I just got access to the data set last week, and I’m starting to try to build out plots as per my colleagues’ requests. I’ve found the data itself to be a little bit tough to work with, but that’s due primarily to how the data is stored. I’m not sure that the data is clean, and it’s hard to get data for specific months when it’s stored as weekly data. So I’m currently checking in to see whether it would be preferable to keep to the weekly data or switch over to the daily data and do some sort of direct conversion. I really just have to wait for feedback on that one.

Based on how things are going with the coronavirus, I’ve decided that trying to work for a casino right now is probably just a bad idea. And so I’m going to volunteer with the Southern Nevada Health District. What exactly this will look like is still kind of open. The lead data scientist suggested that doing COVID modeling would be helpful to them, and it kind of makes sense to me to go down that path. He gave me a couple links to explore:

The statistics with R course is going on full at this point. And by that, I mean I’m just spending most of the day reading and working through the examples in the book. In the first week (plus a couple days because I started early), I’ve worked my way through 12 of the 19 chapters. It’s not really “hard” material (at least, not yet). And it helps that the book has a companion website where you can download chunks of code and data sets instead of having to manually type stuff in.

The course is now officially over. Everything is graded and the final score is 94% for the course. It was a pretty easy course overall for me. And the grading scale is such that even with the group project ending up being somewhat of a mess, the grade for that was still a solid B.

I got my hands on a preliminary spreadsheet of data. The goal was for me to get a sense of what the data would look like so I can start playing with making graphs. It’s a CSV file, but it’s not straight data. The metadata is stored at the top of the file. So I had to first write a short script to strip off the metadata and move it to a different file, and then also move the pure data into its own file. I hope that the different files will all have the same format.

The instructor posted a final exam review today, so I guess that means that we’re done covering material. I’ve enjoyed the class, even though it has been a little slow. I definitely come away from this with a better sense of the underlying logic of databases and how they are constructed. I also got some more SQL practice (but we didn’t do IF-THEN and CASE queries).

Another project I’ve had floating around in the background was the collection of data that captures student affect in mathematics. The questions are taken from the Short ATMI Survey and we try to collect it on basically the entire body of math students twice per semester. I have the data set for the 2019-2020 Academic Year and am in the process of writing scripts to clean the data and start to dive in a bit into what it says.