Skip to main content

A divergence estimator of two sets of samples.

Project description

universal-divergence

universal-divergence is a Python module for estimating divergence of two sets of samples generated from the two underlying distributions. The theory of the estimator is based on a paper written by Q.Wang et al [1].

Install

pip install universal-divergence

Example

from __future__ import print_function

import numpy as np
from universal_divergence import estimate

mean = [0, 0]
cov = [[1, 0], [0, 10]]
x = np.random.multivariate_normal(mean, cov, 100)
y = np.random.multivariate_normal(mean, cov, 100)
print(estimate(x, y))  # will be close to 0.0

mean2 = [10, 0]
cov2 = [[5, 0], [0, 5]]
z = np.random.multivariate_normal(mean2, cov2, 100)
print(estimate(x, z))  # will be bigger than 0.0

References

[1]Qing Wang, Sanjeev R. Kulkarni, and Sergio Verdú. “Divergence estimation for multidimensional densities via k-nearest-neighbor distances.” Information Theory, IEEE Transactions on 55.5 (2009): 2392-2405.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for universal-divergence, version 0.2.0
Filename, size File type Python version Upload date Hashes
Filename, size universal-divergence-0.2.0.tar.gz (2.7 kB) File type Source Python version None Upload date Hashes View

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring DigiCert DigiCert EV certificate Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page