After doing my post last month on OpenCV and face detection, I started looking into other algorithms used for pattern detection in images. As it turns out, Google has done a phenomenal job with their Vision API. It’s absolutely incredible the amount of information it can spit back to you by simply sending it a picture.
Also, it’s 100% free! I believe that includes 1000 images per month. Amazing!
About two weeks ago I created an extremely rough version of an R Shiny Application surrounding Medicare data. Right after publishing the blog post, I received a lot of input for improvement and help from others.
I was traveling for two weeks and had very little time to do any work on it. After creating a GitHub Repository for it, the user Ginberg played a huge role in cleaning it up and adding a lot more functionality. I found it incredible that a complete stranger to me would put in such effort to something like this. In fact, he isn’t even a resident of the USA – so Medicare probably isn’t on his radar as often as it is for some of us. Fantastic generosity!
Ultimately, I will be looking to keep this project alive and grow it to fully utilize a lot more of the Medicare data available. The infections data set was very simple and easy to use, so I started off with it but there are a lot more tables listed on data.gov. The purpose of this application is to allow people who don’t want to spend time digging through tables to utilize the information available. This isn’t necessarily just for people seeking care to make a decision but this could perhaps be utilized for others doing research regarding hospitals in the US.
The R Shiny App allows you to filter by location and infection information. These are important in helping to actually find information on what you care about.
Three key tabs were created by (@Ginberg):
Sorting hospitals by infection score
Maps of hospitals in the area
Data table of hospital data
Sorting hospital data by score:
This is a tricky plot because “score” is different for each type of metric
Higher “scores” aren’t necessarily bad because they can be swayed by more heavily populated areas (or density)
Hello R community. if you’re up for some fun tinkering with a Shiny App please join me on a new project. I would love to see some collaboration in designing a Shiny Application which will help people make a decision about a healthcare provider. I have only just begun on this project but would to work with others.
This is just a quick look at the data, the roughest shiny app you’ve ever seen can be located on my shinyapps.io page
The first goal is to help people find a provider based off of City and State (or perhaps zipcode and latitude/longitude). This can take the form of a list, map, etc. I would also like people to be able to glean some information about the place they are going in comparison to the surrounding locations.
I was only able to put a an hour or so into this (and that was months ago) but have decided that it would be fun to start collaborating with anyone who is interested. Please make any pull requests and I’ll get to them!
Call it gentrification, supply-and-demand, call it whatever you’d like… the fact is, rent prices have gone up in Colorado in the last decade. Chip Oglesby – GitHub – did a nice analysis on the data provided by colorado.gov.
What Type of Data Visualization Do You Choose (if any)?
Determining whether or not you need a visualization is step one. While it seems silly, this is probably something everyone (including myself) should be doing more often. A lot of times, it seems like a great way to showcase the amount of work you have been doing, but winds up being completely ineffective and could potentially harm what you’re doing. Once you determine that you actually need to visualize your data, you should have a rough idea of the options to look at. This post will explain and demonstrate some of the common types of charts and plots.