From 66d6c74e75ba84fec0460723e4950b611723a909 Mon Sep 17 00:00:00 2001 From: Bhaskar Bharath Date: Wed, 7 Mar 2018 22:44:00 -0500 Subject: [PATCH] Documentaion for #10772 MultinomialNB alpha>0 --- doc/modules/naive_bayes.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/doc/modules/naive_bayes.rst b/doc/modules/naive_bayes.rst index b61637c12d87b..04dd2a960ae0c 100644 --- a/doc/modules/naive_bayes.rst +++ b/doc/modules/naive_bayes.rst @@ -127,7 +127,7 @@ in the training set :math:`T`, and :math:`N_{y} = \sum_{i=1}^{|T|} N_{yi}` is the total count of all features for class :math:`y`. -The smoothing priors :math:`\alpha \ge 0` accounts for +The smoothing priors :math:`\alpha > 0` accounts for features not present in the learning samples and prevents zero probabilities in further computations. Setting :math:`\alpha = 1` is called Laplace smoothing,