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

Make predictions from a run easily accessible #1103

Closed
PGijsbers opened this issue Jul 12, 2021 · 1 comment · Fixed by #1128
Closed

Make predictions from a run easily accessible #1103

PGijsbers opened this issue Jul 12, 2021 · 1 comment · Fixed by #1128

Comments

@PGijsbers
Copy link
Collaborator

If I'm not overlooking anything, there is no convenient way to access predictions that are stored in a run. The run object only exposes functions which use the data internally (e.g. get_metric_fn). Internally predictions are downloaded and processed (here).

I propose we add a predictions property which can serve the predictions in dataframe format through lazy loading. The remainder of the code should then also be refactored to use this property.

@PGijsbers
Copy link
Collaborator Author

PGijsbers commented Jul 12, 2021

In the meanwhile, you can access predictions with:

import openml
import arff
r = openml.runs.get_run(RUN_ID)

response = openml._api_calls._download_text_file(r.predictions_url)
predictions_arff = arff.loads(response)

PGijsbers added a commit that referenced this issue Mar 11, 2022
PGijsbers added a commit that referenced this issue Mar 11, 2022
@PGijsbers PGijsbers mentioned this issue Mar 11, 2022
PGijsbers added a commit that referenced this issue Apr 19, 2022
* Add easy way to retrieve run predictions

* Log addition of ``predictions`` (#1103)
PGijsbers added a commit to Mirkazemi/openml-python that referenced this issue Feb 23, 2023
* Add easy way to retrieve run predictions

* Log addition of ``predictions`` (openml#1103)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging a pull request may close this issue.

1 participant