Gaussian Naive Bayes accounts for continuous features by calculating the conditional likelihood rather than conditional probability of an observation belonging to each class using the distribution of the features within each class. At a high level, separate distributions of a continuous feature are formed for each class, and a feature’s respective contribution to the class likelihood score for a given observation is found from the height of the density corresponding to that feature. It assigns prior class probabilities in the same fashion and maintains the assumption of independence between predators to compute the conditional likelihood of belonging to each class.
How are continuous features incorporated into Naive Bayes?
Help us improve this post by suggesting in comments below:
– modifications to the text, and infographics
– video resources that offer clear explanations for this question
– code snippets and case studies relevant to this concept
– online blogs, and research publications that are a “must read” on this topic
Partner Ad
