The repository contains all necessary tools to understand and replicate the project. The scripts and data sets are numbered corresponding to the following steps and their outputs. Each script and dataset has a number corresponding to the steps discribed below e.g. Step 2, data disaggregation, has a script and output dataset labled with a "2" followed by a descriptive name. Only exception is step 1, where the data presents the input, not the output.

The data exploration, disaggregation and preperation is based on Team 23 of Silerzahn et al. (2018). Only "cosmetic" changes were made to the original scripts.