BayesicFitting

Model Fitting and Evidence Calculation

View project on GitHub



class SineSplineModel( LinearModel )Source

Sine of fixed frequency with splineslike amplitudes/phases.

     f( x:p ) = SM0 cos( 2 π ω x ) + SM1 sin( 2 π ω x )

Where SM0 and SM1 are splines models with defined knots and order.

It is a linear model with 2 * ( len(knots) + order - 1 ) papameters.

Examples

knots = [3.0*k for k in range( 11 )]
sine = SineSplineModel( 150, knots )        # fixed frequency of 150 Hz
print( sine.npbase )                        # number of parameters

26

Attributes

  • frequency : float
         (fixed) frequency of the sine
  • knots : array_like
         positions of the spline knots
  • order : int
         order of the spline. default: 3
  • cm : SplinesModel
         amplitude of the cosine
  • sm : SplinesModel
         amplitude of the sine

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

Alternate

The model

model = SineSplineModel( frequency, knots )
  • is equivalent to :

    cm = SplinesModel( knots ) sm = SplinesModel( knots ) fxd = {0:cm, 1:sm} model = SineAmpModel( frequency, fixed=fxd )

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

Sine model of a fixed frequency with a splineslike changing amplitude/phase.

Number of parameters is 2 * ( len(knots) + order - 1 ).

Parameters

  • frequency : float
         the frequency
  • copy : SineSplineModel
         model to be copied
  • fixed : dict
         If not None raise AttributeError.

Raises

AttributeError
     when fixed is not None

copy( )

Copy method.

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

Parameters

  • xdata : array_like
         values at which to calculate the partials
  • params : array_like
         parameters of the model (ignored in LinearModels)
  • parlist : array_like
         list of indices active parameters (or None for all)

baseDerivative( xdata, params )
Returns the derivative of f to x (df/dx) at the input value.

Parameters

  • xdata : array_like
         values at which to calculate the partials
  • params : array_like
         parameters of the model

getAmplitudes( xdata, params )
Return the amplitudes if cosine and sine, resp.

Parameters

  • xdata : array_like
         values at which to calculate the partials
  • params : array_like
         parameters of the model

baseName( )
Returns a string representation of the model.

baseParameterUnit( k )
Return the name 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