As an invasion biologist, the process of spatial spread is at the heart of what I do. When I came across this dataset of Walmart store openings since 1962 I couldn’t help but see it as an invasion front which looks a lot like a biological invasion or (albeit slow) epidemic.
The video shows monthly store openings (in red) between 1962 and 2006.
You can get the code I wrote for generating this visualization on my github page.
bayesianbiologist 
coolol
Very interesting work !
I observe that the new opening are somehow following a “biological” schema: the new openings are closed to the previous ones when I expected to see the first openings in major US cities first.
There was visualization of this dataset on FlowingData: http://projects.flowingdata.com/walmart/
A similar chart just appeared on Mashable:
http://mashable.com/2012/08/30/growth-of-walmart-gif/
I wonder if it used your code…
Thanks for the heads up, but I think that vis predates my R implimentation. After I did this I found a few others who had visualized the same data sets using various tools (see the flowing data link above). I would love to see someone take my R code, make improvements and share it, though!
Wonderful post,
I am having difficulties replicating the post along with the post for and update on bayesian distributions,
this is the error that i get:
Error in png(paste(“plots/”, 1000 + frame, “.png”, sep = “”)) :
unable to start png() device
In addition: Warning messages:
1: In png(paste(“plots/”, 1000 + frame, “.png”, sep = “”)) :
Unable to open file ‘plots/1001.png’ for writing
2: In png(paste(“plots/”, 1000 + frame, “.png”, sep = “”)) :
opening device failed
>
the error happends in the paste walmart post it happens with the variable year like in:
png(paste(‘plots/’year,’_’,100+month,’.png’,sep=”),
Could you please help me understand what am I doing wrong? Thank you!
Hey Manuel,
I am guessing that you may not have created a folder called ‘plots’ under your current working directory. If you create that folder, it should work.
I’m glad you found the post interesting.
-Corey
TOTALLY right! Amazing, thank you so very much, Corey. I will make sure to include your name an refer to your site and work in my lectures!
Thank you, again!
Cheers!
Pingback: Les data en forme » OWNI, News, Augmented
Pingback: The Week In Data » OWNI.eu, News, Augmented
Thank you for doing this and making the code available! I modified it a bit for my own project – a video to demonstrate the pervasiveness of accusations of child sexual abuse in the Boy Scouts of America throughout the US from 1960-1985 based on the now-released BSA Ineligible Volunteer Files. The video can be found at http://youtu.be/0F8uTZcKBU4 And of course, full attribution is given at the YouTube site. Thanks again!
Very cool. I love seeing code being re-purposed for interesting projects. Thanks for letting me know.
Pingback: THE WEEK IN DATA | ngoloan
Pingback: Somewhere else, part 8 | Freakonometrics
Loved this… I have been trying hard to find their recent data.. hope i get those and build something similar. Thanks for the idea.