Clustering small detected pockets

[aalexmmaldonado]

Warnings would occur when we try to cluster points into n_spheres groups with K-means, and one of the groups is empty. In these cases, we retry K-means with a different initialization algorithm. If that still fails, we use all the points as the spheres. This only happens with tiny pockets that are unlikely to be relevant, so this should not tangibly impact results.

[codecov-commenter]

Codecov Report

Attention: Patch coverage is 65.21739% with 8 lines in your changes missing coverage. Please review.

Project coverage is 77.31%. Comparing base (eede130) to head (1a0fd78).

Files with missing lines	Patch %	Lines
povme/pocket/detect.py	65.21%	8 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main       #9      +/-   ##
==========================================
- Coverage   77.80%   77.31%   -0.50%     
==========================================
  Files          15       15              
  Lines        1113     1133      +20     
  Branches      157      157              
==========================================
+ Hits          866      876      +10     
- Misses        182      192      +10     
  Partials       65       65              

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.