Choose one of David Robinson’s tidytuesday screencasts, watch the video, and summarise. https://www.youtube.com/channel/UCeiiqmVK07qhY-wvg3IZiZQ
You must follow the instructions below to get credits for this assignment.
The title of my screencast was Analyzing Simpsons Guest Stars and dialogue in R.
The screencast was published on August 30th, 2019.
Hint: What’s the source of the data; what does the row represent; how many observations?; what are the variables; and what do they mean? There is 1 integer data type and 5 character data types present in this screencast. The five character data types include number(episode number), production_code(production code for the episode), episode_title(title of the episode), guest_star(Guest’s actual name), and role(role in the show, either a character or themselves). The only integer data type is season(season of the show). There are 1200 observations of six variables in this dataset. The rows each represent a guest star.
To import the data, Dave copied the dataset link from github.com, saved it as “Simpsons-guests”, and then pasted dataset link into a blank R code chunk. Dave then used the code “Simpsons%>% count(guest_star, sort = TRUE)” to filter the data by the amount of times each guest star has appeared on the show. By doing this, Dave learned that the top three most common guest stars were Marcia Wallace(156 appearances), Phil Hartman(52 appearances), and Joe Montegna(25 appearances). Dave then took it even further than that by filtering the data down even more by entering the code “Simpsons%>% count(guest_star, role, sort = TRUE)”, which filtered down how many times each fuest star has played a certain role. In doing this, Dave learned that out of Marcia Wallace’s 155 appearances, she played the role of Edna Krabappel in 154 of them.
Some things that I saw in the video that pertained to things we learned in class include loading data packages into R and filtering and sorting data in various types of datasets. Most of the stuff that Dave does in this video looks a bit tougher and more in depth than what we’ve done in class. Although this difference in knowledge of R, Dave does use some of the basic R functions that we’ve used in class before.
Because this screencast is talking about Simpsons characters, the data and information was not super helpful or useful to use to your advantage. However, Dave did provide some cool, little-known information on the show. What I though was the major finding from the analysis is that you were able to see what guest stars had the biggest roles in the show by number of appearances and lines. Side Show Bob and Troy Mcclure were two of the biggest guest stars in the Simpsons episodes.
The most interesting thing that I liked about this analysis was Daves use of different filtering strategies to really filter the data down to what he needed to see. Dave didn’t really need to know the episode number or season number, so he just filtered the dataset down to number of lines and number of appearances on the show. In doing this, Dave showed a great way to show only the information you really need to see.