Data Mining OK Cupid

OK Cupid is one of my ‘holy grail’ datasets. There’s so much interesting data about what we do there.

I recently needed a dataset to test a hypothesis that OK Cupid would be perfect for, so I cobbled this together.

I got a great start from Andrew Matteson.

If this helps you out, let me know!

P.S.  Please read the OKCupid ToS very closely and make sure your use case isn’t breaking those rules.