Parametrize Binomial and Categorical distributions via logit_p

[purna135]

Addressing #5005

Parametrized the Binomial and Categorical distributions via logit_p
Added test in test_distributions_random.py

[purna135]

Hi @ricardoV94 and @MarcoGorelli please have a look.

[codecov]

Codecov Report

Merging #5637 (4fba621) into main (e77e238) will increase coverage by 0.43%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##             main    #5637      +/-   ##
==========================================
+ Coverage   87.64%   88.07%   +0.43%     
==========================================
  Files          76       76              
  Lines       13722    13753      +31     
==========================================
+ Hits        12026    12113      +87     
+ Misses       1696     1640      -56     

Impacted Files	Coverage Δ
pymc/distributions/discrete.py	99.73% <100.00%> (+<0.01%)	⬆️
pymc/distributions/simulator.py	87.58% <0.00%> (+0.08%)	⬆️
pymc/sampling.py	88.14% <0.00%> (+2.17%)	⬆️
pymc/step_methods/hmc/quadpotential.py	80.54% <0.00%> (+9.97%)	⬆️

[ricardoV94]

Looks great. Left a small comment above about the tests

[purna135]

Thank you @ricardoV94, let me fix that

[ricardoV94]

Ah and we need a note in the release notes about the new feature!

[purna135]

Okay, I'm not sure what the proper message should be; could you please advise?

[ricardoV94]

Okay, I'm not sure what the proper message should be; could you please advise?

The easiest is to look at previous entries that are similar for inspiration. I spotted these two:

pymc/RELEASE-NOTES.md

Line 276 in 436f94a

- Add alternative parametrization to NegativeBinomial distribution in terms of n and p (see [#4126](https://github.com/pymc-devs/pymc/issues/4126))

pymc/RELEASE-NOTES.md

Line 597 in 436f94a

- Add `logit_p` keyword to `pm.Bernoulli`, so that users can specify the logit of the success probability. This is faster and more stable than using `p=tt.nnet.sigmoid(logit_p)`.

[purna135]

I think, I also forgot to add logit_p to doc string

[purna135]

Done now : )
Please have a look.

[ricardoV94]

Thanks for your help @purna135!