Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Avoid double impurity calculation inside criterion.pyx in tree module #885

Open
wants to merge 11 commits into
base: main
Choose a base branch
from

Conversation

gdaiha
Copy link
Contributor

@gdaiha gdaiha commented May 10, 2024

Inspired by https://github.com/scikit-learn/scikit-learn/pull/18203/files# in Sklearn`s RandomForest, this PR aims to avoid double calculation of impurity inside criterion.pyx of tree module

kbattocchi and others added 10 commits May 10, 2024 14:33
Signed-off-by: Keith Battocchi <[email protected]>
Signed-off-by: Gabriel Daiha <[email protected]>
until dependencies are available.

Signed-off-by: Keith Battocchi <[email protected]>
Signed-off-by: Gabriel Daiha <[email protected]>
…y-why#879)

* Fixed normal inference results confidence interval unnecessary loop

Signed-off-by: gdaiha <[email protected]>
Signed-off-by: Gabriel Daiha <[email protected]>
Signed-off-by: Gabriel Daiha <[email protected]>
Increase sample size to reduce errors

Signed-off-by: kgao <[email protected]>
Signed-off-by: Gabriel Daiha <[email protected]>
@gdaiha
Copy link
Contributor Author

gdaiha commented May 10, 2024

Can't understand exactly why these tests are failing. The only thing I've done here was to move impurity_improvement after the calculation of best.impurity_left and best.impurity_right and changed impurity_improvement signature. Tests are claiming for errors in shape of outputs of grf and cf tests

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants