Skip to content

Multiclass Classification catalog does not contain EvaluateNonCalibrated #3323

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

Open
artidoro opened this issue Apr 12, 2019 · 0 comments
Open
Labels
bug Something isn't working P2 Priority of the issue for triage purpose: Needs to be fixed at some point.

Comments

@artidoro
Copy link
Contributor

The Multiclass Classification catalog has non calibrated trainers (SdcaNonCalibratedMulticlassTrainer) along with many calibrated trainers.

Currently there is only one Evaluate method, which assumes that the model is calibrated, and therefore produces LogLoss metrics. These metrics don't makes sense for the non calibrated trainers.

We should therefore add an evaluation method named EvaluateNonCalibrated for the non calibrated trainers.

@artidoro artidoro added the bug Something isn't working label Apr 12, 2019
@frank-dong-ms-zz frank-dong-ms-zz added the P2 Priority of the issue for triage purpose: Needs to be fixed at some point. label Jan 9, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working P2 Priority of the issue for triage purpose: Needs to be fixed at some point.
Projects
None yet
Development

No branches or pull requests

2 participants