# GoogleCloudPlatform/ml-design-patterns

Source code accompanying O'Reilly book: Machine Learning Design Patterns

Repository: https://github.com/GoogleCloudPlatform/ml-design-patterns
Canonical: https://ross.abutalabs.com/products/ml-design-patterns
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Archived: true
Last push: 2021-04-28T23:11:45+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2360, "days_push": 1953, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2097, forks 594 (observed 2026-08-28T04:06:13.362067+00:00)

## What it is
Jupyter Notebook source code accompanying the O'Reilly book 'Machine Learning Design Patterns' by Lakshmanan, Robinson, and Munn. It demonstrates 30 ML design patterns covering data representation, model training, serving, reproducibility, and responsible AI.

## Use cases
- learn machine learning design patterns from a book
- find example notebooks for feature engineering patterns like embeddings and feature crosses
- study best practices for ML model serving and reproducibility
- learn responsible AI techniques like explainability and fairness
- get runnable code examples for hyperparameter tuning and transfer learning

## When to choose
- you are reading the Machine Learning Design Patterns book and want the accompanying code
- you want practical notebook examples of common ML engineering patterns
- you are teaching or learning MLOps and responsible AI concepts

## When to avoid
- you need a production-ready ML library or framework
- you want actively developed tooling rather than book companion code
- you need patterns beyond the 30 covered in the book

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, data-science, developer-tools
- domain: machine-learning, tutorials, data-science, education
- platform: python, cross-platform
- tags: design-patterns, jupyter-notebooks, oreilly-book, tensorflow, google-cloud, mlops

## Member repositories
- GoogleCloudPlatform/ml-design-patterns (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:13.362067+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 2026-08-30T02:54:32.442677+00:00, confidence not recorded.
  - readme: https://github.com/GoogleCloudPlatform/ml-design-patterns (fetched 2026-08-28T04:06:13.362067+00:00, sha bb1bd325a7f1)
- Data as of 2026-08-30T08:39:29.467469+00:00.