scikit-learn

❄️ The Christmas release is here! ❄️

Introducing scikit-learn 1.6 with:

🟢 2 major features & 34 improvements
🔵 5 efficiency boosts & 21 enhancements
🟡 14 API changes
🔴 30 fixes
👥 160 amazing contributors

youtu.be/7wiHChpwJe8

20.12.2024 09:44 — 👍 63    🔁 23    💬 1    📌 1

GitHub - glemaitre/sklearn-compat Contribute to glemaitre/sklearn-compat development by creating an account on GitHub.

We are working on a small package to ease developer life: github.com/glemaitre/sk.... The idea is that recurrent work could be centralized in a single package. Once we have a minimal version, we will do a first release to support scikit-learn 1.2 to 1.6

28.11.2024 11:17 — 👍 15    🔁 1    💬 1    📌 0

Have you ever wanted to unpickle a @scikit-learn.bsky.social model you trained with version X while using a newer version X+1? If yes, why? When? How? I'd be interested to hear about your use cases to see if we can make it less painful

28.11.2024 15:04 — 👍 8    🔁 1    💬 2    📌 0

A high-level summary diagram taken from the slides linked below. It shows the interplay of two main components: a probabilistic model and decision maker or planner.

Probabilistic predictions of an underfitting polynomial classifier on a noisy XOR task and the corresponding under-confident calibration curve.

Probabilistic predictions of an overfitting polynomial classifier and the resulting overconfident calibration curve on the same noisy XOR problem.

Simulation study to show the relative lack of stability of hyperparameter tuning when using hard metrics such as Accuracy or soft yet not probabilistic metrics such as ROC AUC compared to a strictly proper scoring rule such as the log-loss.

I recently shared some of my reflections on how to use probabilistic classifiers for optimal decision-making under uncertainty at @pydataparis.bsky.social 2024.

Here is the recording of the presentation:

www.youtube.com/watch?v=-gYn...

27.11.2024 14:17 — 👍 50    🔁 19    💬 1    📌 1

Estimator creating `_more_tags` and inheriting from `BaseEstimator` will not warn about old tag infrastructure · Issue #30257 · scikit-learn/scikit-learn While making the code of skrub compatible with scikit-learn 1.6, I found that the following is really surprising: # %% import numpy as np from sklearn.base import BaseEstimator, RegressorMixin clas...

3rd-party library maintainers might find it cumbersome to handle the transition to the new estimator tags while keeping backward compatibility with older scikit-learn versions. We will devise a way to smooth out the transition before releasing 1.6.0 final:

github.com/scikit-learn...

22.11.2024 17:12 — 👍 10    🔁 5    💬 2    📌 0

Version 1.6 Legend for changelogs something big that you couldn’t do before., something that you couldn’t do before., an existing feature now may not require as much computation or memory., a miscellaneous min...

Please help us test the first release candidate for scikit-learn 1.6: pip install scikit-learn==1.6.0rc1

Changelog: scikit-learn.org/1.6/whats_ne...

In particular, if you maintain a project with a dependency on
scikit-learn, please let us know about any regression.

22.11.2024 14:49 — 👍 38    🔁 18    💬 2    📌 2