Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Best practice to update interactions with an existing dataset #2086

Open
gabarlacchi opened this issue Sep 20, 2024 · 2 comments
Open

Best practice to update interactions with an existing dataset #2086

gabarlacchi opened this issue Sep 20, 2024 · 2 comments
Assignees
Labels
enhancement New feature or request

Comments

@gabarlacchi
Copy link

Hi there! Thanks for the nice work in RecBole!

I'm implementing a simulation system in which I generate interactions between users and items within an existing system. At the start I create the dataset from a pre-loaded environment and define everything for recbole system. Everything's fine.
During the experiment, I would like to fully update the interactions that the system produce. I didn't find any useful functions to easy do such operation.

I missed something or can be a future update of the system?

So far, I just re-init the whole system by appending the new interactions to the .inter file, and run again the model and dataset configuration. There's a better way to do that?

Thanks!

@gabarlacchi gabarlacchi added the enhancement New feature or request label Sep 20, 2024
@TayTroye
Copy link
Collaborator

@gabarlacchi
Hello! Thanks for your attention.
You can use interaction.update to append new interactions.

def update(self, new_inter):

@fightingman1
Copy link

This ''update'' function can not update other field in the Interaction automatically. For example:
The batch_size of interaction: 1
user_id, torch.Size([1]), cpu, torch.int64
item_id, torch.Size([1]), cpu, torch.int64
timestamp, torch.Size([1]), cpu, torch.float32
item_length, torch.Size([1]), cpu, torch.int64
item_id_list, torch.Size([1, 50]), cpu, torch.int64
timestamp_list, torch.Size([1, 50]), cpu, torch.float32

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

3 participants