Interpretability methods to analyze the behavior and predictions of any machine learning model. Implemented methods are: Feature importance described by Fisher et al. (2018) &lt;<a href="https://doi.org/10.48550%2Farxiv.1801.01489" target="_top">doi:10.48550/arxiv.1801.01489</a>&gt;, accumulated local effects plots described by Apley (2018) &lt;<a href="https://doi.org/10.48550%2Farxiv.1612.08468" target="_top">doi:10.48550/arxiv.1612.</a>…