This repository contains python code and raw data to reproduce the results in the paper "An Adaptive Machine Learning Strategy for Accelerating Discovery of Perovskite Electrocatalysts", by Zheng Li, Luke E. Achenie, and Hongliang Xin. The python file named "density_state_descriptor.py" includes all the feature functions for the electronic density of states that are calculated by density functional theory (DFT). The file named "compositional_descriptor.py" contains descriptor functions based on atomic properties in the perovskite structure. 'train.csv' and 'test.csv' contain all the data that are used for model training and model prediction.
