Open bschifferer opened 1 year ago
thanks @bschifferer. these are all valid points. can we also add nulls
issue to this list? integration test fails if we have nulls in the user id
and item id
columns in the real dataset.
Changed priority to P1. Refer https://nvidia.slack.com/archives/C01RP7T89PY/p1663872124879779?thread_ts=1663843219.331779&cid=C01RP7T89PY
Just for context on how we got here:
I agree that this stuff is important though, and we might soon have bandwidth to tackle it, once we get session-based serving for both TF and Torch ironed out. Maybe in the 23.04-23.05 timeline?
Bug description
The unit test of the 2-stage recommender system pipeline is shaky due to multiple reasons:
-1
for not found candidates ---1
cannot be processed by FEAST -- Issue is that FIASS has not enough item vectors to generate an index. Even 256 item_embeddings could result in less than 100 candidatesUnit test: https://github.com/NVIDIA-Merlin/Merlin/blob/main/tests/unit/examples/test_building_deploying_multi_stage_RecSys.py
Edge cases, we should be handling without crashing the systems:
What should be the result in each of the cases?