Skip to content

fallback scenario indexers issue #69

Closed
monkey0head opened this issue Jan 17, 2022 · 2 comments
Closed

fallback scenario indexers issue #69

monkey0head opened this issue Jan 17, 2022 · 2 comments
Milestone

Comments

@monkey0head
Copy link
Contributor

monkey0head commented Jan 17, 2022

In addition to #68 there is probably a bug in fallback scenarios indexers.
they seem to be one object, but they need to be different objects for proper cold users and items processing.
length of scenario user indexer labels is not equal to the number of users in train dataset. also new users from test were not included to the indexers (at least poprec indexers inside Fallback), but should be.
I believe, the length of user indexer for fb_model in scenario should be 6040 as for pure poprec model.
image

@Darel13712
Copy link
Contributor

They are different indexers. One thing to remember is that main and fallback models do not train on full dataset, but only on a warm part of it. Only cold_model sees the whole dataset.

hot_data = min_entries(log, self.threshold)

@Darel13712 Darel13712 added this to the Indexer milestone Feb 3, 2022
@monkey0head
Copy link
Contributor Author

closed by #96

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants