Replies: 1 comment
-
Maybe you can do it in the preprocessing part of creating |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I have a dataset with a particular feature set which I would like to experiment with, but the total number of interactions is very large. Is there a way in RecBole to randomly sample, say, 10% of all users? This way I can experiment with various algorithms and get a rough idea about what might work best for the full dataset.
I see that I can filter by min/max interactions for users/items but that wouldn't quite fit this case
Beta Was this translation helpful? Give feedback.
All reactions