Author: R | JLaw's R Blog

Feed: R-bloggers. Author: R | JLaw's R Blog. [This article was first published on R | JLaw's R Blog, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here) Want to share your content on R-bloggers? click here if you have a blog, or here if you don't. In this fourth (and hopefully final) entry in my “Icing the Kicker” series of posts, I’m going to jump back to the first post where I used tidymodels to predict whether or not a kick attempt would be iced. However, this time I see if using ... Read More

Feed: R-bloggers. Author: R | JLaw's R Blog. [This article was first published on R | JLaw's R Blog, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here) Want to share your content on R-bloggers? click here if you have a blog, or here if you don't. In my last post I looked at the causal effect of icing the kicker using weighting. Those results found that icing the kicker had a non-significant effect on the success of the field goal attempt with a point estimate of -2.82% (CI: -5.88%, 0.50%). In this ... Read More

Feed: R-bloggers. Author: R | JLaw's R Blog. In my prior post I looked at when coaches were most likly to ice a kicker where ‘icing a kicker’ means for a defense to call a timeout right before the offense is about to kick a field goal. In this post, I’ll be looking to apply causal inference techniques to see whether icing the kicker even matters.In a perfect world we’d run an A/B test or some type of experiment where some games could be played with the ability to ice the kicker and some without. However, this is unfeasible because ... Read More

Feed: R-bloggers. Author: R | JLaw's R Blog. Normally, I would do some EDA to better understand the data set but in the interest of word count I’ll jump right into using tidymodels to predict whether or not a given field goal attempt will be iced. In order to make the data work with the XGBoost algorithm I’ll subset and convert some numeric variables including our dependent variable to factors. A frustrating thing I learned in writing this post is that with a factor dependent variable the assumption is that the first level is the positive class. I’m recoding is_iced ... Read More

Feed: R-bloggers. Author: R | JLaw's R Blog. [This article was first published on R | JLaw's R Blog, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here) Want to share your content on R-bloggers? click here if you have a blog, or here if you don't. In my previous post I looked at College Football Non-Conference games to create a network map overlaid on top of the United States using the {ggraph} package. In this post I’ll be extending that to examine Conference Realignment, which is when colleges change from one conference ... Read More

Feed: R-bloggers. Author: R | JLaw's R Blog. Exploring College Football Non-Conference Rivalries with {ggraph} | R-bloggers % count(from, to, first_team, second_team, name = 'weight') knitr::kable(head(edge_list, 5)) from to first_team second_team weight 2 23 Auburn San José State 2 2 97 Auburn Louisville 1 2 166 Auburn New Mexico State 1 2 228 Auburn Clemson 5 2 264 Auburn Washington 1 An interpretation of this first row is that Auburn played San Jose State twice between 2010 and 2019 and only played Louisville once. The {tidygraph} package has its own structure called a tbl_graph which combines the nodes and edges ... Read More

Feed: R-bloggers. Author: R | JLaw's R Blog. I love movies. I enjoy watching them, I enjoy reading about the industry (sometimes), and as a bit of a data-nerd (exhibit a: my blog), I enjoy learning about the outliers in the industry. One of my favorite trends to follow is the shifting dynamics of Hollywood being driven more by International Box Office and the impact this has on the types of movies being made. One of my favorite examples is the movie Warcraft. From a critical perspective the movie is not good sporting a Rotten Tomatoes score of 28% (although ... Read More

Feed: R-bloggers. Author: R | JLaw's R Blog. [This article was first published on R | JLaw's R Blog, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here) Want to share your content on R-bloggers? click here if you have a blog, or here if you don't. Since 1998, MTV’s The Challenge (formerly the Real World/Road Rules Challenge) has graced the airwaves where it is currently in Season 37. In a prior post I had mentioned that this is one of my guilty pleasure shows so this will likely not be the last ... Read More

Feed: R-bloggers. Author: R | JLaw's R Blog. [This article was first published on R | JLaw's R Blog, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here) Want to share your content on R-bloggers? click here if you have a blog, or here if you don't. I’m a big proponent of enabling the reading time option on this blog which uses Hugo’s academic theme. I always appreciate seeing it on other blogs so I know how much time to invest in the post. I also like it because its a feedback mechanism ... Read More

Feed: R-bloggers. Author: R | JLaw's R Blog. In the beginning of May, I used RSelenium to scrape the Google Play Store reviews for Instagram Lite to demonstrate how the package can be used to automate browser behavior. Its taken longer than I had initially planned to do this follow-up on the analysis of that data. But better late than never. So in this analysis I will do some exploratory work and some text mining to look at questions such as:The main libraries that I will use to do this analysis are udpipe for applying the language model used to ... Read More