cgcnn icon indicating copy to clipboard operation
cgcnn copied to clipboard

Question about fetching Materials Project Data

Open shuix007 opened this issue 2 years ago • 2 comments

Hi,

Thank you for your great work! I am trying to fetch the data from the Materials Project database based on the mp-ids that you provided. I am wondering if the mp-ids that you provided are materials id or task id?

I tried

MPRester().get_structure_by_material_id(id)

but a lot of the ids in your csv files return void responses. Then I tried

mid = get_materials_id_from_task_id(id)
structure = get_structure_by_material_id(mid)

and it worked. I want to ask if this is the correct way of fetching the dataset.

Thank you

shuix007 avatar Apr 01 '22 22:04 shuix007

Thanks for the question. I used materials ids. Unfortunately, Materials Project retired some of their old materials ids over the past few years. It is difficult to get the exact dataset used in the CGCNN paper that I downloaded in 2017. If you want to benchmark your algorithm against CGCNN, I'd recommend to create your own dataset with the latest Materials Project data. You should get similar results.

txie-93 avatar Apr 03 '22 12:04 txie-93

Thank you for your response!

shuix007 avatar Apr 04 '22 04:04 shuix007