Crime Doesn't Climb
Learning and science
crime data visualization
SHOW HN2013
How HN took it
3 positive, 22 neutral or asking, 0 mixed, 10 critical, out of 35 comments about the project. Thread score -0.24.
Idea: 3 for, 3 againstExecution: 0 for, 4 againstDesign: 0 for, 2 againstDocs: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Interesting visualization and a good small project
From 3 comments
This is why I'd be interested in looking at the graph for the neighborhoods south of 280, particularly in the eastern section of the city. In many areas, property values drop and…
geebee on HNI agree. This is a good example of a small project that was worth getting out there. The code is posted, so if it's triggering some ideas, that's kind of the point - by all…
geebee on HNInteresting. I suspect elevation is highly correlated with land value, so perhaps that is the hidden factor here? I'd like to see this applied to other hilly cities. Great work!
bdon on HN
Objections
Crime counts are not normalized by population density
From 3 comments
This is invalid. The numbers calculated are counts of crime incidents, not crime rates. A km^2 block with ten times the population density will have ten times the number of…
throwaway_yy2Di on HNData that reports per-person activity needs to control for population density in each section, otherwise it just becomes a population map. http://xkcd.com/1138/
brown9-2 on HNWell, fine. If you don't adjust for population density, you are correct. The more people in an area, the more crime there will be in general.
xxpor on HN
Elevation likely correlates with wealth and other confounders
From 3 comments
I'd like a map overlay of median(not average! that means nothing in SF!!!) income of those areas. Something tells me higher elevation = way more expensive, especially here in SF.…
smtddr on HNInteresting. I suspect elevation is highly correlated with land value, so perhaps that is the hidden factor here? I'd like to see this applied to other hilly cities. Great work!
bdon on HNThis is a fun exploration, but there are just so many plausible additional factors, from population density, to SFPD's selective enforcement, to many others that can be at least…
anateus on HN
Map is an unclear animated GIF with no explanation
From 2 comments
The first thing on that page is a GIF. There is no explanation. It is not clear what the GIF is meant to be portraying. I even went on to read the first two paragraphs, which…
coherentpony on HNThis is interesting, but on my browser, the map cuts out much of the southern section of SF. Is it included in the numbers? This area may present a particularly interesting…
geebee on HN
Requests
Control for population density
From 3 comments
What about weighted by population density?
codezero on HNCorrelate with population density? Also, the time of day?
snake_plissken on HNData that reports per-person activity needs to control for population density in each section, otherwise it just becomes a population map. http://xkcd.com/1138/
brown9-2 on HN
Overlay with topographic map or income data
From 2 comments
How about showing it overlaid with a topographical map?
bluedino on HNI'd like a map overlay of median(not average! that means nothing in SF!!!) income of those areas. Something tells me higher elevation = way more expensive, especially here in SF.…
smtddr on HN
Questions
Does the map include southern San Francisco?
From 1 comment
This is interesting, but on my browser, the map cuts out much of the southern section of SF. Is it included in the numbers? This area may present a particularly interesting…
geebee on HN
Alternatives named
LAPD CompStat crime maps
From 1 comment
There are a lot of confounding variables here, and others have mentioned a few. One I have not seen is "proximity to major arterials". Sometimes crime concentrates around major…
mturmon on HN
Data Science Toolkit
From 1 comment
Very good article! The Data Science Toolkit he pumps as an alternative to pirating google's APIs looks awesome, and deserves a direct link: http://www.datasciencetoolkit.org
kennywinker on HN