O'Reilly logo

Practical Predictive Analytics by Ralph Winters

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Partitional clustering

This is also known as non-hierarchical clustering. In partitional clustering, each object is divided into smaller non-overlapping subsets (partition) that have similar characteristics. An observation can belong to one, and only one, cluster.

Here is a classic example of a three-cluster partitioned model. However, you may wonder why some of the yellow observations end up in the yellow group cluster, rather than the red group. That is because k-means has determined what the linear boundaries are for each of the clusters (right diagram), and any point that falls within any particular decision boundary is defined by the boundaries of that cluster:

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required