Phase 0 of 7 · 6 topics

Your toolkit

Get fast with the tools you will use every day. This phase is short. Do it in the same two weeks as the start of Phase 1.

Tools are like a carpenter's workshop. You cannot learn furniture design while fighting with the saw. NumPy is your saw: practise until it feels natural.

0 of 6 done

Core resources for this phase

Guide
NumPy: the absolute basics for beginners Free

The official guide. Short and clear. Type every example yourself.
Book
From Python to NumPy (Nicolas Rougier) Free

Teaches you to think in whole arrays instead of loops. This is the key NumPy skill.

Topics, in order

Mark "Meet machine learning: the big picture" as done
0.1 Meet machine learning: the big picture
- Watch
  
  Neural Networks, Ch 1–2: what a neural network is, and how it learns
  
  3Blue1Brown
  
  Worth it: Beautiful moving pictures of a model adjusting its weights to lower the loss. It makes the learning loop feel real in a way text can't.
- Watch
  
  A Gentle Introduction to Machine Learning
  
  StatQuest (Josh Starmer)
- Interactive
  
  A Visual Introduction to Machine Learning
  
  R2D3 · an animated story you scroll through
- Read
  
  Machine Learning Crash Course: introduction and linear regression
  
  Google, free
Mark "NumPy arrays, shapes and indexing" as done
0.2 NumPy arrays, shapes and indexing
- Watch
  
  Complete Python NumPy Tutorial
  
  Keith Galli
- Read
  
  A Visual Intro to NumPy and Data Representation
  
  Jay Alammar · illustrated, free
  
  Worth it: Colourful pictures of arrays, slicing and reshaping, and of how tables, images and text become arrays. The best picture-book companion to this topic.
- Read
  
  NumPy: the absolute basics for beginners
  
  numpy.org
- Read
  
  Indexing on ndarrays
  
  numpy.org
Mark "Broadcasting and vectorisation" as done
0.3 Broadcasting and vectorisation
- Read
  
  Broadcasting
  
  numpy.org · with diagrams
- Read
  
  From Python to NumPy: the vectorisation chapters
  
  Nicolas Rougier · free book
- Code
  
  100 NumPy exercises
  
  Nicolas Rougier · GitHub
Mark "Plotting results with Matplotlib" as done
0.4 Plotting results with Matplotlib
- Watch
  
  Matplotlib Tutorial (Part 1)
  
  Corey Schafer
- Read
  
  Quick start guide
  
  matplotlib.org
Mark "Git and GitHub for your projects" as done
0.5 Git and GitHub for your projects
- Watch
  
  Version Control (Git)
  
  The Missing Semester (MIT)
- Interactive
  
  Learn Git Branching
  
  interactive, in the browser
  
  Worth it: You type real Git commands and watch the branch picture redraw itself. The fastest way to make branches and merges click.
- Read
  
  Pro Git, Chapters 1–3
  
  Scott Chacon · free book
Mark "Testing numerical code (np.allclose, pytest)" as done
0.6 Testing numerical code (np.allclose, pytest)
- Read
  
  Get Started
  
  pytest docs
- Read
  
  numpy.testing.assert_allclose
  
  numpy.org
- Read
  
  Floating Point Arithmetic: Issues and Limitations
  
  Python docs

Go deeper (optional)

Course
The Missing Semester (MIT) Free

Shell, Git and developer tools. The Git lecture is the important one.
Tutorial
PyTorch: Learn the Basics Free

Keep this for the start of Phase 3.

Your toolkit

Core resources for this phase

Topics, in order

0.1 Meet machine learning: the big picture

0.2 NumPy arrays, shapes and indexing

0.3 Broadcasting and vectorisation

0.4 Plotting results with Matplotlib

0.5 Git and GitHub for your projects

0.6 Testing numerical code (np.allclose, pytest)

Go deeper (optional)