provide re-ranking runs from datasets #262
Merged
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
It's becoming increasingly common for datasets to include a standard initial result set for re-ranking experiments. ir_datasets provides these, but they are a bit inconvenient to use in pyterrier right now because it involves using
irds_ref
, building an appropriate dataframe, and merging in the query/document text.This PR exposes the functionality more conveniently through
dataset.get_reranking_run()
. (I'm open to alternative names here.)I also considered including the document text, but it's not always going to be needed and it seems more suitable to use the existing
pt.text.get_text()
pipeline for this.