Github user srowen commented on a diff in the pull request: https://github.com/apache/spark/pull/3626#discussion_r21402810 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala --- @@ -65,6 +65,24 @@ class NaiveBayesModel private[mllib] ( override def predict(testData: Vector): Double = { labels(brzArgmax(brzPi + brzTheta * testData.toBreeze)) } + + def classProbabilities(testData: RDD[Vector]): + RDD[scala.collection.mutable.Map[Double, Double]] = { + val bcModel = testData.context.broadcast(this) + testData.mapPartitions { iter => + val model = bcModel.value + iter.map(model.classProbabilities) + } + } + + def classProbabilities(testData: Vector): scala.collection.mutable.Map[Double, Double] = { + val posteriors = (brzPi + brzTheta * testData.toBreeze) --- End diff -- These aren't quite the class probabilities as the expression doesn't have the probability of the evidence incorporated. This would work if you first normalized the probabilities to sum to 1.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org