Data Science For Dummies, 3rd Edition

Chapter 5

Grouping Your Way into Accurate Predictions

IN THIS CHAPTER

Understanding the basics of clustering, classification, and other grouping algorithms

Clustering your data with the k-means algorithm and kernel density estimation

Choosing between decision trees and random forests

Getting to know hierarchical and neighborhood clustering algorithms

Working through nearest neighbor algorithms

When it comes to making predictions from data, grouping techniques can be a simple and powerful way to generate valuable insights quickly. Although grouping methods tend to be relatively simple, you can choose from quite a few approaches. In this chapter, I introduce you to classification, and clustering algorithms, as well as decision trees and random forests.

Data scientists use clustering to help them divide their unlabeled data into subsets. If they’re starting with labeled data, they can use classification methods to build predictive models that they can then use to forecast the classification ...