Understanding clustering algorithms

One of the most common methods that fall within the category of UL is clustering analysis. The main idea behind clustering analysis is the grouping of data into two or more categories of a similar nature to form groups or clusters. Within this section, we will explore these different clustering models, and subsequently apply our knowledge in a real-world scenario concerning the development of predictive models for the detection of breast cancer. Let's go ahead and explore some of the most common clustering algorithms.

Exploring the different clustering algorithms

There exists not one, but a broad spectrum of clustering algorithms, each with its own approach to how to best cluster data depending on the dataset at hand. We can divide these clustering algorithms into two general categories: hierarchical and partitional clustering. We can see a graphical representation of this here:

Figure 6.2 – The two types...