Pros and cons
There is so much information that can be crammed into one chapter. The examples selected in this chapter do not do justice to the versatility and accuracy of the Naïve Bayes family of classifiers.
The Naïve Bayes algorithm is a simple and robust generative classifier that relies on prior conditional probabilities to extract a model from a training dataset. The Naïve Bayes model has its benefits, as mentioned here:
It is easy to implement and parallelize
It has a very low computational complexity: O((n+c)*m), where m is the number of features, c is the number of classes, and n is the number of observations
It handles missing data
It supports incremental updates, insertions, and deletions
However, Naïve Bayes is not a silver bullet. It has the following disadvantages:
It requires a large training set to achieve reasonable accuracy
The assumption of the independence of features is not practical in the real world
It requires dealing with the zero-frequency problem for counters
