Analyze zone type as a predictor of user accuracy

[jonfroehlich]

We can get the zone information for Seattle from Raymond Fok and for Washington DC from @misaugstad.

This relates to #22

[misaugstad]

I think this is probably the data you want from DC https://drive.google.com/open?id=1owNZR7PPpJXWtVfGDBRTrxD7LKpCxhxY

[nch0w]

Here's a plot of zone type vs proportion of labels that are correct for each label type.
I filtered out zone types that had less than 100 labels of the given label type.

A trend: Industrial is hard, as we predicted.

[jonfroehlich]

Could likely do a chi-squared test to see if there are significant differences in the pattern

…

On Fri, Aug 2, 2019 at 4:43 PM Neil Chowdhury ***@***.***> wrote: Here's a plot of zone type vs proportion of labels that are correct for each label type. I filtered out zone types that had less than 100 labels of the given label type. [image: Screenshot from 2019-08-02 16-38-01] <https://user-images.githubusercontent.com/17211794/62403775-909b2100-b544-11e9-8101-c2c83a13581d.png> A trend: Industrial is hard, as we predicted. — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#32?email_source=notifications&email_token=AAML55OGYKQAQUHJYAKGZMTQCTBDDA5CNFSM4IILNQN2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOD3PB5KA#issuecomment-517873320>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AAML55K5KLL7DEROHD333GLQCTBDDANCNFSM4IILNQNQ> .

-- Jon Froehlich Associate Professor Paul G. Allen School of Computer Science & Engineering University of Washington http://makeabilitylab.io @jonfroehlich <https://twitter.com/jonfroehlich> - Twitter Help make sidewalks more accessible: http://projectsidewalk.io