Computes Kendall's coefficient of concordance
Project description
kendall-w
Author: Ugo Loobuyck
Overview
Computes Kendall's coefficient of concordance for inter-annotator agreement in the case of item ranking between more than two annotators.
Installation
To install use pip:
$ pip install kendall-w
Or clone the repo:
$ git clone https://github.com/ugolbck/kendall-w.git
$ python setup.py install
Usage
import kendall_w as kw
annotations = [
[1, 1, 1, 2],
[2, 2, 2, 3],
[3, 3, 3, 1],
]
W = kw.compute_w(annotations) # returns 0.4375 (fair overall agreement)
Contributions
All contributions are welcome.
How to help?
- Fork this repository to your GitHub account
- Clone the forked repositery to local
- Code something and push to your branch
- Create a pull request from your repository
TODO:
- Handle
pandas.DataFrame
as an input with the instructions in the main file - Use numpy for faster computation?
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
kendall-w-1.0.0.tar.gz
(3.3 kB
view hashes)
Built Distribution
Close
Hashes for kendall_w-1.0.0-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 2d555081ea1b1fa7345a7e24aaedbd079520d566953e2b7e31d91ee68337cca5 |
|
MD5 | 35f8f0b0687e6fdd53c225196962649e |
|
BLAKE2b-256 | c8f4d25d5fcfa6e771cb930e1d132bd6e7fc306060ffd921b5c4534a8631143c |