# Exercise $2$: Forward Selection

In class, our main focus on feature selection was using the idea of penalized regression implemented in tools such as glmnet, ridge, and lasso. This exercise will give you a feel for a stepwise feature selection tool.

While there are multiple version, this example will look at forward selection.

The following, $`$golf$2.$csv$`,$ data set contains various measurements on professional golfers. There are $3$ variables related to monetary compensation. Additionally, numerous attributes of the golfer are provided that can be lumped together in $2$ categories. Variables such as average drive and driving accuracy tells us a little bit about the golfers ability to hit the ball long range. Additional variables such as Greens, Average Putt, and Saves tell us how well the golf is with their "short game" when working on shots closer to the hole. Finally, there are some additional "mystery variables" with generic labeling.

$```\{$r$\}$

golf$<-$read.csv$("$GolfData$2.$csv$")$

#str$($golf$)$

names$($golf$)$

Explain Briefly whats going on this