This problem involves the OJ data set which is part of the ISLR package.

1. (a) Create a training set containing a random sample of 800 observations, and a test

   set containing the remaining observations. Make sure to use set.seed(1).

2. (b) (Please make sure to use set.seed(1) once again prior to each tune() operation, for parts (c) (d) as well.) Use tune() function to find the optimal support vector classifier with respect to cost value, using Purchase as the response and the other variables as predictors. Consider the following grid

of values for cost: 0.01, 0.05, 0.1, 0.5, 1, 10. Provide code and report both the training error and test error of the optimal selected model.

2

(c) Repeat part (b) using an SVM with a polynomial kernel with degree = 3.

4. (d) Repeat part (b) using an SVM with a radial kernel with default gamma value

   (gamma = 2).

5. (e) Which approach gave best results in terms of training error? Test error?