mleveryday/100-days-of-ml-code

★ 22,250Jupyter NotebookAudience · vibe coderComplexity · 1/5LicenseSetup · easy

Mindmap

mindmap
  root((repo))
    What it does
      Daily ML lessons
      Runnable code
      Visual diagrams
    Topics covered
      Supervised learning
      Unsupervised learning
      Deep learning intro
    Learning format
      Jupyter Notebooks
      Python examples
      External resources
    Audience
      Chinese speakers
      ML beginners
      Self-paced learners

mindmap root((repo)) What it does Daily ML lessons Runnable code Visual diagrams Topics covered Supervised learning Unsupervised learning Deep learning intro Learning format Jupyter Notebooks Python examples External resources Audience Chinese speakers ML beginners Self-paced learners

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Follow a structured 100-day plan to learn machine learning fundamentals from scratch with daily coding exercises.

USE CASE 2

Run Python code examples in Jupyter Notebooks to understand supervised learning algorithms like regression and classification.

USE CASE 3

Study unsupervised learning techniques such as clustering with working code and visual explanations.

USE CASE 4

Use infographics and daily lessons as a reference guide while building your first machine learning projects.

Tech stack

PythonJupyter NotebookNumPyPandasScikit-learn

Getting it running

Difficulty · easy Time to first run · 5min

Use freely for any purpose including commercial, as long as you keep the copyright notice.

In plain English

100-Days-Of-ML-Code (Chinese edition) is a translated and adapted version of Avik-Jain's "100 Days of ML Code" challenge, presented as a study plan for learning machine learning over roughly a hundred days. The repository itself is not a piece of software you run, it is a day-by-day learning log written mostly in Simplified Chinese, with code in Jupyter notebooks, infographics, and links to external resources for each day's topic. The structure follows the typical machine-learning curriculum and is organised into two top-level sections. Under supervised learning, the days cover data preprocessing, simple and multiple linear regression, logistic regression and the math behind it, k-Nearest Neighbours, Support Vector Machines including the kernel trick, Naive Bayes, decision trees and random forests, with code implementations using Scikit-Learn. Under unsupervised learning the project covers K-means and hierarchical clustering. Interleaved with the algorithm days are study days that point to outside courses and videos: Coursera's deep learning specialization, Bloomberg's machine learning course, Yaser Abu-Mostafa's Caltech course CS156, and the 3Blue1Brown YouTube channel for linear algebra and calculus. Later days include deep-learning foundation notebooks using Python, TensorFlow and Keras, web-scraping practice with Beautiful Soup, and NumPy study from Jake VanderPlas's Python Data Science Handbook. You would use this repository if you read Chinese and want a structured, opinionated curriculum that mixes algorithm-by-algorithm coding exercises with curated outside videos and courses. Sample datasets are included.

Copy-paste prompts

Prompt 1

I'm starting to learn machine learning. Walk me through Day 1 of this 100-day challenge and explain what linear regression does with a simple example.

Prompt 2

Show me how to run the Jupyter Notebook for k-nearest neighbors from this repo and explain what the code is doing step by step.

Prompt 3

I want to understand the difference between supervised and unsupervised learning. Use the examples from this 100-days-of-ml-code repo to explain both.

Prompt 4

Help me set up Jupyter Notebook and run the first week of Python code examples from this machine learning learning challenge.

Prompt 5

Explain what a decision tree is using the infographic and code example from this 100-day ML learning resource.

Open on GitHub → Explain another repo

← mleveryday on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.