A numpy implementation of Robust Rank Correlation Coefficients.
Project description
fuzzycorr
A numpy
implementation of Robust Rank Correlation Coefficients (fuzzy correlation) based on paper:
Bodenhofer, U., and F. Klawonn. "Robust rank correlation coefficients on the basis of fuzzy." Mathware & Soft Computing 15.1 (2008): 5-20.
This implementation is experimental and need future optimization and testing.
Installation
This package will be avaliable soon on pip
.
Basic usage
from fuzzycorr import fuzzy_correlation_factory
from fuzzycorr.strict_orderings import lukasiewicz_strict_ordering_factory
from fuzzycorr.t_norms import godel
# create strict fuzzy ordering or supply own one
strict_ordering = lukasiewicz_strict_ordering_factory(r=0.2)
# create fuzzy correlation function with tnorm
fuzzy_corr = fuzzy_correlation_factory(strict_ordering, godel)
# load data
x = np.random.random(10)
y = np.random.random(10)
# calculate fuzzy correlation
fuzzy_corr(x, y)
Visit example Jupiter Notebook.
Development
Clone this repository to the folder, then:
# create virtualenv (optional)
$ mkvirtualenv fuzzycorr -p python3
#if is not actived (optional)
$ workon fuzzycorr
$ pip install -e .
$ python setup.py test
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
fuzzycorr-0.1.0.tar.gz
(3.8 kB
view hashes)
Built Distribution
fuzzycorr-0.1.0-py3.10.egg
(6.6 kB
view hashes)