As part of each of the Watson Analytics projects thus far in this book, we have always taken a moment to review or peek at the data we will be loading into Watson and ultimately be working with (for example, in the previous chapter, we covered this in the Gathering and reviewing of data section).
It's an important step in any project, even if the peek is simply a conversation with the data provider about some background and what might be expected to be in the file.
Here is what we should know in this project.
Football is one sport that is rich in data. From game results, betting/bookmaking, fantasy football leagues to the NFL Combine, the sport is overflowing with data. Let's look at the combine (as a data source).
The NFL Scouting Combine is a week-long showcase occurring every February, where college football players perform physical and mental tests in front of National Football League coaches, general managers, and scouts. With increasing interest in the NFL Draft, the scouting combine has grown in scope and significance, allowing personnel directors to evaluate upcoming prospects in a standardized setting (Wikipedia, 2018).
In this project, we are expecting to be supplied with data on prospective players who have participated in combine workouts, with statistics that include results by player for the following activities:
- 40-yard dash
- Bench press
- Vertical jump
- Broad jump
- 3-cone drill
- Shuttle run
In addition to this data, we'll expect to see some supplemental data based upon the player's physical attributes such as height, weight, arm length, and hand size, as well as statistics from the player's college and possibly even high school careers.
The following is a portion of our data source:
We could expect that if our team is looking to recruit for the wide receiver (WR) position, we may not be interested in a prospect's body weight, but height may be important; and perhaps a prospect's recorded time in the 40-yard dash may outshine their performance in the bench press drill. Remember, these are only suspicions—based upon an individual's personal feelings—not on data. That's where Watson Analytics can help, so read on!
The preceding table seems to be a pretty sufficient peek at the data, so let us move on now and get going with the next step in the project!