Update metropolis.py

[elliottperryman]

allow for covariance matrix not only variance

What is this PR about?
...

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

• ...

New features

• ...

Bugfixes

• when using the differential evolution metropolis methods the parameters say that they accept a 2D covariance matrix but fail when this is given. This is because the initialization step does not check for a 2D covariance function as other classes do and go straight to normal. Then the step gives a "scale < 0" error. I fix this.

Documentation

• ...

Maintenance

• ...

---

📚 Documentation preview 📚: https://pymc--6825.org.readthedocs.build/en/6825/

[welcome]

💖 Thanks for opening this pull request! 💖 The PyMC community really appreciates your time and effort to contribute to the project. Please make sure you have read our Contributing Guidelines and filled in our pull request template to the best of your ability.

[michaelosthege]

ok, for consistency we can do this.

However, be aware that covariance in the jitter is unlikely to have any impact on sampling.

[codecov]

Codecov Report

Merging #6825 (2b00b55) into main (13e7c88) will decrease coverage by 3.27%.
The diff coverage is 66.66%.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #6825      +/-   ##
==========================================
- Coverage   92.02%   88.75%   -3.27%     
==========================================
  Files          95       95              
  Lines       16262    16275      +13     
==========================================
- Hits        14965    14445     -520     
- Misses       1297     1830     +533     

Impacted Files	Coverage Δ
pymc/step_methods/metropolis.py	65.06% <25.00%> (-21.54%)	⬇️
pymc/distributions/distribution.py	96.08% <100.00%> (-0.98%)	⬇️
pymc/model.py	91.01% <100.00%> (+0.05%)	⬆️

... and 16 files with indirect coverage changes

[ricardoV94]

I marked this as a draft due to failing tests