Default to pm.Data(mutable=False), deprecate MLDA and bump to v4.1.0

[michaelosthege]

What is this PR about?
When attempting to bump the version to 4.1.0, I ran into a change f the pm.Data(mutable=...) default setting that we had already announced to happen in 4.1.0.

Consequently, I made that change and adapted tests accordingly.

I also sneaked in a DeprecationWarning about moving MLDA over to pymc-experimental (#5942).

Checklist

• Explain important implementation details 👆
• Make sure that the pre-commit linting/style checks pass.
• Link relevant issues (preferably in nice commit messages)
• Are the changes covered by tests and docstrings?
• Fill out the short summary sections 👇

Major / Breaking Changes

• pm.Data() now defaults to mutable=False (use pm.ConstantData/pm.MutableData or pass mutable=True/False to avoid a warning).

Bugfixes / New features

None

Docs / Maintenance

• Added a DeprecationWarning about moving MLDA to pymc-experimental.
• __version__ was incremented to "4.1.0"

[codecov]

Codecov Report

Merging #5944 (65f999e) into main (f617180) will increase coverage by 0.01%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##             main    #5944      +/-   ##
==========================================
+ Coverage   89.52%   89.54%   +0.01%     
==========================================
  Files          73       73              
  Lines       13271    13271              
==========================================
+ Hits        11881    11883       +2     
+ Misses       1390     1388       -2     

Impacted Files	Coverage Δ
pymc/__init__.py	100.00% <100.00%> (ø)
pymc/data.py	81.48% <100.00%> (-0.16%)	⬇️
pymc/model.py	88.20% <100.00%> (+0.14%)	⬆️
pymc/step_methods/mlda.py	96.38% <100.00%> (+0.01%)	⬆️
pymc/step_methods/hmc/base_hmc.py	90.55% <0.00%> (+0.78%)	⬆️

[twiecki]

Can you do the bump in a separate PR?

[michaelosthege]

Can you do the bump in a separate PR?

Why that? The other changes should come before 4.1.0.

Also, I'm confident the CI will go green this time (I tried that one test locally..)
Just had to push again, because I forgot to fixup a commit.

[michaelosthege]

I shpuld clarify: The 4.1.0 bump depends on some of these changes. I tried just bumping first, but the tests went red..

[michaelosthege]

Thomas wanted to get another PR merged beforehand - that's done so I'm merging this one now.