ennemi: easy nearest neighbor estimation of mutual information. Mutual information (MI) can be used to find non-linear correlations between variables, and this Python 3 package is designed to fit into your data analysis workflow.

This release only contains internal infrastructure changes. This version should produce same results as ennemi 1.4.0 (up to possible differences in random number generation). This minor release drops support for pandas 1.x. If you cannot upgrade pandas, you should stay in ennemi 1.4.0.

The documentation for this release is available at https://polsys.github.io/ennemi. This release requires at least

• Python 3.11
• NumPy 1.24 (NumPy 2.0 is supported)
• SciPy 1.10
• (Optional: pandas 2.0+)

Changes since 1.4.0

• Minimum required versions of dependencies have been increased: in particular pandas 1.x will no longer work with this release.
• Tested to work with Python 3.13. The new experimental features (JIT and free-threading mode) in Python 3.13 are not yet guaranteed to work.
• Internal changes in how the package is built.

There are no new features or algorithm changes. If you cannot upgrade your Python version, ennemi 1.4 should produce (near-)identical results.

Installation

This package is available on PyPI. To install/update it, execute

pip install --upgrade ennemi

on your Python installation.

Contributing

Your feedback is very valuable! If you encounter any problems, please file an issue. Code contributions are welcomed as well.