PyMCModelAdapter#

class causalpy.experiments.model_adapter.PyMCModelAdapter[source]#

Adapter for PyMCModel backends.

Parameters:: model (PyMCModel) – Fitted or unfitted PyMC backend model.

Methods

`PyMCModelAdapter.build`(X, y, *[, coords])	Merge priors and construct the PyMC graph without sampling.
`PyMCModelAdapter.coefficients`(*[, group])	Return coefficient draws from the requested group, canonically.
`PyMCModelAdapter.fit`(X, y, *[, coords])	Fit the PyMC model (build + prior phase + posterior phase).
`PyMCModelAdapter.predict`(X, *[, coords, ...])	Predict expected outcomes using the PyMC model.
`PyMCModelAdapter.print_coefficients`(labels)	Print model coefficients with labels.
`PyMCModelAdapter.require_idata`()	Return fitted inference-result DataTree or raise an explicit capability error.
`PyMCModelAdapter.sample_posterior`(**kwargs)	Sample the posterior phase on the built graph.
`PyMCModelAdapter.sample_prior_predictive`(...)	Sample the prior predictive phase on the built graph.
`PyMCModelAdapter.score`(X, y, *[, coords])	Score predictions from the PyMC model.

Attributes

`has_posterior`	Whether posterior draws are available.
`has_prior`	Whether prior draws are available.
`idata`	Return the model's DataTree when fitted.
`is_bayesian`	Whether the backend is Bayesian (PyMC or pymc-forecast).
`is_built`	Whether the PyMC graph has been constructed.
`is_ols`	Whether the backend is OLS/sklearn.
`kind`	Backend identifier.
`model`	The underlying PyMC model.
`supports_idata`	Whether the backend exposes an inference-result DataTree.
`supports_prior_predictive`	Whether the wrapped PyMC model exposes a prior predictive phase.

__init__(model)[source]#