joelgrus/data-science-from-scratch resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

9705 stars · 4716 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Companion code repository for the book 'Data Science from Scratch' (2nd edition) by Joel Grus, containing pure-Python implementations of data science fundamentals. It includes a 'scratch' package covering linear algebra, statistics, probability, machine learning, neural networks, and more.

Use cases

• learn data science fundamentals in pure python
• implement machine learning algorithms from scratch
• understand linear algebra and statistics for data science
• study gradient descent and neural network basics
• follow along with the Data Science from Scratch book
• teach introductory data science with simple python examples

When to choose

• you are learning data science concepts and want minimal-dependency python code
• you want to see how algorithms like k-NN, regression, and neural nets work internally
• you are reading the book and want runnable examples

When to avoid

• you need production-grade, performant machine learning libraries
• you want actively developed tooling rather than book companion code
• you need scalable implementations for large datasets

Facets

learning-resource · maturity maintenance

data-science machine-learning math data-visualization data-science machine-learning education tutorials python cross-platform book-code educational from-scratch-implementations statistics linear-algebra deep-learning-basics

Member repositories

For agents

markdown · JSON · MCP: product_card(name="joelgrus/data-science-from-scratch")