ennemi: Non-linear correlation detection with mutual information

We present ennemi, a Python package for correlation analysis based on mutual information (MI). MI is measure of relationship between variables. Unlike Pearson it valid also non-linear relationships, yet in the linear case two are equivalent. The effect other variables can be removed like with partial correlation, same equivalence. These features make better exploratory many variable pairs. Our provides methods common tasks using MI. It scalable, integrated data science ecosystem, and requires minimal configuration.