Most awesome Chaz! I’m currently reading Tidy Modeling with R and thinking about how it might be applied to SC. But yeah, I’m a rank amateur at this point. Having the data is a great starting point.
Another thing… people make data sets by binge watching sitcoms. Perhaps we could encourage people to binge-read the canon and gather data on interesting features. If it doesn’t work, you’ve read some suttas anyway. 