Lab week 13

In this lab, we will explore how to use SVM models. We will start by using the Khan data set from the ISLR package.

library(ISLR)
library(tidymodels)

Khan_train <- data.frame(x = Khan$xtrain, y = as.factor(Khan$ytrain))
Khan_test <- data.frame(x = Khan$xtest, y = Khan$ytest)

We will fit a linear SVM on the training data set and predict the test data set. What do we expect the performance to be on the training and testing data set?

Next, we will switch to the Carseats and try to predict whether a store is located in the US or not. We will tune some of the arguments to get a good fit.