Forward model argument to add_fit_to_inference_data in find_MAP (#543)

* Forward model argument to  add_fit_to_inference_data in find_MAP

* Add 2d test for nonstandard dims

Update and Refactor `find_MAP` and `fit_laplace` (#531)

* Move laplace and find_map to submodule

* Split idata utilities into `idata.py`

* Refactor find_MAP

* Refactor fit_laplace

* Update better-optimize version pin

* Handle labeling of non-scalar RVs without dims

* Add unconstrained posterior draws/points to unconstrained_posterior

Forecast exogenous vars bug fix (#510)

* fixed bug in statespace forecast method when exogenous variables are present.

* updated solution to handle input shapes correctly

* simplified fix, renamed mu and cov for transparancy and added a check for the graph replacements

* Refactor model builder logic out of `forecast` method

* made slight change with _build_forecast_model and created a test case

* made change to test_build_forecast_model() to ensure data is replaced with pm.set_data method

* added additional checks to test_build_forecast_model

* added mock_sample_setup_and_teardown to statespace tests

---------

Co-authored-by: jessegrabowski <jessegrabowski@gmail.com>

Add deserialize module (#489)

Remove `mode` argument passed from Statespace.build_statespace_graph …

…to scan (#482)

* Remove `mode` argument from everywhere

* Add deprecation warning to mode argument of `build_statespace_graph`

Add mode argument to statespace constructors

* Rename tests -> test

* Remove _set_default_mode

Increment version (#460)

Bump version (#433)

Bump version (#423)

Release version 0.2.2 (#418)

Adapt the GHA PyPI publishing workflow for trusted publishing (#409)

All the changes here are in line with those recently made to the PyMC workflow