AmenRa / ranx

⚡️A Blazing-Fast Python Library for Ranking Evaluation, Comparison, and Fusion 🐍

https://amenra.github.io/ranx

AmenRa/ranx Issues

JIT compilation on serverless (i.e. Modal Labs)
Updated 2 months ago
[Question] How to compute precision for a retriever operating at passage-level
Updated 3 months ago
[Question] About the correction among multiple hypotheses
Updated 4 months ago
Spearman, Kendall correlation functions
Updated 4 months ago5
How do we compare different runs with multiple folds per run?
Updated 4 months ago1
[Feature Request] Propensity-scored Metrics
Updated 5 months ago
PSP@k: Propensity-scored precision at k
Closed 9 months ago9
[Feature Request] stddev statistic
Closed 6 months ago3
Getting "Segmentation fault (core dumped)" error
Closed 6 months ago2
Why ranx is too slow in this simple example?
Closed 2 years ago8
Couldn't find any documentation about Qrel and run score range
Closed 6 months ago2
Question on rank aggregation usage
Closed 7 months ago4
[BUG] Issues when storing/loading Qrels from a dataframe and a parquet file.
Closed 8 months ago6
[Feature Request] Run.from_df and Run.from_parquet does not allow specifying run name
Closed 8 months ago1
[BUG] Misleading exception message on dataframe types
Closed 8 months ago2
Zero-scored documents
Closed 9 months ago10
[Feature Request] Support gzipped files?
Closed 10 months ago3
Incorrect result for f1 score
Closed 10 months ago13
[BUG] RBP with multiple relevance levels
Closed 10 months ago3
[Feature Request] memory issue / make Run more efficient
Closed 10 months ago2
[Feature Request] Use black to indent the code
Closed a year ago1
[BUG] dcg and dcg_burges do not work in the compare function
Closed a year ago2
[Feature Request] Expose DCG as metric
Closed a year ago3
[Feature Request] Add interpolated recall-precision plot function
Closed a year ago4
[BUG] Missing results causes AssertionError
Closed a year ago1
question: why student rather than fisher stat test?
Closed a year ago4
ValueError: max() arg is an empty sequence
Closed a year ago7
[BUG] Could not find a version that satisfies the requirement ranx
Closed a year ago4
[Feature Request] custom fusion method in optimize_fusion
Closed a year ago14
[Feature Request] optimize norm and method in optimize_fusion
Closed a year ago1
[BUG] Precision calculation incorrect?
Closed a year ago6
Ranx pip installing failed
Closed 2 years ago1
[BUG] `MRR@1` is not equal `Recall@1`
Closed 2 years ago3
[Feature Request] relevance_level parameter
Closed 2 years ago1
Qrels and Run query ids do not match
Closed 2 years ago3
[Feature Request] infer run/qrels format from file extension in `from_file`
Closed 2 years ago2
[BUG] ttest_rel() got an unexpected keyword argument 'alternative' when using compare with stat_test="student"
Closed 2 years ago4
Problems with MAP
Closed 2 years ago2
Issues with MAP
Closed 2 years ago
Integer relevance score
Closed 2 years ago4
Why in Recall@k you divide on len(relevant), but not min(len(relevant), k)
Closed 2 years ago2
[Feature Request] Benchmarking
Closed 2 years ago1
[BUG] from_ir_datasets seems to be missing from Qrels
Closed 2 years ago3
[BUG] win_tie_loss in Report.to_dict
Closed 2 years ago1
[Feature Request] from ranx import Report
Closed 2 years ago9
[Feature Request] Reciprocal Rank Fusion
Closed 2 years ago1
set Report’s rounding_digits in compare
Closed 2 years ago5
feature request: hits (or accuracy?)
Closed 2 years ago7
bug: using built-in `type` function instead of type argument
Closed 2 years ago1
add an option to disable sort_dict_of_dict_by_value when adding results to a run
Closed 2 years ago6