Where to look for more information

This book can’t possibly cover everything there is to know in two massive disciplines. Each author here has obtained their knowledge through other references and through experience. The latter is hard earned but we can easily share some of the former.


Machine Learning and Data Science

  • Statistics, Data Mining, and Machine Learning in Astronomy by Željko Ivezić, Andrew J. Connolly, Jacob T. VanderPlas & Alexander Gray

    • This book, which also has an accompanying python module called AstroML, introduces the reader to sophisticated statistics, data mining, and machine learning techniques to analyze large data sets in astrophysics. Heliophysics can be be considered a specialized subset of astrophysics, so many of the methods described in this book are relevant.

  • Python Data Science Handbook by Jacob T. VanderPlas

    • A good way to get started with the core libraries necessary for scientific computing. The final chapter is dedicated to machine learning with the python package scikit-learn.

  • Machine Learning via Coursera by Andrew Ng

    • This online course provides a broad, practical introduction machine learning techniques by going through weekly lectures and coding homeworks (based on the Stanford University course CS 229).

  • A Gallery of Interesting Jupyter notebooks

    • A (seemingly) endless list of notebooks that both introduce machine learning at a beginner’s level and work through practical examples (John Wittenauer’s collection is especially impressive).


  • Clean Code by Robert C. Martin

    • Well-written book that teaches best programming practices using lots of example code.

  • A Byte of Python by Swaroop C. H.

    • An excellent tutorial on Python for beginners.