717104.0);
   fitter.addObservedPoint(4.08366408, 620014.0);
  GaussianFunction fitFunction = fitter.fit();
 

Since:

2.2

Version:

$Revision: 1073158 $ $Date: 2011-02-21 22:46:52 +0100 (lun. 21 févr. 2011) $

See Also:

ParametricGaussianFunction

Constructor Summary

Constructors

Constructor and Description
GaussianFitter(DifferentiableMultivariateVectorialOptimizer optimizer) Constructs an instance using the specified optimizer.

Method Summary

Modifier and Type	Method and Description
void	addObservedPoint(double x, double y) Adds point (x, y) to list of observed points with a weight of 1.0.
void	addObservedPoint(double weight, double x, double y) Adds point (x, y) to list of observed points with a weight of weight.
protected GaussianParametersGuesser	createParametersGuesser(WeightedObservedPoint[] observations) Factory method to create a GaussianParametersGuesser instance initialized with the specified observations.
GaussianFunction	fit() Fits Gaussian function to the observed points.

Methods inherited from class java.lang.Object

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

Constructor Detail

GaussianFitter

public GaussianFitter(DifferentiableMultivariateVectorialOptimizer optimizer)

Constructs an instance using the specified optimizer.

Parameters:

optimizer - optimizer to use for the fitting

Method Detail

addObservedPoint

public void addObservedPoint(double x,
                             double y)

Adds point (x, y) to list of observed points with a weight of 1.0.

Parameters:

x - x point value

y - y point value

addObservedPoint

public void addObservedPoint(double weight,
                             double x,
                             double y)

Adds point (x, y) to list of observed points with a weight of weight.

Parameters:

weight - weight assigned to point

x - x point value

y - y point value

fit

public GaussianFunction fit()
                     throws FunctionEvaluationException,
                            OptimizationException

Fits Gaussian function to the observed points.

Returns:

Gaussian function best fitting the observed points

Throws:

FunctionEvaluationException - if CurveFitter.fit throws it

OptimizationException - if CurveFitter.fit throws it

IllegalArgumentException - if CurveFitter.fit throws it

See Also:

CurveFitter

createParametersGuesser

protected GaussianParametersGuesser createParametersGuesser(WeightedObservedPoint[] observations)

Factory method to create a GaussianParametersGuesser instance initialized with the specified observations.

Parameters:

observations - points used to initialize the created GaussianParametersGuesser instance

Returns:

new GaussianParametersGuesser instance