By theory I know that Naive Bayes Classifier is a linear one, but when I implemented the decision boundary it was a curve (not linear as shown below). Is there any explanation why this is happening? or Are there any reasons to make Naive Bayes nonlinear?

Here is the code

from sklearn.naive_bayes import GaussianNB

classifier = GaussianNB()

classifier.fit(X_train, y_train)

y_pred = classifier.predict(X_test)

enter image description here

  • $\begingroup$ What implementation of NB did you use? $\endgroup$ Jun 5, 2019 at 3:49
  • $\begingroup$ I have edited the question with the code I used $\endgroup$ Jun 5, 2019 at 3:55


Browse other questions tagged or ask your own question.