finds.dev

jakevdp/sklearn_pycon2015

Materials for my Pycon 2015 scikit-learn tutorial.

View on GitHub

★ 889Jupyter NotebookBSD-3-Clauseupdated Oct 2020

// the take

A set of Jupyter notebooks from Jake VanderPlas's 2015 PyCon scikit-learn tutorial, covering classification, regression, PCA, clustering, GMM, and validation basics. Useful for someone who wants a slow, guided first pass through core scikit-learn concepts, not for anyone already writing ML code.

The notebooks are organized as a genuine progression (preliminaries → intro → specific algorithms → validation) rather than a grab-bag of examples, so you can follow it top to bottom. VanderPlas is a clear technical writer and the fig_code helpers generate decent visualizations for each concept, which is more effort than most tutorial repos put in.

The README itself says to go use github.com/jakevdp/sklearn_tutorial instead — this repo is explicitly superseded by its own author. It targets Python 2.6-2.7/3.3-3.4 and scikit-learn 0.14, both long dead, and the 889 stars are a relic of 2015 popularity, not current relevance. The 2020 push is almost certainly a README edit, not a content refresh, so the API calls in the notebooks will throw deprecation errors or outright fail on any modern sklearn install.

We read the README, the directory tree and a key source file in September 2026. Nobody pays to be listed. How we judge →

// at a glance

Stars
889
Forks
572
Language
Jupyter Notebook
License
BSD-3-Clause
Last commit
2 Oct 2020

// nearby

If sklearn_pycon2015 isn't quite it.

All repos →