# datawhalechina/pumpkin-book

南瓜书：《机器学习》（西瓜书）公式详解

Repository: https://github.com/datawhalechina/pumpkin-book
Canonical: https://ross.abutalabs.com/products/pumpkin-book
License: NOASSERTION
License Family: other
Topics: machine-learning, pumpkin-book, book
Last push: 2026-04-22T20:35:48+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 78, release rhythm 8, longevity 100
- inputs: {"age_days": 2811, "days_push": 133, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 26005, forks 4797 (observed 2026-08-28T04:11:38.816119+00:00)

## What it is
The Pumpkin Book is an open-source companion guide that explains and derives the formulas skipped in Zhou Zhihua's classic machine-learning textbook (the 'Watermelon Book'). It is maintained by Datawhale and available as PDF releases, a printed edition, and video tutorials.

## Use cases
- understand formula derivations in the watermelon book
- learn machine learning math fundamentals
- supplement self-study of Zhou Zhihua's ML textbook
- find step-by-step derivations for ML equations
- study machine learning with undergraduate-level math

## When to choose
- you are reading the Watermelon Book and get stuck on a derivation
- you want a free, community-maintained ML math companion
- you prefer derivations explained with undergraduate-level math

## When to avoid
- you want a standalone ML textbook rather than a companion
- you need a rigorous graduate-level treatment of the math
- you cannot read Chinese

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, documentation
- domain: machine-learning, tutorials, education
- platform: cross-platform
- tags: open-textbook, math-derivations, chinese, companion-book, datawhale

## Member repositories
- datawhalechina/pumpkin-book (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:38.816119+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 2026-08-29T16:55:56.323227+00:00, confidence not recorded.
  - readme: https://github.com/datawhalechina/pumpkin-book (fetched 2026-08-28T04:11:38.816119+00:00, sha 706a688429a0)
- Data as of 2026-08-30T08:39:29.467469+00:00.