|
Walker = class Walker(builtins.object) |
| |
Walker(wid, problem, allpars, fitIndex, parent=-1,
start=0, copy=None)
Walker is member of the cloud of points used in NestedSampler.
Attributes
----------
id : int
identification number
parent : int
id of the parent (-1 for Adam/Eve)
start : int
iteration in which the walker is constructed
problem : Problem
the problem being addressed
logL : float
log Likelihood = log Prob( data | params )
allpars : array_like
list of parameters and hyperparameters
fitIndex : array_like
list of (super)parameters to be fitted.
parameters : array_like (read only)
parameters (of the model)
hypars : array_like (read only)
list of hyper parameters (of the error distribution)
Author Do Kester
|
| |
Constructor:
- Walker( wid, problem, allpars, fitIndex, parent=-1,
start=0, copy=None)
- Constructor.
Either errdis or copy is obligatory.
Parameters
----------
wid : int
id of the walker
problem : Problem
the problem being used. Parameters are copied from its model.
allpars : array_like
array of parameters and hyperparameters
fitIndex : None or array_like
indices of allpars to be fitted
None is all
parent : int
id of the parent (-1 for Adam/Eve)
start : int
iteration in which the walker is constructed
copy : Walker
the walker to be copied
Methods defined here:
- check( nhyp=0, nuisance=0)
- Perform some sanity checks.
- copy()
- Copy.
- toSample( logW)
- Return the contents of the Walker as a Sample.
|
|