concept exercise in category R

appears as: exercises, exercise, exercises
Machine Learning with R, the tidyverse, and mlr

This is an excerpt from Manning's book Machine Learning with R, the tidyverse, and mlr.

The scale argument controls whether the variables are divided by their standard deviations to put them all on the same scale as each other, and its default value is FALSE. There isn’t a clear consensus on whether you should standardize your variables before running PCA. A common rule of thumb is that if your original variables are measured on a similar scale, standardization isn’t necessary; but if you have one variable measuring grams and another measuring kilograms, you should standardize them by setting scale = TRUE to put them on the same scale. This is important because if you have one variable measured on a much larger scale, this variable will dominate the eigenvectors, and the other variables will contribute much less information to the principal components. In this example, we’ll set scale = TRUE, but one of the exercises for this chapter is to set scale = FALSE and compare the results.

Do the same as in exercise 2 again, but this time set the arguments center = FALSE and scale = TRUE.