Make basic INLA interface and simple marginalisation routine

[Michal-Novomestsky]

Addresses #532 and #344.

Relies on pymc-devs/pytensor#1582 and pymc-devs/pymc#7895.

Currently uses a closed-form solution for a specific case (nested normals) while awaiting pymc-devs/pytensor#1550

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[Michal-Novomestsky]

@maresb, @zaxtax suggested that I reach out to you about the Docs not being built. Do you have any ideas why it's failing? Thanks!

[Michal-Novomestsky]

pre-commit.ci autofix

[maresb]

@maresb, @zaxtax suggested that I reach out to you about the Docs not being built. Do you have any ideas why it's failing? Thanks!

Hey @Michal-Novomestsky, thanks for all your work here! I recently returned from travel so I'm just now catching up on my backlog.

I assume you're asking why the Read the Docs workflow is failing? Opening the CI logs and expanding the line with the error displays the following stack trace:

File "/home/docs/checkouts/readthedocs.org/user_builds/pymc-extras/envs/533/lib/python3.11/site-packages/pymc_extras/model/marginal/distributions.py", line 11, in
from pymc.distributions.multivariate import _precision_mv_normal_logp
ImportError: cannot import name '_precision_mv_normal_logp' from 'pymc.distributions.multivariate' (/home/docs/checkouts/readthedocs.org/user_builds/pymc-extras/envs/533/lib/python3.11/site-packages/pymc/distributions/multivariate.py)

Is this helpful?

[Michal-Novomestsky]

I assume you're asking why the Read the Docs workflow is failing? Opening the CI logs and expanding the line with the error displays the following stack trace:

File "/home/docs/checkouts/readthedocs.org/user_builds/pymc-extras/envs/533/lib/python3.11/site-packages/pymc_extras/model/marginal/distributions.py", line 11, in
from pymc.distributions.multivariate import _precision_mv_normal_logp
ImportError: cannot import name '_precision_mv_normal_logp' from 'pymc.distributions.multivariate' (/home/docs/checkouts/readthedocs.org/user_builds/pymc-extras/envs/533/lib/python3.11/site-packages/pymc/distributions/multivariate.py)

Is this helpful?

@maresb Ah yep that makes sense - this PR is dependent on two other PRs in PyMC and Pytensor respectively, so it (and the rest of the unittests) are failing because those haven't been merged yet. Thanks for the help!

[Michal-Novomestsky]

pre-commit.ci autofix

[Michal-Novomestsky]

For some reason, /tests/distributions/test_discrete.py::TestGeneralizedPoisson::TestRandomVariable::test_random_lam_expected_moments[2.5] is failing even though it passes locally (local is up to date with remote). It's a test case completely unrelated to this merge (TestGeneralizedPoisson), would greatly appreciate any pointers @ricardoV94 @jessegrabowski @zaxtax .

[Michal-Novomestsky]

Ok, just three test cases are failing, which @zaxtax agrees shouldn't be related to the PR itself. Once these are sorted we can merge @ricardoV94 @jessegrabowski