BayesicFitting

Model Fitting and Evidence Calculation

View project on GitHub



class SurfaceSplinesModel( LinearModel )Source

Surface splines model of arbitrary order and knot settings.

It is a linear model.

Surface splines are direct product of a splines model in the x-direction with a splines model in the y-direction.

The number of parameters is ( xknotlength + xorder - 1 ) * ( yknotlength + yorder - 1 )

The SplinesModel has more information about order and knots.

Examples

nxk = 17
nyk = 11
xknots = numpy.arange(  nxk , dtype=float ) * 10      # make knots from 0 to 160
yknots = numpy.arange(  nyk , dtype=float ) * 10      # make knots from 0 to 100
csm = SurfaceSplinesModel( xknots, yknots, 2 )
print csm.getNumberOfParameters( )      # ( nxk + order - 1 )*( nyk + order - 1 )
216
# ... fitter etc. see Fitter

Category mathematics/Fitting

Attributes

  • knots : list of array_like
         positions of the knots in all dimensions
  • order : list of ints
         order of the splines in all dimensions
  • models : list of Model
         SplinesModels in all dimensions

Attributes from Model

     npchain, parameters, stdevs, xUnit, yUnit

Attributes from FixedModel

     npmax, fixed, parlist, mlist

Attributes from BaseModel

     npbase, ndim, priors, posIndex, nonZero, tiny, deltaP, parNames

SurfaceSplinesModel( knots, order=3, copy=None, fixed=None, **kwargs )

Splines on a given set of knots and a given order.

The number of parameters is ( length( knots ) + order - 1 )

Parameters

  • knots : list of array_like
         positions of the knots in all dimensions
  • order : int or list of ints
         order of the splines in all dimensions
  • copy : SurfaceSplinesModel
         model to be copied
  • fixed : dict
         If not None raise AttributeError.

Raises

  • AttributeError : When fixed is not None

copy( )

Copy method.

calcNp( knots, order )

basePartial( xdata, params, parlist=None )
Returns the partials at the input value.

The partials are the powers of x (input) from 0 to degree.

Parameters

  • xdata : array_like
         value at which to calculate the partials
  • params : array_like
         parameters to the model (ignored in LinearModels)
  • parlist : array_like
         not used in this model

baseName( )
Returns a string representation of the model.

baseParameterName( k )
Return the name of a parameter. Parameters
  • k : int
         the kth parameter.

baseParameterUnit( k )
Return the unit of a parameter. Parameters
  • k : int
         the kth parameter.
Methods inherited from LinearModel
Methods inherited from Model
Methods inherited from FixedModel
Methods inherited from BaseModel