The Naive Bayes model is one of the most efficient and effective learning algorithms, particularly in the field of text classification. Although over-simplistic, this model has worked out quite well. In this section, we are going to discuss the following topics:
What is a Naive Bayes model?
Why does it even work?
Types of Naive Bayes models
Before discussing the Naive Bayes model, let's first discuss about the Bayesian classifier. A Bayesian classifier is a probabilistic classifier that uses the Bayes theorem to predict a class. Let c be a class and be a set of features. Then, the probability of the features belonging to class c, that is , can be computed using the Bayes theorem as follows:
So, for a given set of features, the output class can be predicted as follows:
Here, P(c) is the prior probability of the class c and is the likelihood of X given c. If X were an univariate feature, then computing would be , which is easier to compute. However, in the case of multivariate...