Heads-Up! Lots of great resources below.

This is the Boulder Data Science repo for all of the best resources we find across the web. From learning the basics to hacking on projects and getting jobs, it's all here.

Machine Learning in Python

• scikit-learn documentation: The primary machine learning package for Python. From preprocessing to models to evaluation, it's all here.

Neural Networks / Deep Learning

• Neural Networks and Deep Learning: An online book that teaches you neural networks in 6 chapters, from simple perceptrons to deep learning.
• Google / Udacity Deep Learning Course
• Deep Learning, NLP, and Representations
• OpenAI

Data Science for Good

• DataKind
• Open Data Science Initiative

Data Visualization

• Seaborn: An easy and beautiful Python visualization tool. Builds off of matplotlib.
• matplotlib: The main data visualization library in Python.
• A Neural Network Playground: One of the best visualization tools for how neural networks work, completely in-browser.
• ConvNetJS: Deep Learning in your browser.
• Setosa.io

Competitions

• Kaggle: The self-proclaimed "Home of Data Science".

Auto-ML

• auto-sklearn: Automated machine learning toolkit for Python.
• The Automated Statistician

Learning the Foundations

Resources for Learning and Help

• Stack Overflow
• Cross Validated

Statistics

• Introduction to Statistical Learning: A highly-praised introduction to everything you need to know about statistics and machine learning.
• Elements of Statistical Learning: A more math-heavy version of "Intro to Statistical Learning".

Maths

• Singular Value Decomposition

Programming in Python

• Learn Python the Hard Way: Just learning Python? There's a reason this online tutorial is so popular.
• Anaconda: All the data science packages you need, wrapped up in a nice single bundle.
• Jupyter Notebooks

GitHub

• The Git Book: The quintessential git book.
• Try Git: Got 15 minutes? Try git in-browser.
• GitHub Pages: Build websites hosted using GitHub.
• GitHub Pages & Jekyll: Jekyll is a static site generator that works really well with GitHub Pages.

Linux

• Linux Journey: Learn the ways of Linux-fu, for free.

Conferences and Papers

• UCAR - Software Engineering Assembly Conference Papers: UCAR = University Corporation for Atmospheric Research. Some presentations and links from the 2016 conference.

Other

• Julia: Julia is a high-level, high-performance dynamic programming language for technical computing. Designed for parallelism, speeds close to C.

Get in Touch

Got a stellar resource to add to this list? Send us a message on the BDS Meetup page, or submit a pull request to the 'gh-pages' branch of this resources repo.