Github user zhengruifeng commented on a diff in the pull request: https://github.com/apache/spark/pull/12819#discussion_r79752969 --- Diff: mllib/src/test/scala/org/apache/spark/ml/classification/NaiveBayesSuite.scala --- @@ -150,6 +150,75 @@ class NaiveBayesSuite extends SparkFunSuite with MLlibTestSparkContext with Defa validateProbabilities(featureAndProbabilities, model, "multinomial") } + test("Naive Bayes Multinomial with weighted samples") { + val (dataset, weightedDataset) = { + val nPoints = 1000 + val piArray = Array(0.5, 0.1, 0.4).map(math.log) + val thetaArray = Array( + Array(0.70, 0.10, 0.10, 0.10), // label 0 + Array(0.10, 0.70, 0.10, 0.10), // label 1 + Array(0.10, 0.10, 0.70, 0.10) // label 2 + ).map(_.map(math.log)) + val pi = Vectors.dense(piArray) + val theta = new DenseMatrix(3, 4, thetaArray.flatten, true) + + val testData = generateNaiveBayesInput(piArray, thetaArray, nPoints, 42, "multinomial") + + // Let's over-sample the label-1 samples twice, label-2 samples triple. + val data1 = testData.flatMap { case labeledPoint: LabeledPoint => + labeledPoint.label match { + case 0.0 => Iterator(labeledPoint) + case 1.0 => Iterator(labeledPoint, labeledPoint) + case 2.0 => Iterator(labeledPoint, labeledPoint, labeledPoint) + } + } + + val rnd = new Random(8392) + val data2 = testData.flatMap { case LabeledPoint(label: Double, features: Vector) => --- End diff -- Good point. Of course, I will update this testsuite keep in line with other algorithms.
--- 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