Context

I really wanted to run some statistical correlations on boardgames and their mechanics, so I scraped this data. I hope it helps others!

Content

Data was acquired by scraping the BoardGameGeek XML API at all boardgame entry endpoints. Finished acquiring data on 7/15/2020. XML files in raw_data represent the raw endpoints, while the CSVs are distillations of that data for users' convenience.

• basic_data.csv - basic stats on all boardgames in the database
• categories_data.csv - what categories do games belong to, and what are their BGG scores?
• mechanics_data.csv - what game mechanics do games use, and what are their BGG scores?
• subdomain_data.csv - what broad BGG categories do games fall under (e.g. Strategy Games, Party Games, etc.) and what are their BGG scores?

Acknowledgements

Thanks to BGG for providing the XML API that made this possible, as well as to mrpantherson whose original BGG dataset of the top 5,000 games inspired this effort. And thanks to the many users that powered this data by providing scores, tagging mechanics, etc.!

Inspiration

I'd love to get a better understanding of the correlations between various game attributes and how they are rated on BGG. It might also be fun to correlate with the "owned" property to get a rough measure of what qualities in games drive sales (at least among the BGG community).