Repolode
Submit
MLEveryday

MLEveryday/100-Days-Of-ML-Code

A Chinese-language 100-day machine learning course with Python code, notes and exercises, covering Day 1 to 54 so far.

View on GitHub
Stars
22,234
Forks
5,455
Open issues
18
Last commit
15 days ago

What is it?

This repository is a Simplified Chinese learning path for machine learning, adapted from an English 100-day course. It is organized as daily lessons that move from data preprocessing and linear regression through classification, neural networks, decision trees, CNNs on MNIST and cat-vs-dog images, clustering, and NumPy, pandas and Matplotlib basics.

Each lesson pairs Python scripts in the Code folder with Markdown explanations and Jupyter notebooks generated from the same source. Scripts save their plots to an outputs folder. Setup covers Python 3.11 or 3.12, a requirements file for the basic course, and separate installation for deep learning dependencies. Days 55 to 100 are not yet written.

The project also includes a dataset guide, a FAQ on common pitfalls such as data leakage and model formats, a learning-path guide for beginners and experienced readers, and notes on updating examples that rely on older APIs.

Key features

  • 01Daily lessons from data preprocessing to CNNs and clustering
  • 02Python scripts paired with Markdown notes and Jupyter notebooks
  • 03Plots saved to an outputs folder when scripts run
  • 04Dataset preparation guide for MNIST and cat-dog images
  • 05Updated examples for modern scikit-learn and Keras 3

Use cases

  • Chinese-speaking beginners who want a structured first course in machine learning
  • Developers reviewing core supervised and unsupervised algorithms with runnable code
  • Instructors looking for classroom material with notebooks and exercises

Quick start

  1. 1

    Create a virtual environment

    python -m venv .venv
  2. 2

    Activate the virtual environment

    source .venv/bin/activate
  3. 3

    Install the requirements

    python -m pip install -r requirements.txt
  4. 4

    Run the Day 1 script

    python "Code/Day 1_Data_Preprocessing.py"

Things to know

  • Course content covers only Day 1 to 54; Day 55 to 100 are not yet written.
  • The lessons and notes are in Chinese.

Topics

#machine-learning#deep-learning#python#tutorial#jupyter-notebook#scikit-learn#keras#chinese#100-days-of-ml-code#chinese-simplified

FAQ

What is 100-Days-Of-ML-Code?
A Chinese-language 100-day machine learning course with Python code, notes and exercises, covering Day 1 to 54 so far. This repository is a Simplified Chinese learning path for machine learning, adapted from an English 100-day course. It is organized as daily lessons that move from data preprocessing and linear regression through classification, neural networks, decision trees, CNNs on MNIST and cat-vs-dog images, clustering, and NumPy, pandas and Matplotlib basics.
Is 100-Days-Of-ML-Code free to use? What license does it have?
100-Days-Of-ML-Code is open source under the MIT license. Check the license terms before using it in commercial products.
Is 100-Days-Of-ML-Code still maintained?
Actively maintained. The last commit to 100-Days-Of-ML-Code was on Oct 24, 2026.
What can I use 100-Days-Of-ML-Code for?
Chinese-speaking beginners who want a structured first course in machine learning Developers reviewing core supervised and unsupervised algorithms with runnable code Instructors looking for classroom material with notebooks and exercises
How do I install 100-Days-Of-ML-Code?
Create a virtual environment: python -m venv .venv Activate the virtual environment: source .venv/bin/activate Install the requirements: python -m pip install -r requirements.txt Run the Day 1 script: python "Code/Day 1_Data_Preprocessing.py"
Where can I get 100-Days-Of-ML-Code?
The source code and installation instructions are on GitHub: https://github.com/MLEveryday/100-Days-Of-ML-Code

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects