# NannyML/The-Little-Book-of-ML-Metrics

The book every data scientist needs on their desk.

Repository: https://github.com/NannyML/The-Little-Book-of-ML-Metrics
Canonical: https://ross.abutalabs.com/products/the-little-book-of-ml-metrics
Homepage: https://www.nannyml.com/metrics
Language: Jupyter Notebook
License Family: other
Topics: book, classification-metrics, clustering-metrics, computer-vision-metrics, data-science, machine-learning, machine-learning-evaluation, machine-learning-metrics, nlp-metrics, python, ranking-metrics, regression-metrics
Last push: 2026-06-04T19:45:13+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 85, release rhythm 8, longevity 55
- inputs: {"age_days": 771, "days_push": 90, "days_rel": 688, "gap_med": null, "n_releases_24m": 1}
- flags: prerelease_only, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1003, forks 83 (observed 2026-09-03T02:15:06.853229+00:00)

## What it is
An open-source reference book covering machine learning evaluation metrics across regression, classification, clustering, ranking, computer vision, NLP, GenAI, bias and fairness, and data observability. It is maintained by the NannyML team as a quick-reference handbook for data scientists, with a free digital version and a paid printed edition.

## Use cases
- look up the definition of a regression metric like MAPE
- find the right classification metric for an imbalanced dataset
- learn evaluation metrics for ranking or recommender systems
- understand computer vision metrics like IoU or mAP
- compare NLP and GenAI evaluation metrics
- find metrics for bias and fairness auditing
- quick reference handbook for ML model evaluation

## When to choose
- you need a concise reference explaining ML evaluation metrics
- you want free, open-source educational material on metrics
- you are a data scientist or ML engineer evaluating models across domains
- you want to contribute to or review an open-source metrics book

## When to avoid
- you need a software library to compute metrics (use scikit-learn or NannyML instead)
- you need ML model monitoring tooling rather than metric documentation
- you need a formal textbook with exercises rather than a quick-reference handbook

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, data-science, documentation
- domain: machine-learning, data-science, tutorials, education
- platform: cross-platform
- tags: book, ml-metrics, evaluation-metrics, reference-handbook, open-source-book, jupyter-notebook

## Member repositories
- NannyML/The-Little-Book-of-ML-Metrics (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:06.853229+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 2026-08-30T07:13:56.531232+00:00, confidence not recorded.
  - readme: https://github.com/NannyML/The-Little-Book-of-ML-Metrics (fetched 2026-09-03T02:15:06.853229+00:00, sha 0fe2456de675)
  - homepage: https://www.nannyml.com/metrics (fetched 2026-08-29T13:13:53.801620+00:00, sha 4b88a0c60e8d)
  - site_page: https://docs.nannyml.com/cloud (fetched 2026-08-29T13:13:53.810778+00:00, sha f5378d5b2037)
  - site_page: https://www.nannyml.com/about (fetched 2026-08-29T13:13:53.814312+00:00, sha cd6e7a7ff0eb)
  - site_page: https://www.nannyml.com/pricing (fetched 2026-08-29T13:13:53.812625+00:00, sha 845caf4e2ae8)
- Data as of 2026-08-30T08:39:29.467469+00:00.