[ENH, FIX] Allow scaling_factor in trunk_mixture_classification to be specified

[adam2392]

Changes proposed in this pull request:

• The covariance should be able to be specified, such that it is the identity matrix in trunk mixture.

Before submitting

• I've read and followed all steps in the Making a pull request
  section of the CONTRIBUTING docs.
• I've updated or added any relevant docstrings following the syntax described in the
  Writing docstrings section of the CONTRIBUTING docs.
• If this PR fixes a bug, I've added a test that will fail without my fix.
• If this PR adds a new feature, I've added tests that sufficiently cover my new functionality.

After submitting

• All GitHub Actions jobs for my pull request have passed.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 89.81%. Comparing base (48ca383) to head (0cf395d).
Report is 2 commits behind head on main.

❗ Current head 0cf395d differs from pull request most recent head 7844529. Consider uploading reports for the commit 7844529 to get more accurate results

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #234   +/-   ##
=======================================
  Coverage   89.81%   89.81%           
=======================================
  Files          54       54           
  Lines        5026     5029    +3     
=======================================
+ Hits         4514     4517    +3     
  Misses        512      512           

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

[PSSF23]

Why is 2/3 default? We don't have any simulations that use such scaling right now. Maybe in the future, but I would set the default to be identity.

[adam2392]

Why is 2/3 default? We don't have any simulations that use such scaling right now. Maybe in the future, but I would set the default to be identity.

cc: @sampan501 what was the reason again? Iforgot.

[sampan501]

Why is 2/3 default? We don't have any simulations that use such scaling right now. Maybe in the future, but I would set the default to be identity.

cc: @sampan501 what was the reason again? Iforgot.

I had done that before because when making the visualization, using 1 doesn't look bimodal. So, I stuck with the Marron and Wand default. For the sake of this though, I think we should just use 1

[sampan501]

Pending green CIs, lgtm