mcmc.rst   mcmc.rst 
skipping to change at line 21 skipping to change at line 21
- emcee_walkers: emcee v3.x multi-Walkers algorithms with M oves - emcee_walkers: emcee v3.x multi-Walkers algorithms with M oves
- dynesty: unsupported - dynesty: unsupported
- multinest: still experimental - multinest: still experimental
- pymc3: to be implemented - pymc3: to be implemented
mcmc_sampling: mcmc_sampling:
- galpak: 'Cauchy' [default] | 'Normal' | 'AdaptiveCauchy' - galpak: 'Cauchy' [default] | 'Normal' | 'AdaptiveCauchy'
- emcee_walkers: 'walkers' [default] | 'walkersCauchy' | 'D E' | 'Snooker' | 'Cauchy' | 'Normal' - emcee_walkers: 'walkers' [default] | 'walkersCauchy' | 'D E' | 'Snooker' | 'Cauchy' | 'Normal'
- multinest: None - multinest: None
- pymc3: to be implemented - pymc3: to be implemented
The proposal sampling methods The proposal sampling methods
.. figure:: images/GalPaK_MCMC.png .. figure:: images/GalPaK_MCMC.png
:scale: 60% :scale: 60%
:align: center :align: center
GalPaK3D uses an internal :class:`MCMC <galpak.MCMC>` class which extend th e galpak class. GalPaK3D uses an internal :class:`MCMC <galpak.MCMC>` class which extend th e galpak class.
This can be used to call its likelihood such as : :: This can be used to call its likelihood such as: ::
li = gk(params) li = gk(params)
using a :meth:`self.__call__() <MCMC.__call__>` method which returns the ln prob using a :meth:`self.__call__() <MCMC.__call__>` method which returns the ln prob
Here is a full example: :: Here is a full example: ::
import galpak import galpak
gk=galpak.GalPaK3D('data/input/GalPaK_cube_1101_from_paper.fits',model= galpak.DefaultModel()) gk=galpak.GalPaK3D('data/input/GalPaK_cube_1101_from_paper.fits',model= galpak.DefaultModel())
p=gk.model.Parameters() p=gk.model.Parameters()
params=p.from_ndarray([15,15,15,1e-16,5,60,90,1,100,10]) params=p.from_ndarray([15,15,15,1e-16,5,60,90,1,100,10])
 End of changes. 2 change blocks. 
1 lines changed or deleted 3 lines changed or added

This html diff was produced by rfcdiff 1.41. The latest version is available from http://tools.ietf.org/tools/rfcdiff/