xenonpy 0.1.0b4

material descriptor library

What is XenonPy project

XenonPy is a Python library focus on the material informatics which be designed for material explore based on machine learning.

The main purpose of this project is to build a complex system to calculate various chem/phys descriptors for machine learning then extend them to explore material space. To reach this target, system also provide model training routines and try to re-use pre-trained model by various deep learning methods such as transfer learning.

This project has just started and a long way to run. The final goal of this project is to build a All-In-One virtual environment for material development come with:

• Massive dataset and Pre-trained models out-of-box

• Various descriptor calculation methods

• Model training and re-use

• Combined with deep learning methods seamless

• Visualization tools for analysis and publish ready

XenonPy inspired by matminer: https://hackingmaterials.github.io/matminer/.

XenonPy is a open source project https://github.com/yoshida-lab/XenonPy.

See our documents for details: http://xenonpy.readthedocs.io

Contribution guidelines

• Discussion with others

• Docstring use Numpy style.

• Check codes with Pylint

• Writing tests if possible

Contract

• With issues

• With Gitter

Copyright and license

Code and documentation © 2017 TsumiNa. Released under the BSD-3 license.