About

This mini project aims to apply methods of interpreting machine learning models as described in Christoph Molnar's Interpretable Machine Learning book.

Data

Data was obtained from Kaggle website, in particular Lifestyle and Wellbeing dataset. The data used in this project was downloaded from Kaggle on March 22, 2021.

Resources

• Molnar's code on how to use iml package to interpret ML models following examples in his book is here. In his code, Molnar uses mlr and caret package for modeling.

• To use iml package for interpretation, and h2o package for modeling check this post. A similar post is here.

• To use lime, vip, and pdp package for interpretation, and caret and h2o for modeling check this post.

• To use DALEX package for interpretation, and h2o for modeling check this post.

• To use lime and pdp package for interpretation, and gbm, xboost, and h2o package for modeling check this post.

• Chapter 16 in Hands-on Machine Learning with R book provides examples on using pdp, vip, iml, DALEX, and lime package for interpretation, and h2o and xboost package for modeling.