Chapter 9. Finding Groups of Data – Clustering with k-means

Have you ever spent time watching large crowds? As a sociologist, this was one of my favorite pastimes. I would choose a busy location, such as a coffee shop, library, or cafeteria, and observe the masses of people for interesting patterns of behavior. The goal was to look for details that reveal an insight into how people, as a general rule, relate to each other and their environment.

The more you perform such observational research, the more you may see recurring personalities. Perhaps a certain type of person, identified by a freshly-pressed suit and a briefcase, comes to typify the white-collar business executive. A twenty-something wearing tight jeans, a flannel shirt, and sunglasses might fall into the hipster category, while a woman unloading children from a minivan could be labeled a soccer mom.

Of course, these types of stereotypes are dangerous to apply to individuals—no two people are exactly alike. Used in aggregate, however...