# ageron/handson-ml3

A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.

Repository: https://github.com/ageron/handson-ml3
Canonical: https://ross.abutalabs.com/products/handson-ml3
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Last push: 2026-05-19T22:55:16+00:00

## Health v2 (maintenance only)
Score: 70/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 83, release rhythm 35, longevity 100
- inputs: {"age_days": 1656, "days_push": 106, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 14010, forks 5266 (observed 2026-08-28T04:11:05.301443+00:00)

## What it is
A series of Jupyter notebooks teaching the fundamentals of Machine Learning and Deep Learning in Python, accompanying the 3rd edition of the O'Reilly book 'Hands-on Machine Learning with Scikit-Learn, Keras and TensorFlow'. It includes example code and exercise solutions runnable locally, in Docker, or on Colab/Kaggle/Binder.

## Use cases
- learn machine learning fundamentals with scikit-learn
- learn deep learning with tensorflow and keras
- find solutions to hands-on ML book exercises
- run ML tutorials in a Jupyter notebook environment
- get started with neural networks in python

## When to choose
- you are learning ML/DL from scratch or following the Hands-on ML book
- you want runnable, well-maintained example notebooks with exercise solutions
- you prefer browser-based environments like Colab or Kaggle

## When to avoid
- you need production-ready ML code or a reusable library
- you want a course with videos or graded assignments rather than notebooks
- you need coverage of ML frameworks other than Scikit-Learn, Keras, and TensorFlow

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, deep-learning, data-science
- domain: machine-learning, deep-learning, data-science, tutorials
- platform: python, cross-platform
- tags: jupyter-notebooks, scikit-learn, tensorflow, keras, education, book-companion

## Member repositories
- ageron/handson-ml3 (main) score 70

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:05.301443+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:12:52.724215+00:00, confidence not recorded.
  - readme: https://github.com/ageron/handson-ml3 (fetched 2026-08-28T04:11:05.301443+00:00, sha 6d92f5634505)
- Data as of 2026-08-30T08:39:29.467469+00:00.