What is the correct way to establish the X_train.tsv/X_test.tsv/server.tsv file needed in the 38/44/50th line of data.py？

[Gengsheng-Li]

Dear authors,

I hope this email finds you well. I have already gained the OpenBHB dataset needs here, howerver, it seems like X_train.tsv/X_test.tsv/server.tsv (X is the client index, they appear in the 38/44/50th line of data.py) files are necessary for running this project completely. Could you please give me some instructions on how to correctly establish these .tsc files?

Thanks for your kind help! Looking forward to your reply.

Best regards! :-D

[Abtinmy]

Hi,

These files serve as records for each client in our methodology as their local data. Establishing these .tsv files involves sampling records for each client from the original dataset based on specific criteria. You can employ methods such as random sampling or grouping records based on common attributes such as site, acquisition settings, age, etc.