8000 Unexpected class_weight behavior in RidgeClassifier · Issue #1489 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]

Skip to content
Unexpected class_weight behavior in RidgeClassifier #1489
Closed
@amueller

Description

@amueller

While testing the class_weight parameter in several estimators to investigate #1411, I noticed that the parameter doesn't work as I would expect in RidgeClassifier either.
Maybe this is some misunderstanding on my part or some regularization issue, but if I have noisy labels, I would have expected to be be able to move the decision boundary.

This is not the case as illustrated in this notebook

Any input would be appreciated.

Metadata

Metadata

Assignees

No one assigned

    Labels

    Type

    No type

    Projects

    No projects

    Milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions

      0