M3GNetSite describer; DIRECT samples smallest cells possible

[JiQi535]

Summary

Addition of functionalities for DIRECT sampling and describer. All are covered by tests.

Major changes:

• Add M3GNetSite as a describer.

• Add "smallest" and "random" as selection_criteria for the stratified sampling step of DIRECT sampling pipeline. The default selection_criteria is still "center", i.e., select structures w.r.t. their distances to the respective centroid.

• Allow DIRECT sampling to decide # of clusters based on desired cluster radius.

• Add tests to all above functionalities and previous missing ones.

• Corrections for typos for DIRECT sampling codes and notebooks.

• Additional docs all over maml to pass ruff and black.

Todos

• The M3GNet structural and atomic featurizer are all based on tensorflow version of M3GNet. MatGL models are to be added.
• A notebook of DIRECT sampling with atom features.

Checklist

• [x] Google format doc strings added. Check with ruff.
• [x] Type annotations included. Check with mypy.
• [x] Tests added for new features/fixes.
• [ ] If applicable, new classes/functions/modules have duecredit @due.dcite decorators to reference relevant papers by DOI (example)

[codecov[bot]]

Codecov Report

Attention: Patch coverage is 90.90909% with 8 lines in your changes are missing coverage. Please review.

Project coverage is 67.58%. Comparing base (eb4a8ea) to head (1463eee).

Files	Patch %	Lines
maml/apps/pes/_mtp.py	50.00%	3 Missing :warning:
maml/describers/_m3gnet.py	92.68%	3 Missing :warning:
maml/apps/gbe/describer.py	50.00%	2 Missing :warning:

Additional details and impacted files

@@            Coverage Diff             @@
##           master     #596      +/-   ##
==========================================
+ Coverage   66.92%   67.58%   +0.66%     
==========================================
  Files          68       68              
  Lines        5209     5263      +54     
==========================================
+ Hits         3486     3557      +71     
+ Misses       1723     1706      -17     

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.