#55th of 18 in Learning and cookbooks

ml-for-beginners

12-week, 26-lesson classic machine learning course using Scikit-learn

Stars
91.5k
License
MIT
Last commit
Sep 2026
Language
Jupyter Notebook
Stars, last 29 weeks+7,695
25 Mar 2026: 83,785 stars1 Apr 2026: 83,991 stars8 Apr 2026: 84,187 stars15 Apr 2026: 84,358 stars22 Apr 2026: 84,561 stars29 Apr 2026: 84,742 stars6 May 2026: 84,900 stars13 May 2026: 85,028 stars20 May 2026: 85,197 stars27 May 2026: 85,345 stars3 Jun 2026: 85,694 stars10 Jun 2026: 86,047 stars17 Jun 2026: 86,439 stars24 Jun 2026: 86,772 stars1 Jul 2026: 87,112 stars8 Jul 2026: 87,386 stars15 Jul 2026: 87,747 stars22 Jul 2026: 88,081 stars29 Jul 2026: 88,379 stars5 Aug 2026: 88,712 stars12 Aug 2026: 89,006 stars19 Aug 2026: 89,288 stars26 Aug 2026: 89,576 stars2 Sept 2026: 89,858 stars9 Sept 2026: 90,110 stars16 Sept 2026: 90,417 stars23 Sept 2026: 90,778 stars30 Sept 2026: 91,086 stars7 Oct 2026: 91,287 stars14 Oct 2026: 91,480 stars

83,785 on 25 Mar 202691,480 on 14 Oct 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

A Microsoft Cloud Advocates curriculum covering classic machine learning (regression, classification, clustering, NLP) with Scikit-learn, deliberately excluding deep learning. Each lesson has pre- and post-lecture quizzes, a written lesson, a solution, a challenge and an assignment, built around datasets from different world regions. Lessons are in Python, with R Markdown versions for many.

Who it is for: Beginners and teachers learning classic machine learning with Python

Strengths

  • Project-based lessons with solutions in /solution folders and quizzes for each lesson
  • Many lessons also provided in R as .rmd files
  • Translated into 50+ languages via automated GitHub Action
  • MIT license; can run in GitHub Codespaces without local Python setup

Weaknesses

  • Covers classic ML only; deep learning is in a separate curriculum
  • Not about LLMs or generative AI
  • Clone is large because of 50+ translations unless sparse checkout is used
  • Per-lesson dependencies must be installed manually

What it needs

  • no GPU
  • Needs Python, Scikit-learn, Jupyter, R (optional)

Also in Learning and cookbooks

See all 18
Also in Learning and cookbooks
RankProjectScore
1ai-engineering-from-scratchHands-on curriculum for building AI systems from math to agents69.1k starsMIT83 out of 100
2generative-ai-for-beginners21-lesson course on building generative AI apps in Python and TypeScript121.4k starsMIT81 out of 100
3llms-from-scratchCode for the book on building a GPT-style LLM in PyTorch106.5k starscustom license76 out of 100
#4hello-agentsChinese-language course on building LLM agents from scratch83.1k starscustom license76 out of 100
#6ai-agents-for-beginners18-lesson course on building AI agents with Microsoft Agent Framework77.2k starsMIT75 out of 100