Navigation

Global	Documentation
Home	Manual
Readme	Glossary
Notes	Design
Examples	Classes
	Trouble
	Style

class BaseModel( object )	Source

BaseModel implements the common parts of simple Models.

A simple model is a function in x with parameters p : f(x:p). The variable x is an array of points in a space of one or more dimensions; p can have any length, including 0 i.e. the model has no parameters.

The result of the function for certain x and p is given by model.result( x, p )

The partial derivatives of f to p (df/dp) is given by model.partial( x, p ) Some fitters make use of the partials

The derivative of f to x (df/dx) is given by model.derivative( x, p )

BaseModel checks parameters for positivity and nonzero-ness, if such is indicated in the model itself.

BaseModel also implements the numerical calculation of the (partial) derivatives to be used when they are not given in the model definition itself.

Attributes

• npbase : int
       number of params in the base model

• ndim : int
       number of dimensions (parallel streams) of input. (default : 1)

• priors : list of Prior
       pertaining to each of the parameters of the model.
       If the list is shorter than the number of parameters, the last one is repeated.

• posIndex : list of int
       list of indices indication positive-definite parameters.

• nonZero : list of int
       list of parameters that need a warning when they are equal to zero.
       Warnings will only be issued once. Values are replaced by self.tiny

• tiny : float
       very small value, replacing zero valued when found on NonZero.
       (default : 1e-20)

• deltaP : array_like
       (list of) width(s) for numerical partial calculation. (default : 0.00001)

• parNames : list of str
       list of parameter names. (default : "parameter_k")

• Author : Do Kester

BaseModel( nparams=0, ndim=1, copy=None, posIndex=[], nonZero=[], **kwargs )

BaseModel Constructor.
Parameters

• nparams : int
       Number of parameters in the model (default: 0)
• ndim : int
       Number of dimensions of the input (default: 1)
• copy : BaseModel
       to be copied
• posIndex : list of int
       indices of parameters that need to be > 0
• nonZero : list of int
       indices of parameters that cannot be zero.
       they are replaced by self.tiny kwargs
       for internal use.

result( xdata, param )

Returns the result calculated at the xdatas.

Parameters

• xdata : array_like
       values at which to calculate the result
• param : array_like
       values for the parameters.

partial( xdata, param, parlist=None )

Returns the partial derivatives calculated at the inputs.

Parameters

• xdata : array_like
       values at which to calculate the result
• param : array_like
       values for the parameters.
• parlist : None or array_like
       indices of active parameters

checkParameter( param )

Return parameters corrected for positivity and Non-zero.

Parameters

• param : array_like
       values for the parameters.

checkPositive( param )

Check parameters for positivity. Silently correct.

Parameters

• params : array_like
       values for the parameters

checkZeroParameter( param )

Check parameters for Non-zero. Correct after one warning.

Parameters

• params : array_like
       values for the parameters

isDynamic( )

Whether the model implements Dynamic

isModifiable( )

Whether the model implements Modifiable

shortName( )

Return a short version the string representation: upto first non-letter.

derivative( xdata, param )

Returns the derivative of the model to xdata.

It is a numeric derivative as the analytic derivative is not present in the model.

Parameters

• xdata : array_like
       values at which to calculate the derivative
• param : array_like
       values for the parameters. (default: model.parameters)

setPrior( kpar, prior=None, **kwargs )

set the prior and/or limits for the indicated parameter.

The prior (by default UniformPrior) is appended when kpar is equal to np, the length of the existing list of priors. It replaces the prior when kpar < np and it generates an error when kpar > np

Parameters

• kpar : int
       parameter number.
• prior : Prior
       prior for the parameter
• kwargs : dict
       attributes to be passed to the prior

Raises

IndexError
     when kpar is larger than the length of priors list already present

hasPriors( isBound=True )

Return True when the model has priors for all its parameters.

Parameters

• isBound : bool
       Also check if the prior is bound.

getPrior( kpar )

Return the prior of the indicated parameter.

Parameters

• kpar : int
       parameter number.

basePrior( kpar )

Return the prior of the indicated parameter.

Parameters

• kpar : int
       parameter number.

getParameterName( kpar )

Return the name of the indicated parameter.

Parameters

• kpar : int
       parameter number.

baseParameterName( kpar )

Return the name of the indicated parameter.

Parameters

• kpar : int
       parameter number.

getParameterUnit( kpar )

Return the unit of the indicated parameter.

Parameters

• kpar : int
       parameter number.

baseParameterUnit( kpar )

Return the name of the indicated parameter.

Parameters

• kpar : int
       parameter number.

hasLimits( fitindex=None )

Return True if the model has limits set.