Skip to content

Kedar-Materials-by-Design-Lab/SC_model

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

SC_model

SC Model is an inorganic material crystal materials synthesizability score prediction model

Installation

Please use Python 3.7.7 to run the model.

To install, just clone the repository. Then install all required packages:

pip install -r requirement.txt

Usage

You can train and test the ternary SC model by:

python main.py

You can choose to include or exclude FTCP feature set, or use only atomic features by running:

python main.py --rp include_ftcp
python main.py --rp exclude_ftcp
python main.py --rp atomic

You can also use pre-trained compositional model or full crystal representation model to predict SC for compounds:

python .\predict.py --type formula --crystal CaTiO3
python .\predict.py --type cif --crystal .\data\predict_cif\CaTiO3_mp-4019_conventional_standard.cif

Authors

The code was primarily written by Ruiming Zhu, under supervision of Prof. Kedar Hippalgaonkar.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • PureBasic 66.7%
  • Python 33.3%