search

neurodata / scikit-learn

scikit-learn-tree fork: A fork that enables extensions of Python and Cython API for decision trees
https://scikit-learn.org
BSD 3-Clause "New" or "Revised" License
7 stars 6 forks source link

[SHOW PR] Submodulev2 #44

Open adam2392 opened 1 year ago

adam2392 commented 1 year ago

Reference Issues/PRs

Supersedes: #42

Incorporates the latest changes in scikit-learn upstream main, where missing-value support for trees was added.

What does this implement/fix? Explain your changes.

Any other comments?

github-actions[bot] commented 1 year ago

✔️ Linting Passed

All linting checks passed. Your pull request is in excellent shape! ☀️

Generated for commit: 6ec023b. Link to the linter CI: here

adam2392 commented 1 year ago

https://github.com/neurodata/scikit-learn/pull/44/commits/1994f15615c551aff26864321e46c568110022e6 introduces a regression where the missing values are not going to the node with the most nodes.

adam2392 commented 1 year ago

As of: https://github.com/neurodata/scikit-learn/pull/44/commits/9a614f4458583370a1df7de541c312fa291f0828

the categorical is a bit more complicated because the stuff in sklearn/tree/_splitter.pyx was not completed.