Port remaining distributions to v4

[twiecki]

There are still various continuous distributions missing for v4 that need to get ported.
Here is an example of how to do this port for where aesara does not provide a RandomVariable (which is all of the currently missing ones): https://github.com/pymc-devs/pymc3/blob/v4/pymc3/distributions/continuous.py#L2648

Here is a list of the missing continuous ones:

• Flat Refactor Flat and HalfFlat distributions #4723
• HalfFlat Refactor Flat and HalfFlat distributions #4723
• TruncatedNormal Port Truncated Normal and Wald Distributions to V4 #4711
• Wald Port Truncated Normal and Wald Distributions to V4 #4711
• Kumaraswamy refactor kumaraswamy #4706
• Laplace refactor pareto and laplace #4691
• AsymmetricLaplace Refactored continuous distributions to v4 (AsymmetricLaplace, HalfStudentT, ExGaussian, Interpolated) #4746
• StudentT Refactor Student T Distribution #4694
• Pareto refactor pareto and laplace #4691
• ChiSquared Refactoring the ChiSquared distribution #4695
• HalfStudentT Refactored continuous distributions to v4 (AsymmetricLaplace, HalfStudentT, ExGaussian, Interpolated) #4746
• ExGaussian Refactored continuous distributions to v4 (AsymmetricLaplace, HalfStudentT, ExGaussian, Interpolated) #4746
• SkewNormal Refactor Rice and Skew Normal distribution #4705
• Rice Refactor Rice and Skew Normal distribution #4705
• LogitNormal Refactor LogitNormal #4703
• Interpolated Refactored continuous distributions to v4 (AsymmetricLaplace, HalfStudentT, ExGaussian, Interpolated) #4746
• Moyal refactor Moyal distribution #4704
• DensityDist Refactor DensityDist into v4 #5026

And the missing multivariate ones:

• MvStudentT Make MvStudentT distribution v4 compatible #4731
• DirichletMultinomial Port Dirichlet Multinomial to v4 #4758
• Wishart Refactored Wishart and MatrixNormal distribution #4777
• LKJCorr LKJCorr and LKJCholeskyCov refactor #5382
• LKJCholeskyCov LKJCorr and LKJCholeskyCov refactor #5382
• MatrixNormal Refactored Wishart and MatrixNormal distribution #4777
• KroneckerNormal [WIP] Porting kroneckernormal distribution to v4 #4774
• CAR CAR random variables #4596

Would be very important to add these to get an alpha out.

See @ricardoV94's comment below for a step-by-step guide on how to port a distribution.

[ricardoV94]

@ricardoV94 Thanks, edited the above. If you have time, perhaps you could write a short list of steps of what to do to port them. (Unless you want to take these on yourself :)).

This PR illustrates well with a single distribution refactoring I think: https://github.com/pymc-devs/pymc3/pull/4615/files. What is needed is:

1. Create a new RV op by inheriting from aesara RandomVariable, porting the code in the old random method to the rng_fn classmethod of the new RandomVariable.
2. Add the new (instance) of the RandomVariable to the rv_op field in the respective PyMC3 distribution.
3. Port any initialization logic in the old __init__ to the new dist classmethod
4. Refactor logp and logcdf to expect arguments in this order: value, arg1, arg2, ... argn
5. Re-enable tests in test_distributions.py
6. Create new test in test_distributions_random.py as seen here, and remove old BaseTestCase in that file.
7. Re-enable other tests that depended on this distribution in other test files.

Importantly, if there are multiple parametrizations, one will have to be set as the default in the dist classmethod in step 3. This will be the one that the RandomVariable is defined in terms of. If the random methods and logp/logcdf methods use different parametrizations, they will have to be converted to the ones that the RandomVariable is defined in terms of in step 3, and converted back to the logp and logcdf methods in step 4.

More details can be found here: #4518 (comment)

[farhanreynaldo]

I would like to help on this issue. Should we create a separate PR for each distribution?

[twiecki]

No you can do multiple in one go, just mark the ones you are working on.

…

On Wed, May 12, 2021, 13:28 Farhan Reynaldo ***@***.***> wrote: I would like to help on this issue. Should we create a separate PR for each distribution? — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#4686 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAFETGDPFKEEQJRE2ZEKOVDTNJQ4ZANCNFSM44X5P5LQ> .

[ricardoV94]

I would like to help on this issue. Should we create a separate PR for each distribution?

That might be too much. You can group a couple (or all) in a single PR.

I would suggest you start with the univariate distributions. The multivariate ones will probably be a bit more tricky.

[ricardoV94]

@brandonwillard what should we do with the flat and halfFlat distributions that don't have a random method? Should we create a RandomVariable whose rng_fn returns the same ValueError("Cannot sample from Flat distribution") as in V3?

[brandonwillard]

@brandonwillard what should we do with the flat and halfFlat distributions that don't have a random method? Should we create a RandomVariable whose rng_fn returns the same ValueError("Cannot sample from Flat distribution") as in V3?

Yeah, we can do that for now.