Drop links or images here to add them to the editor.

Predict the number of applications received using all other variables in the College data set.

plot

The dataset, available in the ISLR2 library, contains statistics for a large number of US Colleges. It has 777 observations and 18 variables.

dim(College)
[1] 777  18

Questions

Create a 70-30 train-test split of the College data set. Use a seed value of 1. Store the numeric vector with training data indices in train.idx.
Fit a regression tree on the training data with Apps as dependent variable and all other variables as independent variables. Store the model in the variable tree.college.
Perform cross-validation to determine the optimal level of tree complexity. Use a seed value of 1. Store the model in the variable cv.college.
Interpret the results and store the optimal number of nodes in the variable size.cv.
(note: try to avoid hardcoding and use e.g. the which.min() function to find the index of the tree size with the lowest value for the dev attribute)
Prune the tree to obtain the desired number of nodes size.cv. Store the model in the variable prune.college.
Use the pruned tree to make predictions on the test set. Store the predictions in the variable yhat.
Finally, calculate the test set MSE. Store the result in the variable mse.

Assume that: