Discovery breast cancer subtypes: unsupervised analysis
Materials for class on Monday, July 20, 2020
Contents
Slides
Action Items
Assignment 4
Plase read R for Data Science, Chapter 23. It will provide more background and supporting concepts for the supervised analysis that comes next.
Points of Reflection
How did we know k in the k-means algorithm? Or did we?
How well do our \(5\) subtypes line up with the \(5\) subtypes from Parker et al.?
With respect to the breast cancer dataset, what happens when you change the number of clusters to \(3\),\(4\), or \(10\) for example? What happens? And how does it compare again Parker et al.?
Please read Chapter 23