Mailman 3 September 2024 - scikit-learn

Fwd: [SP] Standardized system for parameter management across Scientific Python libraries
by Adrin Sept. 15, 2024

Sept. 15, 2024

This sounds quite related to our parameter validation stuff. Thought I'd share. ---------- Forwarded message --------- From: Ewout ter Hoeven via Scientific Python < noreply(a)discuss.scientific-python.org> Date: Thu, Sep 12, 2024 at 9:57 AM Subject: Re: [SP] Standardized system for parameter management across Scientific Python libraries To: <adrin.jalali(a)gmail.com> EwoutH <https://discuss.scientific-python.org/u/ewouth> September 12 Yes, a library might be the right implementation solution here. I was thinking of a spec to get the requirements and capabilities right for a wide set of repos, since this is not technically difficult to build (it’s can probably be just a dataclass with a few helper methods), but it’s difficult to get the format right and get everybody aligned. ------------------------------ Visit Topic <https://discuss.scientific-python.org/t/standardized-system-for-parameter-m…> or reply to this email to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, click here <https://discuss.scientific-python.org/email/unsubscribe/da04c0dffea3cf72ed7…> .

1 0

[ANN] scikit-learn 1.5.2 is online!
by Guillaume Lemaître Sept. 11, 2024

Sept. 11, 2024

Hello everyone, We're happy to announce the 1.5.2 release ! It contains fixes for a few regressions introduced in 1.5. You can see the changelog here: https://scikit-learn.org/stable/whats_new/v1.5.html#version-1-5-2 You can upgrade with pip as usual: pip install -U scikit-learn The conda-forge builds can be installed using: conda install -c conda-forge scikit-learn Thanks to everyone who contributed to this release ! Guillaume, on behalf of the scikit-learn maintainers team.

1 0

ANN: model-diagnostics 1.2 released
by Christian Lorentzen Sept. 4, 2024

Sept. 4, 2024

Dear scikit-learn community I am very glad to announce the release of model-diagnostics <https://lorentzenchr.github.io/model-diagnostics/> 1.2 with its new |plot_marginal| and |compute_marginal|. Model-diagnostics helps you to assess calibration and performance of most supervised model - be it machine learning or statistical - for point predictions (like the mean, a quantile, or the probability for binary classification). The focus is on visualization and user-friendliness while well backed by statistical theory. The new |plot_marginal|, for instance, gives a great overview of the calibration as well as the model effect by a single feature, see 1.2 release notes <https://github.com/lorentzenchr/model-diagnostics/releases>: image Best, Christian

1 0