Magpie Manual

What is Magpie?

Magpie is an extensible platform for using machine learning to create models of the properties of material.

Magpie is also an acronym for “Material-Agnostic Platform for Informatics and Exploration”, and is named after an intelligent bird.

Reasons to use Magpie

  1. Ability to manipulate datasets, create models, and evaluate performance in the same program
  2. Access to extensive library of machine learning algorithms through Weka
  3. Interactive text-based scripting interface
  4. Easy sharing of models in a machine-independent format

Getting Magpie

Magpie open source, and is both hosted on BitBucket and available in compiled form on OQMD.org. The distribution of Magpie includes:

Magpie is written entirely in Java, which allows it to be run on most computers without modification. As long as the Java 7 Runtime Environment is installed on your computer, Magpie should run without issue.

Learning About Magpie

If you are brand new to Magpie, you might want to read the tutorial section of this manual and then review a few example scripts:

Additionally, you may also want to read the following article, which provides a short introduction to using machine learning to predict new materials and explains the science behind one of algorithms available through Magpie.

Ward, L., et. al.. Journal. Issue (Year), Pages.