#1717th of 28 in Learning and cookbooks
100-days-of-ml-code
Chinese-language machine learning course with daily scikit-learn and Keras exercises
- Stars
- 22.2k
- License
- MIT
- Last commit
- Oct 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
Chinese adaptation of Avik-Jain's 100-Days-Of-ML-Code, with each lesson as a Python script plus generated Markdown and Jupyter notebook. Days 1 to 54 are written, covering preprocessing, regression, SVM, trees, neural networks, CNNs on MNIST and cats/dogs, and clustering. Days 55 to 100 are not yet written.
Who it is for: Chinese-speaking beginners learning classical ML and basic deep learning
Strengths
- Code updated for current scikit-learn and Keras 3, with Python 3.11/3.12 setup docs
- Each lesson ships as script, Markdown and notebook, generated by tools/sync_lessons.py
- Basic lessons need no GPU; deep learning dependencies are installed separately
- Includes an FAQ on data leakage and a dataset guide with field descriptions
Weaknesses
- Only Day 1 to 54 of 100 are written
- Chinese only; the README shows no English lessons
- Some theory days still rely on images and external video as supplements
- No releases published
What it needs
- GPU optional
- Needs Python 3.11/3.12, scikit-learn, Keras 3, Jupyter
Also in Learning and cookbooks
See all 28| Rank | Project | Score |
|---|---|---|
| 1 | ai-engineering-from-scratchHands-on AI engineering curriculum with 542 lessons across 20 phases | 86 out of 100 |
| 2 | generative-ai-for-beginners21-lesson course on building generative AI apps in Python and TypeScript | 81 out of 100 |
| 3 | hello-agentsChinese-language course on building LLM agents from scratch | 77 out of 100 |
| #4 | ai-agents-for-beginners18-lesson course on building AI agents with Microsoft Agent Framework | 77 out of 100 |
| #5 | llms-from-scratchCode for the book on building a GPT-style LLM in PyTorch | 76 out of 100 |