Skip to content

ncoop57/cute_ranking

main
Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
nbs
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Cute Ranking

A cute little python module for calculating different ranking metrics. Based entirely on the gist from https://gist.github.com/bwhite/3726239.

PyPI - Python Version PyPI Status PyPI Status license

Install

Requires a minimum python installation of 3.6

pip install cute_ranking

How to use

from cute_ranking.core import mean_reciprocal_rank

relevancies = [[0, 0, 1], [0, 1, 0], [1, 0, 0]]
mean_reciprocal_rank(relevancies)
0.611111111111111

The library current supports the following information retrieval ranking metrics:

  1. Mean Reciprocal Rank - mean_reciprocal_rank
  2. Relevancy Precision - r_precision
  3. Precision at K - precision_at_k
  4. Recall at K - recall_at_k
  5. F1 score at K - f1_score_at_k
  6. Average Precision - average_precision
  7. Mean Average Precision - mean_average_precision
  8. Discounted Cumulative Gain at K - dcg_at_k
  9. Normalized Discounted Cumulative Gain at K - ndcg_at_k
  10. Mean Rank - mean_rank
  11. Hit@k - hit_rate_at_k

Contributing

PRs and issues welcome! Please make sure to read through the CONTRIBUTING.md doc for how to contribute :).