Cathy Deng

Our current training data consists of: - some GA campaign finance names - only rows that have both first & last name (to filter out organizations), w/ first & last...

@waldoj this is wonderful - thanks!!

looks like 85/1148 were parsed incorrectly, & most failures were more than one token, but had some tricky words that the parser hasn't seen before. these failures are great training...

hey @Downchuck - we already have the most common names from the census. do any of these datasets contain full name strings, instead of name components that are already split...

yes - instructions here: https://github.com/datamade/probablepeople#for-the-nerds

:sparkling_heart:

yes these are excellent suggestions - thanks for opening this issue!

merge w/ info on issue #22?

we probably need to discuss this again, before the ad campaign...

just set up one IDK page for now: http://www.expunge.io/notsure perhaps later we can discuss an IDK page for arrests & an IDK page for court cases, as which questions will...