matsML

Huan Tran, huantd@gmail.com

matsML

matsML is a python-based machine-learning (ML) toolkit for some problems in materials science. Being initiated to support some of non-polymer ML works of Dr. Huan Tran, matsML was designed to be portable and self-contained, providing necessary materials to follow the workflows and reproduce the results reported. Given this objective, actual scripts used for Dr. Tran's works can be found in some examples of matsML while others are for tutorial purposes and beyond. matsML is free at https://github.com/huantd/matsml.git.

A typical workflow of materials informatics includes preparing/generating/collecting suitable data, featurizing (or fingerprinting) the data, learning the featurized data to make models, using the developed models to make predictions, inverting the models to solve inverse problems, and more. This toolkit does not aim at providing complete solutions to any of these steps. However, demonstrations for most of the typical workflow can be found in some examples of matsML.

Most of the computed data referred to in this toolkit are from Dr. Tran's works (see here), supported by the XSEDE's DMR170031 project; others are open reported data. In cases of experimental data that are subjected to copyright and ownership, suitable freely available alternatives are provided for demonstration purpose. Questions, requests, and comments are welcome at huantd@gmail.com.