[ENH] Continuing CMI work

[adam2392]

Towards #48

Changes proposed in this pull request:

• implements KSG estimator using scipy KDTree
• implements KSG estimator using an unsupervised tree, which is validated on a Jupyter notebook

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.

[adam2392]

@PSSF23 this implements the conditional sampling strategy that can enable both i) bootstrapping and ii) permutation of sample indices conditioned on a conditional array that we want to use to only permute "nearest-neighbors"

[PSSF23]

LGTM

[codecov]

Codecov Report

Patch coverage: 45.45% and project coverage change: -10.78% ⚠️

Comparison is base (52bca43) 86.81% compared to head (b4c029b) 76.04%.
Report is 4 commits behind head on main.

❗ Current head b4c029b differs from pull request most recent head 5e50021. Consider uploading reports for the commit 5e50021 to get more accurate results

Additional details and impacted files

@@             Coverage Diff             @@
##             main      #94       +/-   ##
===========================================
- Coverage   86.81%   76.04%   -10.78%     
===========================================
  Files          24       32        +8     
  Lines        1919     2442      +523     
===========================================
+ Hits         1666     1857      +191     
- Misses        253      585      +332     

Files Changed	Coverage Δ
sktree/ensemble/_supervised_forest.py	100.00% <ø> (ø)
sktree/experimental/simulate.py	41.25% <8.33%> (-46.88%)	⬇️
sktree/experimental/mutual_info.py	33.33% <10.52%> (+12.82%)	⬆️
sktree/experimental/forest.py	15.38% <15.38%> (ø)
sktree/experimental/ksg.py	17.12% <17.12%> (ø)
sktree/neighbors.py	58.58% <45.90%> (-27.63%)	⬇️
sktree/tree/_classes.py	73.09% <50.00%> (-3.29%)	⬇️
sktree/ensemble/_honest_forest.py	91.35% <54.54%> (-5.79%)	⬇️
sktree/experimental/tests/test_ksg.py	60.00% <60.00%> (ø)
sktree/experimental/monte_carlo.py	69.11% <69.11%> (ø)
... and 10 more

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

[adam2392]

I want to add a bunch of unit tests after I ensure that the supervised/unsupervised forests estimate mutual information correctly.

Rn either there's an issue w/ the simulation, or there's an issue w/ the code.