inter_workshop

Workshop materials for ODSC 2019-2020 Interpretability Talk

The Notebooks here are to show:

1. Reading Skills Variable Importance, which shows how split based importance is misleading compared to permutation based approach.
2. Lack of Fidelity-Diversity using LIME on Adult, which shows how the Adult dataset on LIME provides the same top explanation for every explanation.
3. Lack of Consistency using LIME on Adult, which shows how the same datapoint can have different explanations.
4. Lack of Consistency LIME Boston, which shows how the same datapoint can have different explanations.

For more on learning about permutation, partial dependence, and explanations, take a look at the excellent Kaggle mini course on explainability as well as the Intepretable Machine Learning book.