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.

Sign up for GitHub

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

Jump to bottom

[v2 QUESTION]: test dataset of ensemble #1130

Closed
jia-huang opened this issue Dec 19, 2024 · 1 comment
Closed

[v2 QUESTION]: test dataset of ensemble #1130

jia-huang opened this issue Dec 19, 2024 · 1 comment
Labels
question Further information is requested

Comments

@jia-huang
Copy link

When using the following commands for training, is the test set the same for each model? If it is the same, how can we adjust the settings to ensure that each model's test set is different?

chemprop train --data-path FDA-smiles.csv --task-type classification --output-dir FDA_checkpoints_rdkit_2d-hpopt-20ensembl-8 --molecule-featurizers v1_rdkit_2d_normalized --no-descriptor-scaling --ensemble-size 20 --config-path best_config_zidong.toml --epochs 30

Additionally, how can we configure the settings to implement 20-fold cross-validation during training?
@jia-huang jia-huang added the question Further information is requested label Dec 19, 2024
@shihchengli
Copy link
Contributor

If you use --ensemble-size, it trains 20 models on the same data split. To run 20-fold cross-validation, you need to create a JSON file with 20 splits on your own (an example can be found here).

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
question Further information is requested
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@shihchengli @jia-huang