How can I use sklearn.naive_bayes with (multiple) categorical features?

Question

I want to learn a Naive Bayes model for a problem where the class is boolean (takes on one of two values). Some of the features are boolean, but other features are categorical a

Answer 1

1. CategoricalNB by scikit-learn is a new class to be added in the naive_bayes module. It's in the nightly build here.

2. Mixed Naive Bayes (https://github.com/remykarem/mixed-naive-bayes). It can assume a mix of Gaussian and categorical (multinoulli) distributions on the training data features. The library is written such that the APIs are similar to scikit-learn's.

from mixed_naive_bayes import MixedNB
X = [[0, 0],
     [1, 1],
     [2, 1],
     [1, 1],
     [0, 2]]
y = [0, 0, 1, 1, 0]
clf = MixedNB(categorical_features='all')
clf.fit(X,y)
clf.predict(X)

See my response in a similar question here https://stackoverflow.com/a/58428035/4570466.