mat_discover 1.2.0

Data-driven materials discovery based on composition.

DiSCoVeR

A materials discovery algorithm geared towards exploring high performance candidates in new chemical spaces using composition-only.

Installation

Updates coming soon, including a PyPI distribution. Anaconda distribution to follow.

The current instructions are:

conda install flit # or `pip install flit`
git clone --recurse-submodules https://github.com/sparks-baird/mat_discover.git
cd mat_discover
flit install

Usage

The basic usage is:

from mat_discover.discover_ import Discover
disc = Discover()
disc.fit(train_df) # DataFrames should have at minimum "formula" and "target" columns
scores = disc.predict(val_df)
disc.plot()
disc.save()
print(disc.dens_score_df.head(10), disc.peak_score_df.head(10))

See mat_discover_example.py.

Citing

The preprint is hosted on ChemRxiv:

Baird S, Diep T, Sparks T. DiSCoVeR: a Materials Discovery Screening Tool for High Performance, Unique Chemical Compositions. ChemRxiv 2021. doi:10.33774/chemrxiv-2021-5l2f8. This content is a preprint and has not been peer-reviewed.

The BibTeX citation is as follows:

@article{baird_diep_sparks_2021,
place={Cambridge},
title={DiSCoVeR: a Materials Discovery Screening Tool for High Performance, Unique Chemical Compositions},
DOI={10.33774/chemrxiv-2021-5l2f8},
journal={ChemRxiv},
publisher={Cambridge Open Engage},
author={Baird, Sterling and Diep, Tran and Sparks, Taylor},
year={2021}
}