BayesicFitting

Model Fitting and Evidence Calculation

View project on GitHub



class Huber( Kernel )[source]

Huber is an improper Kernel function

  K( x ) = 1.0 if |x| < 1 else 1.0 / |x|

It is improper because the integral equals +inf.

It plays a role in robust fitting, see RobustShell, for medianizing the fit.

Huber( ) [source]

Constructor.

Improper Kernel.

  Using
  integral = inf
  fwhm = 4
  range = inf

result( x ) [source]
Return the result for input values.

Parameters

  • x : array-like
         input values

partial( x ) [source]
Return the partial derivative wrt the input values.

Parameters

  • x : array-like
         the input values

isBound( ) [source]

Return False

name( ) [source]

Return the name of the kernel

Methods inherited from Kernel