pastas.solver.EmceeSolve
========================

.. toctree::
   :hidden:

   /api/pastas/solver/EmceeSolve.log_probability
   /api/pastas/solver/EmceeSolve.log_likelihood
   /api/pastas/solver/EmceeSolve.log_prior
   /api/pastas/solver/EmceeSolve.set_parameter
   /api/pastas/solver/EmceeSolve.to_dict

.. py:class:: pastas.solver.EmceeSolve(objective_function=None, nwalkers: int = 20, backend=None, moves=None, parallel: bool = False, progress_bar: bool = True, **kwargs)



   
   Solver based on MCMC approach in emcee :cite:p:`foreman-mackey_emcee_2013`.

   :param objective_function: An objective function to be minimized. If not provided, the
                              GaussianLikelihood is used. See the pastas.objective_functions module for
                              more information.
   :type objective_function: func, optional
   :param nwalkers: Number of walkers to use. Default is 20.
   :type nwalkers: int, optional
   :param backend: One of the Backends from Emcee used to store MCMC results. See Emcee
                   for more information.
   :type backend: emcee.backend, optional
   :param moves: The moves argument determines how the next step for a walker is chosen in
                 the MCMC approach. One of the Moves classes from Emcee has to be provided.
                 See Emcee documentation for more information.
   :type moves: emcee.moves, optional
   :param parallel: Run the sampler in parallel or not.
   :type parallel: bool, optional
   :param progress_bar: Show the progress bar or not. Requires the `tqdm` package to be installed.
   :type progress_bar: bool, optional
   :param \*\*kwargs: All other keyword arguments are passed on to the BaseSolver class.
   :param optional: All other keyword arguments are passed on to the BaseSolver class.

   .. rubric:: Notes

   The EmceeSolve solver uses the emcee package to perform a Markov Chain Monte Carlo
   (MCMC) approach to find the optimal parameter values. The solver can be used as
   follows::

       solver = ps.EmceeSolve(
           nwalkers=20,
           progress_bar=True,
       )
       ml.solve(solver=solver)

   The arguments provided are mostly passed on to the `emcee.EnsembleSampler`
   and determine how that instance is created. Arguments you want to pass on to
   `run_mcmc` (and indirectly the `sample` method), can be passed on to
   `Model.solve`, like::

       ml.solve(solver=ps.EmceeSolve(), thin_by=2)

   .. rubric:: Examples

   Example usage::

       ml.solve(solver=ps.EmceeSolve(), steps=5000)

   To obtain the MCMC chains, use::

       ml.solver.sampler.get_chain(flat=True, discard=3000)

   .. rubric:: References

   https://emcee.readthedocs.io/en/stable/

   .. seealso:: :py:obj:`emcee.EnsembleSampler`, :py:obj:`emcee.moves`, :py:obj:`emcee.backend`, :py:obj:`pastas.objective_functions`















   ..
       !! processed by numpydoc !!
Methods
-------

.. autoapisummary::

   pastas.solver.EmceeSolve.log_probability
   pastas.solver.EmceeSolve.log_likelihood
   pastas.solver.EmceeSolve.log_prior
   pastas.solver.EmceeSolve.set_parameter
   pastas.solver.EmceeSolve.to_dict