Naive Bayes Feature importance

Hi,

Does Matlab provide any function or attributes to get the importance of each feature for a Naice Bayes classifier. Preictor Importance does that for a decision tree, but I want for Naive Bayes.

Thanks.

Answer 1

[Gouri Chennuru]

Hi Shathesh

MATLAB has various functions and attributes defined for Naive Bayes Classifier.

ClassificationNaiveBayes is a naive Bayes classifier for multiclass learning. We can use fitcnb Train multiclass naive Bayes model. There are various properties, functions, inherted methods defined under this class. Categorical predictors, categorical levels, Misclassification cost, Kernal smoother types can also be updated.

There are many inbuilt methods like compact to compact naive Bayes classifier, crossval for Cross validating, resubEdge for Classification edge in naive Bayes classifiers by resubstitution, resubLoss for Classification loss in naive Bayes classifiers by resubstitution, resubMargin for Classification margins, resubPredict to Predict resubstitution labels.

Refer to this link for more information.

Hope this Helps !