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

How to fill the value in JoinOrderBenchmark.TRUE_FULL_OUTER_CARDINALITY? #1

Open
hzy9819 opened this issue Apr 10, 2021 · 2 comments
Open

Comments

@hzy9819
Copy link

hzy9819 commented Apr 10, 2021

I want to change a new dataset for the model but I don't know the meaning of this dict

@concretevitamin
Copy link
Member

@hzy9819 those are the full outer join cardinalities for specific join graphs. They are used as the normalizing constant to convert probability outputs from NeuroCard's model to cardinalities.

For a new dataset/join graph, the full outer cardinality is automatically calculated and cached in the attribute FactorizedSampler.join_card. This can then be statically registered in datasets.py. Specifically, try printing join_iter_dataset.sampler.join_card after this line of run.py.

@hzy9819
Copy link
Author

hzy9819 commented Apr 15, 2021

Got it! It seems i need to change a lot for a new dataset... Could you please write a guide for this?

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

No branches or pull requests

2 participants