Skip to content

Conversation

@glemaitre
Copy link
Member

closes #764

Solve several issues in NeighbourhoodCleaningRule:

  • apply the threshold_cleaning on the minority classes and not the full dataset
  • deprecate kind_sel since it does not make in regards to the proposed literature. We need to remove samples that are linked with the misclassification of samples using the NN rule for the minority class.
  • Make the code for this selection clearer.

@glemaitre glemaitre merged commit 6622afb into scikit-learn-contrib:master Jul 10, 2023
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.

[BUG] NCL - class should be cleaned if number of sampes is 0.5 * minority samples, not if 0.5* data.shape[0]

1 participant