// the find
Visualize-ML/Book5_Essentials-of-Probability-and-Statistics
Book_5_《统计至简》 | 鸢尾花书:从加减乘除到机器学习;上架!
This is the companion code repo for a Chinese-language statistics/ML textbook (part of the '鸢尾花书' series), pairing each chapter's PDF with Jupyter notebooks that walk through the same concepts in Python. It's aimed at readers of the physical/ebook who want runnable code alongside the text, not a general-purpose library.
The chapter-by-chapter structure (Bk5_ChNN_*.ipynb next to the matching PDF) makes it trivial to jump straight to one topic, like conditional Gaussians or MCMC, without digging through unrelated code. Coverage is unusually wide for a single book: classical probability, discrete/continuous distributions, multivariate Gaussians, Bayesian inference, PCA, and regression all get their own notebooks. A handful of chapters ship small Streamlit apps for interactive visualization of distributions rather than static plots.
The README is pure marketing copy (discount links to buy the book) with zero setup instructions, no requirements.txt or environment file, so you're guessing at dependencies notebook by notebook. Everything is in Chinese, including file and directory names, which makes navigation and search painful if you don't read the language. There's no visible license, so it's unclear what you're allowed to do with the code beyond reading along. The repo also commits large PDFs and pickled dataframes directly into git history instead of using releases, which bloats every clone.