I'm interested in building histograms over the values of data observed one-at-a-time in a sequence. However, the only techniques I know of for building histograms require ALL of the data to be present at once. This seems like it must be a common problem, so i'm assuming there are some algorithms out there that i'm unaware of. I'm looking for any pointers or suggestions to some of these. Btw- i'm happy to simplify and pick a # bins in advance if that makes things easier.

asked Apr 14 '12 at 14:29

downer's gravatar image

downer
54891720

Be the first one to answer this question!
toggle preview

powered by OSQA

User submitted content is under Creative Commons: Attribution - Share Alike; Other things copyright (C) 2010, MetaOptimize LLC.