Let's compare bits of code between R and SAS that do the exact same thing. I've got a data set with lots of information about wines. The data is already split into 3 chunks; train, test, and score. I'd like to create several new variables for each of the eleven numeric variables that already exist … Continue reading More Fun Between R and SAS
Proc Fastclus Is Going to be Useful
This week in learning SAS we began working with Proc Fastlclus - a procedure to group data together by two or more variables. This is particularly useful for data that has little linear relationship. Once you've identified clusters it helps to find similar characteristics among the clusters to aid in predicting outcomes for other observations … Continue reading Proc Fastclus Is Going to be Useful
Carolina/Dook Round 1
On the eve of the first Carolina/Duke matchup I've updated my scatter plot of KenPom ratings. Carolina has improved in efficiency margin by about a point since the last check-in and Duke has slipped by roughly 1/2 a point. The difference between the two is 9.3 points in favor of the bad guys. And coincidentally … Continue reading Carolina/Dook Round 1
I’ll be Using SAS a Lot Soon
I find myself struggling with what to write about this week. But I've learned that at some point in the future I'll be using SAS mainly instead of R. So I suppose that learning to use SAS as part of MSBA is timely. I'll still need to use R for the dashboard report that I've … Continue reading I’ll be Using SAS a Lot Soon
NCAA Bball Update #3
Alright, it's time to really take this NCAA graphic to a new level. I don't know about all of you, but I'm most interested in winning the NCAA tournament pool at work. I came in third last year and it came down to the championship game for me. And while you could have zoomed in … Continue reading NCAA Bball Update #3
It’s all in how you look at it…
I mentioned SAS macros a couple of weeks ago and how I thought they'd be helpful. And they are, tremendously. But I don't think I understood when we were told, "they're kind of like function-lite." It was a little confusing because they have the structure of a function and they seemed to behave mostly like … Continue reading It’s all in how you look at it…
NCAA KenPom Efficiency Rankings Updated
I've updated my chart with the latest KenPom rankings AND I've now added the past NCAA Champions (2002-2018) as diamonds on the chart. It really stands out now that past champions have always had an efficiency margin of greater than 20 - or to the right of the green line. In fact, of the 17 … Continue reading NCAA KenPom Efficiency Rankings Updated
I’ve Made a Mistake
For anyone familiar with programming these words are said often, perhaps accompanied by some more colorful language. Such is the case while I learned to use PROC SQL in SAS. As I started I thought to myself, 'I've written hundreds of SQL queries this shouldn't be hard.' I honestly think I'd have been better off … Continue reading I’ve Made a Mistake
Even more NCAA Hoops Fun
In addition to the ncaahoopR package in R, I had also been working on building a plot using Ken Pomeroy's efficiency ratings. And voila! Here it is. Unfortunately, WordPress doesn't support the embedded interactive graphic. But if you visit my site on Plotly you'll get the full experience. What I've Done I've written an R … Continue reading Even more NCAA Hoops Fun
NCAA Hoops Analysis Just Got Easy!
I just came across a fantastic R package on Github by lbenz730 - ncaahoopR - that provides easy access to scraping NCAA Basketball stats from ESPN.com AND includes functions for a handful of automatic charts. I'll play around with this a little more but here's a taste of what can be done with a single … Continue reading NCAA Hoops Analysis Just Got Easy!
Analytics By Casey 