Chapter 4. Classification

	"It is a truth universally acknowledged, that a single man in possession of a good fortune, must be in want of a wife."
	--Jane Austen, Pride and Prejudice

In the previous chapter, we learned how to make numeric predictions using linear regression. The model we built was able to learn how the features of Olympic swimmers related to their weight and we were able to use the model to make a weight prediction for a new swimmer. As with all regression techniques, our output was a number.

Not all predictions demand a numeric solution, though—sometimes we want our predictions to be items. For example, we may want to predict which candidate a voter will back in an election. Or we may want to know which of several products a customer is likely to buy. In these cases, the outcome is a selection from one of a number of possible discrete options. We call these options classes, and models we'll build in this chapter are classifiers...