Skip to main content

Empirical Information Bottleneck

Project description

EMBO - Empirical Bottleneck

License PyPI version Build status

A Python implementation of the Information Bottleneck analysis framework (Tishby, Pereira, Bialek 2000), especially geared towards the analysis of concrete, finite-size data sets.


embo requires Python 3, numpy and scipy.


To install the latest release, run:

pip install embo

(depending on your system, you may need to use pip3 instead of pip in the command above).


(requires setuptools). If embo is already installed on your system, look for the copy of the script installed alongside the rest of the embo files and execute it. For example:

python /usr/lib/python3.X/site-packages/embo/

Alternatively, if you have downloaded the source, from within the root folder of the source distribution run:

python test

This should run through all tests specified in embo/test.


You probably want to do something like this:

import numpy as np
from embo import empirical_bottleneck

# data sequences
x = np.array([0,0,0,1,0,1,0,1,0,1]*300)
y = np.array([1,0,1,0,1,0,1,0,1,0]*300)

# IB bound for different values of beta
i_p,i_f,beta,mi,H_x,H_y = empirical_bottleneck(x,y)

More examples

A simple example of usage with synthetic data can be found in the source distribution, located at embo/examples/embo_example.ipynb.


embo is maintained by Eugenio Piasini, Alexandre Filipowicz and Jonathan Levine.

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

embo-0.3.0.tar.gz (45.2 kB view hashes)

Uploaded Source

Built Distribution

embo-0.3.0-py3-none-any.whl (19.5 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page