Hacker News new | past | comments | ask | show | jobs | submit login

It wouldn't surprise me in the slightest if your Age, Salary and hours are unique in the table. In fact, I'm relative certain that any two of the numerical fields (family excluded, since so many people had 0) would uniquely identify you, or at least limit it to on a handful of individuals. The concept of "Anonymous data" is largely non-existant; if you know who you're looking for in a table of anonymous data, you can usually find them.



Hmm. I whipped up a quick python script to test this theory.

  Age,Hours Wrkd,Income was unique ~89% of the time
  Age,Hours Wrkd, Yrs in industy,Income was unique 97% of the time
  Age,Education,Hours Wrkd,Income was unique 94% of the time
  Age,Education,Hours Wrkd,Yrs in Industry,Income was unique 98% of the time

Here it is if anyone wants to play with it. http://paste.pocoo.org/show/136649/




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: