8000 Use sample_weight when validating LogisticRegressionCV · Issue #25906 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]

Skip to content
Use sample_weight when validating LogisticRegressionCV #25906
Closed
@luiscastro193

Description

@luiscastro193

Metadata Routing #24027 will add much needed support for taking into account sample_weight when cross-validating. However, the current implementation of LogisticRegressionCV doesn't seem to be taking advantage of this:

scores.append(scoring(log_reg, X_test, y_test))

Therefore, the scores used for choosing the correct hyperparameter will still be misleading even when the tools for solving this become available.

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions

      0