Github user jkbradley commented on a diff in the pull request: https://github.com/apache/spark/pull/4087#discussion_r26169291 --- Diff: mllib/src/test/scala/org/apache/spark/mllib/classification/NaiveBayesSuite.scala --- @@ -85,19 +90,87 @@ class NaiveBayesSuite extends FunSuite with MLlibTestSparkContext { assert(numOfPredictions < input.length / 5) } - test("Naive Bayes") { - val nPoints = 10000 + def validateModelFit( + piData: Array[Double], + thetaData: Array[Array[Double]], + model: NaiveBayesModel) = { + def closeFit(d1: Double, d2: Double, precision: Double): Boolean = { + (d1 - d2).abs <= precision + } + val modelIndex = (0 until piData.length).zip(model.labels.map(_.toInt)) + for (i <- modelIndex) { + assert(closeFit(math.exp(piData(i._2)), math.exp(model.pi(i._1)), 0.05)) + } + for (i <- modelIndex) { + for (j <- 0 until thetaData(i._2).length) { + assert(closeFit(math.exp(thetaData(i._2)(j)), math.exp(model.theta(i._1)(j)), 0.05)) + } + } + } - val pi = NaiveBayesSuite.smallPi - val theta = NaiveBayesSuite.smallTheta + test("Naive Bayes Multinomial") { + val nPoints = 1000 + val pi = Array(0.5, 0.1, 0.4).map(math.log) + val theta = 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 testData = NaiveBayesSuite.generateNaiveBayesInput( + pi, --- End diff -- For function calls, you can put multiple parameters in 1 line. (here and below)
--- 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