Fast computation of the Krippendorff's alpha measure.
Project Links
Meta
Author: Santiago Castro
Requires Python: >=3.10
Classifiers
Development Status
- 4 - Beta
Intended Audience
- Science/Research
License
- OSI Approved :: GNU General Public License v3 (GPLv3)
Operating System
- OS Independent
Programming Language
- Python
- Python :: 3
- Python :: 3.10
- Python :: 3.11
- Python :: 3.12
- Python :: 3.13
- Python :: 3.14
Topic
- Scientific/Engineering
- Scientific/Engineering :: Artificial Intelligence
Fast Krippendorff
Fast computation of Krippendorff's alpha agreement measure.
Based on Thomas Grill implementation.
Example usage
Given a reliability data matrix, run:
import krippendorff
krippendorff.alpha(reliability_data=...)
See sample.py and alpha's docstring for more details.
Installation
pip install krippendorff
Caveats
The implementation is fast as it doesn't do a nested loop for the coders. However, V should be small, since a VxV matrix it's used.
Citing
If you use this code in your research, please cite Fast Krippendorff:
@misc{castro-2017-fast-krippendorff,
author = {Santiago Castro},
title = {Fast {K}rippendorff: Fast computation of {K}rippendorff's alpha agreement measure},
year = {2017},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/pln-fing-udelar/fast-krippendorff}}
}
0.8.2
Nov 03, 2025
0.8.1
Jan 15, 2025
0.8.0
Oct 08, 2024
0.7.0
Jun 18, 2024
0.6.1
Oct 04, 2023
0.6.0
Mar 28, 2023
0.5.2
Oct 26, 2022
0.5.1
Dec 06, 2021
0.5.0
Oct 06, 2021
0.4.0
Oct 12, 2020
0.3.3
Oct 07, 2020
0.3.2
Nov 25, 2019
0.3.1
Oct 20, 2019
0.3.0
Apr 26, 2019
0.2.3
Feb 05, 2019
0.2.2
Apr 02, 2018
0.2.1
Oct 08, 2017
0.2.0
Oct 08, 2017
0.1.1
Oct 04, 2017
0.1.0
Sep 28, 2017
Wheel compatibility matrix
Files in release
Extras:
None
Dependencies:
numpy
(<3,>=1.21)