Skip to content

This repository contains models predicting whether each element in the composition formula is ordered/both oredered and disordered/disordered

Notifications You must be signed in to change notification settings

lrcfmd/Element-disorder-prediction

Repository files navigation

Element-disorder-prediction

This repository contains models predicting whether each element in the composition formula is ordered/both ordered and disordered/disordered (3 classes)

The latest model is a modified CrabNet. Also it would be reasonable to use Roost for this task, but I think I have lost the old code for that, and did not write the new one recentely..

CrabNet + Mat2Vec

Per element balanced accuracy = 0.79, per-element f1-score = 0.79, per-element mcc = 0.77

Compound accuracy (compound is classified correctly if all elements in it are classified correctly) = 0.71

Compound accuracy for ordered compounds = 0.88

Compound accuracy for disordered compounds = 0.59

Ensembling does not help

I think that we also can train model which has only two classes -- ordered and disordered (meaning that it has at least one disordered orbit) -- it should have higher scores

About

This repository contains models predicting whether each element in the composition formula is ordered/both oredered and disordered/disordered

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published