Unsupervised learning and clustering

Information is a key driver for any type of organization. However, with the rapid growth in the volume of data, valuable information may be hidden and go unnoticed due to the lack of effective data processing and analyzing mechanisms.

Clustering is an unsupervised learning mechanism that can find the hidden patterns and structures in data by finding data points that are similar to each other. No prelabeling is required. So, you can organize data using clustering with little or no human intervention.

For example, let's say you are given a collection of balls of different sizes without any category labels, such as big and small, attached to them; you should be able to categorize them using clustering by considering their attributes, such as radius and weight, for similarity.

In this chapter, you will learn how to use Apache Mahout to perform clustering using different algorithms.