Anubhav Jain

The relevant section of the paper is below:

N_e = sum of s and p valence electrons per formula unit of the material. I imagine the best is we do sum of s and p valence electrons per...

Another thing one could do is: - "pymatgen" preset just contains a large list of pymatgen element properties - add a new "matminer" preset that tries to find all the...

Note that returning a NaN for precheck could be considered as neither failing or passing a precheck, e.g., if the precheck test was skipped for a large structure

At the very least precheck skipping should be discouraged. Let's not introduce this unless we feel it is *really* necessary. Based on your comment I got the sense that some...

Hi, The initial (default) purpose of a background task was to run a process repeatedly at some interval - e.g., every 60 seconds or so - while the main task...

As @shyuep says, currently you can build your own convergence tests using the workflows in atomate but it does require a little bit of coding and thought. I could see...

@Doppe1g4nger I'd lump this more into "transfer learning" than "feature learning" - i.e., you are using models trained on a different data set to inform your ML on your current...

@ardunn good point. We might want to have a set of pre-fit StackedFeaturizers in matbench that matminer can use

As long as it can be done cleanly in the code and not making too much complication I think this could be fine. I guess the mechanism for doing this...