Skip to content

**zero-to-ml** is a project-based path to go from *no ML experience* to building real models.

Notifications You must be signed in to change notification settings

subhasmitasahoo/zero-to-ml

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 

Repository files navigation

zero-to-ml

Learn Machine Learning from absolute zero — no math background, no coding experience required.

🔰 Status: Days 1-2 Available | Python Basics & Math Foundations


🎯 What You'll Build

By the end of Week 1, you'll understand linear regression and build your first ML model from scratch.

Current Content:

  • Day 1: Python basics (variables, lists, loops, functions, NumPy)
  • Day 2: Math foundations (lines, slope, predictions, error)
  • Day 3+: Coming soon...

🚀 Quick Start

How to use this course:

Step 1: Fork & Clone (Recommended)

This allows you to save your work and submit solutions!

# 1. Fork this repository on GitHub (click "Fork" button)

# 2. Clone YOUR fork
git clone https://github.com/YOUR-USERNAME/zero-to-ml.git
cd zero-to-ml

# 3. Create your student folder
mkdir -p students/YOUR-NAME/week01

Step 2: Choose Your Environment

Method Best For Setup
VS Code Local Regular practice, offline work Instructions
GitHub Codespaces VS Code in browser Instructions
Google Colab Quick experiments Instructions

Local Setup

# Install Python 3.8+ from python.org
# Install VS Code from code.visualstudio.com

# In your cloned folder:
pip install numpy matplotlib jupyter ipykernel

# Open in VS Code
code .

# Open week01-linear-regression/01-python-primer.ipynb

GitHub Codespaces

  1. On YOUR forked repo, click CodeCodespacesCreate codespace
  2. Wait for VS Code to load in browser
  3. Open week01-linear-regression/01-python-primer.ipynb

Google Colab

  1. Go to colab.research.google.com
  2. FileOpen notebookGitHub → Enter YOUR fork URL
  3. ⚠️ Note: Save copies to Drive, then manually copy to your repo later

📖 Detailed setup instructions: SETUP_GUIDE.md


📝 How to Submit Your Work

Submission instructions have been consolidated into SUBMISSION_WORKFLOW.md. Please follow that document for step-by-step guidance, PR templates, naming conventions, and grading criteria.

Refer to that file before preparing your students/<your-name>/ folder and opening a Pull Request.


📚 Course Structure

week01-linear-regression/
├── 01-python-primer.ipynb      # Day 1: Python basics
└── 02-math-foundations.ipynb   # Day 2: Understanding lines & predictions

Learning Path:

  1. Start with Day 1 (even if you know some Python)
  2. Complete exercises in each notebook
  3. Move to Day 2
  4. Check Week 1 README for external resources

💡 Why This Course?

Designed for absolute beginners:

  • ✅ No math beyond high school algebra
  • ✅ Every concept explained visually
  • ✅ Real examples (study hours, sleep) not abstract math
  • ✅ Hands-on exercises in every section
  • ✅ Completely free and open source

What makes it different:

  • Starts at true zero
  • Visual-first approach
  • Builds confidence through small wins
  • Community-driven improvements

🤝 Contributing

Students: Submit Your Solutions

See SUBMISSION_WORKFLOW.md for the official submission workflow, examples, and PR templates. That document covers forking, folder structure, committing, and submitting Pull Requests.

File: SUBMISSION_WORKFLOW.md./SUBMISSION_WORKFLOW.md

Contributors: Improve the Course

Want to make this better? Here's how:

  • 📝 Add new exercises or examples
  • 🎨 Create visualizations or diagrams
  • 🌍 Translate content to other languages
  • 🐛 Fix typos or bugs
  • 💡 Improve explanations
  • 📹 Create video tutorials

Open an Issue to discuss ideas before making big changes!


💬 Get Help

No question is too basic — this is for beginners!


🗺️ Roadmap

Now Available:

  • ✅ Day 1: Python Primer
  • ✅ Day 2: Math Foundations

Coming Soon:

  • 🔜 Day 3-5: Building Linear Regression
  • 🔜 More coming soon...

📖 Documentation


📝 License

Open source for educational use. (License to be added)


Ready to start?Week 1, Day 1 🚀

Questions? Open an Issue | Want updates? Star the repo ⭐

About

**zero-to-ml** is a project-based path to go from *no ML experience* to building real models.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published