Replication package for "Investigating Language Design Choices on Class Openness"

This dataset includes scripts, text files, and cached Parquet or raw TXT data files used to generate all analysis and results from the paper.  A README.md file is included for details on using the scripts - though all of the data the scripts generate should already be cached as Parquet or you can use the raw TXT files (download just one data ZIP) and none of the scripts actually need run.