Skip to content
Get packs

100-Days-Of-ML-Code

A 100-day learning log of machine learning topics, with notes, code links, and infographics.

GitHub Download source
Stars
52k
Forks
11.6k
Licence
MIT
Language
—
Last update
2.9 years ago
Type
Learning resource

No commits in over a year — check for forks or alternatives before adopting.

What it is

This is a public diary of one person's 100-day self-study of machine learning, posted as a GitHub repository. Each day covers a topic such as linear regression, logistic regression, SVMs, decision trees, or random forests, with short notes, links to code, and infographic images. It is useful as a guided path through beginner ML concepts and a set of links to further courses and videos.

  • Follow the day-by-day topics as a self-paced introductory ML curriculum
  • Open the linked Python code for logistic regression, KNN, SVM, decision trees, or random forests
  • Use the linked infographics as quick visual summaries of individual topics
  • Find links to the 3Blue1Brown linear algebra and calculus playlists and the Bloomberg ML lectures

Great for

  • Beginners who want a day-by-day sequence of basic machine learning topics
  • Learners who like studying alongside someone else's notes and links
  • People looking for pointers to scikit-learn examples for classic algorithms
  • Students who want references to the 3Blue1Brown and Caltech lecture series

Not ideal for

  • Readers who need complete, maintained tutorials: the README is a log, and the last push was 2023-12-29
  • Anyone expecting a software library or app to install: the README describes no installable package
  • Advanced practitioners looking for new material; the content covers introductory topics
Step-by-step guide: how to use 100-Days-Of-ML-CodeInstall, first run, examples, tips and FAQs

How to get it

  1. 1

    Clone and build from source

    Clone the repository

    git clone https://github.com/Avik-Jain/100-Days-Of-ML-Code
  2. 2

    Run it

    • Clone the repository or open it on GitHub.
    • Open the README and pick a day, starting with Day 1 (Data PreProcessing).
    • Read the linked markdown file in the Code folder for that day.
    • Open the infographic image or linked video for the same topic.
    • Download datasets from the datasets folder if you want to run examples.
  3. 3

    Get the most out of it

    • Work through the 3Blue1Brown linear algebra and calculus playlists linked in Days 26 to 32 for the math behind the methods.
    • Compare the scikit-learn code for SVM and random forests with the concepts in the day notes.
    • Use the linked Bloomberg and Caltech lectures for deeper theory after the introductory posts.
    • Keep a copy of the datasets folder locally so the code examples can run offline.

Downloads

Source code (.zip)master branch · straight from GitHub

Also on GitHub as mirrors or translations (not listed separately): MLEveryday/100-Days-Of-ML-Code

Strengths

  • Clear, chronological structure that is easy to follow
  • Links to well-known free resources such as 3Blue1Brown and Caltech CS 156
  • Released under the MIT license, so the material can be reused

Trade-offs

  • The log is a personal diary, so explanations are brief and not a full course
  • The README is truncated here and the repo's last push was in December 2023, so some links may be stale
  • Code is linked from separate markdown files rather than organized as a runnable project

How it compares

ProjectStarsTypeLevelUpdatedBest for
100-Days-Of-ML-Code (this)52kLearning resourcebeginner2.9 years agoBeginners who want a day-by-day sequence of basic machine learning topics
python-machine-learning-book12.7kLearning resourcebeginner4 months agoReaders who own the 1st edition and want to run its code
ML-For-Beginners91.9kLearning resourcebeginner5 days agoBeginners who want a structured, self-paced introduction to machine learning
homemade-machine-learning24.8kLearning resourcebeginner12 months agoStudents learning the math behind machine learning algorithms
MLAlgorithms11.2kLearning resourceintermediate1 months agoStudents who want to see how algorithms work step by step
stanford-tensorflow-tutorials10.4kLearning resourceintermediate5.9 years agoStudents following the original CS 20 course materials

Stats synced from GitHub. The assessment above was drafted with AI from the project's README on 2026-10-29 and may miss recent changes — check the README before relying on a command. MIT licence: free to use, modify and distribute, including commercially, as long as you keep the copyright notice.