Implement RayleighRV

[twiecki]

Motivation for these changes

Implement RayleighRV, downstream of aesara-devs/aesara#1433

Implementation details

...

Checklist

• Explain motivation and implementation 👆
• Make sure that the pre-commit linting/style checks pass.
• Link relevant issues, preferably in nice commit messages.
• The commits correspond to relevant logical changes. Note that if they don't, we will rewrite/rebase/squash the git history before merging.
• Are the changes covered by tests and docstrings?
• Fill out the short summary sections 👇

Major / Breaking Changes

• ...

New features

• Implement RayleighRV. Downstream of Aesara PR Split numba tests into different files #1433 Implement RayleighRV aesara-devs/aesara#1433

Bugfixes

• ...

Documentation

• ...

Maintenance

• ...

[ricardoV94]

Why isn't it picking the more informative titles:

pytensor/bin/downstream_pr.sh

Line 46 in 4730d0c

gh pr create --repo pymc-devs/pytensor --label "aesara downstream" --title "🔄 From Aesara: $1: $title" --body "Downstreaming https://github.com/aesara-devs/aesara/pull/$1. PR port done by downstream_pr.sh script."

[twiecki]

Because there were conflicts and I finished it manually.

[ricardoV94]

Can you edit it? It's not useful for the release notes like this

[ricardoV94]

I am not sure we should implement it as a new Op. According to the web rayleigh is just a scaled chi2 with 2 df, so this should be the same:

def rayleigh(scale=1.0, *, size=None, **kwargs):
  return chi2(df=2, size=size, **kwargs) * as_tensor_variable(scale)

https://github.com/scipy/scipy/blob/dde50595862a4f9cede24b5d1c86935c30f1f88a/scipy/stats/_continuous_distns.py#L7669-L7787

The advantage being we don't need to implement new JAX or Numba Ops, nor implement logp in PyMC