smile.interpolation

Class LaplaceInterpolation

java.lang.Object

smile.interpolation.LaplaceInterpolation

public class LaplaceInterpolation
extends java.lang.Object

Laplace interpolation to restore missing or unmeasured values on a 2-dimensional evenly spaced regular grid. In some sense, Laplace interpolation produces the smoothest possible interpolant, which are obtained by solving a very sparse linear equations with biconjugate gradient method.

Constructor Summary

Constructors

Constructor and Description
LaplaceInterpolation()

Method Summary

Modifier and Type	Method and Description
static double	interpolate(double[][] matrix) Laplace interpolation.
static double	interpolate(double[][] matrix, double tol) Laplace interpolation.
static double	interpolate(double[][] matrix, double tol, int maxIter) Laplace interpolation.

Methods inherited from class java.lang.Object

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

Constructor Detail

LaplaceInterpolation

public LaplaceInterpolation()

Method Detail

interpolate

public static double interpolate(double[][] matrix)

Laplace interpolation.

Parameters:

matrix - on input, values of NaN are deemed to be missing data. On output, they are refilled with the interpolated solution.

Returns:

the estimated error.

interpolate

public static double interpolate(double[][] matrix,
                                 double tol)

Laplace interpolation.

Parameters:

matrix - on input, values of NaN are deemed to be missing data. On output, they are refilled with the interpolated solution.

tol - the desired convergence tolerance.

Returns:

the estimated error.

interpolate

public static double interpolate(double[][] matrix,
                                 double tol,
                                 int maxIter)

Laplace interpolation.

Parameters:

matrix - on input, values of NaN are deemed to be missing data. On output, they are refilled with the interpolated solution.

tol - the desired convergence tolerance.

maxIter - the maximum number of allowed iterations.

Returns:

the estimated error.