org.apache.commons.math3.fitting.leastsquares

Class LeastSquaresFactory.LocalLeastSquaresProblem

java.lang.Object

org.apache.commons.math3.optim.AbstractOptimizationProblem<LeastSquaresProblem.Evaluation>

org.apache.commons.math3.fitting.leastsquares.LeastSquaresFactory.LocalLeastSquaresProblem

All Implemented Interfaces:

LeastSquaresProblem, OptimizationProblem<LeastSquaresProblem.Evaluation>

Enclosing class:

LeastSquaresFactory

private static class LeastSquaresFactory.LocalLeastSquaresProblem
extends AbstractOptimizationProblem<LeastSquaresProblem.Evaluation>
implements LeastSquaresProblem

A private, "field" immutable (not "real" immutable) implementation of LeastSquaresProblem.

Since:

3.3

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
private static class	LeastSquaresFactory.LocalLeastSquaresProblem.LazyUnweightedEvaluation Container with the model lazy evaluation at a particular point.
private static class	LeastSquaresFactory.LocalLeastSquaresProblem.UnweightedEvaluation Container with the model evaluation at a particular point.

Nested classes/interfaces inherited from interface org.apache.commons.math3.fitting.leastsquares.LeastSquaresProblem

LeastSquaresProblem.Evaluation

Field Summary

Fields

Modifier and Type	Field and Description
private boolean	lazyEvaluation Whether to use lazy evaluation.
private MultivariateJacobianFunction	model Model function.
private ParameterValidator	paramValidator Model parameters validator.
private RealVector	start Initial guess.
private RealVector	target Target values for the model function at optimum.

Constructor Summary

Constructors

Constructor and Description
LeastSquaresFactory.LocalLeastSquaresProblem(MultivariateJacobianFunction model, RealVector target, RealVector start, ConvergenceChecker<LeastSquaresProblem.Evaluation> checker, int maxEvaluations, int maxIterations, boolean lazyEvaluation, ParameterValidator paramValidator) Create a LeastSquaresProblem from the given data.

Method Summary

Methods

Modifier and Type	Method and Description
LeastSquaresProblem.Evaluation	evaluate(RealVector point) Evaluate the model at the specified point.
int	getObservationSize() Get the number of observations (rows in the Jacobian) in this problem.
int	getParameterSize() Get the number of parameters (columns in the Jacobian) in this problem.
RealVector	getStart() Gets the initial guess.

Methods inherited from class org.apache.commons.math3.optim.AbstractOptimizationProblem

getConvergenceChecker, getEvaluationCounter, getIterationCounter

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.apache.commons.math3.optim.OptimizationProblem

getConvergenceChecker, getEvaluationCounter, getIterationCounter

Field Detail

target

private final RealVector target

Target values for the model function at optimum.

model

private final MultivariateJacobianFunction model

Model function.

start

private final RealVector start

Initial guess.

lazyEvaluation

private final boolean lazyEvaluation

Whether to use lazy evaluation.

paramValidator

private final ParameterValidator paramValidator

Model parameters validator.

Constructor Detail

LeastSquaresFactory.LocalLeastSquaresProblem

LeastSquaresFactory.LocalLeastSquaresProblem(MultivariateJacobianFunction model,
                                            RealVector target,
                                            RealVector start,
                                            ConvergenceChecker<LeastSquaresProblem.Evaluation> checker,
                                            int maxEvaluations,
                                            int maxIterations,
                                            boolean lazyEvaluation,
                                            ParameterValidator paramValidator)

Create a LeastSquaresProblem from the given data.

Parameters:

model - the model function

target - the observed data

start - the initial guess

checker - the convergence checker

maxEvaluations - the allowed evaluations

maxIterations - the allowed iterations

lazyEvaluation - Whether the call to LeastSquaresProblem.evaluate(RealVector) will defer the evaluation until access to the value is requested.

paramValidator - Model parameters validator.

Method Detail

getObservationSize

public int getObservationSize()

Get the number of observations (rows in the Jacobian) in this problem.

Specified by:

getObservationSize in interface LeastSquaresProblem

Returns:

the number of scalar observations

getParameterSize

public int getParameterSize()

Get the number of parameters (columns in the Jacobian) in this problem.

Specified by:

getParameterSize in interface LeastSquaresProblem

Returns:

the number of scalar parameters

getStart

public RealVector getStart()

Gets the initial guess.

Specified by:

getStart in interface LeastSquaresProblem

Returns:

the initial guess values.

evaluate

public LeastSquaresProblem.Evaluation evaluate(RealVector point)

Evaluate the model at the specified point.

Specified by:

evaluate in interface LeastSquaresProblem

Parameters:

point - the parameter values.

Returns:

the model's value and derivative at the given point.