Using Clustering to Subdivide Data
IN THIS CHAPTER
Understanding the basics of clustering
Clustering your data with the k-means algorithm and kernel density estimation
Getting to know hierarchical and neighborhood clustering algorithms
Checking out decision tree and random forest algorithms
Data scientists use clustering to help them divide their unlabeled data into subsets. The basics behind clustering are relatively easy to understand, but things get tricky fast when you get into using some of the more advanced algorithms. In this chapter, I introduce the basics behind clustering. I follow that by introducing several nuanced algorithms that offer clustering solutions to meet your requirements, based on the specific characteristics of your feature dataset.
Introducing Clustering Basics
To grasp advanced methods for use in clustering your data, you should first take a few moments to make sure you have a firm understanding of the basics that underlie all forms of clustering. Clustering is a form of machine learning — the machine in this case is your computer, and learning ...