Package gPy :: Module Samplers :: Class GibbsSampler

Class GibbsSampler

DO NOT USE: this is INCORRECT

A Gibbs sampler for Bayesian networks. Variables are instantiated in a topological order. Hence when no variables are instantiated, this is just forward sampling (no burn in is necessary).

When conditioning occurs, topological ordering is still used but conditioned variables are not updated.

Instance Methods

[hide private]

__init__(self, bn, burnin=1000)
x.__init__(...) initializes x; see x.__class__.__doc__ for signature

source code

sample(self)

source code

_next_sample(self)

source code

samples(self, num, skip=0)

source code

Inherited from object: __delattr__, __getattribute__, __hash__, __new__, __reduce__, __reduce_ex__, __repr__, __setattr__, __str__

Properties

[hide private]

Inherited from object: __class__

Method Details

[hide private]

init(self, bn, burnin=1000)
(Constructor)

source code

x.__init__(...) initializes x; see x.__class__.__doc__ for signature

Overrides: object.__init__: (inherited documentation)

Class GibbsSampler

__init__(self, bn, burnin=1000) (Constructor)

init(self, bn, burnin=1000)
(Constructor)