Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/15721#discussion_r93891824
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/classification/NaiveBayesSuite.scala
---
@@ -157,50 +162,26 @@ class NaiveBayesSuite extends SparkFunSuite with
MLlibTestSparkContext with Defa
validateProbabilities(featureAndProbabilities, model, "multinomial")
}
- test("Naive Bayes Multinomial with weighted samples") {
- 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 testData = generateNaiveBayesInput(piArray, thetaArray, nPoints,
42, "multinomial").toDF()
- val (overSampledData, weightedData) =
- MLTestingUtils.genEquivalentOversampledAndWeightedInstances(testData,
- "label", "features", 42L)
- val nb = new NaiveBayes().setModelType("multinomial")
- val unweightedModel = nb.fit(weightedData)
- val overSampledModel = nb.fit(overSampledData)
- val weightedModel = nb.setWeightCol("weight").fit(weightedData)
- assert(weightedModel.theta ~== overSampledModel.theta relTol 0.001)
- assert(weightedModel.pi ~== overSampledModel.pi relTol 0.001)
- assert(unweightedModel.theta !~= overSampledModel.theta relTol 0.001)
- assert(unweightedModel.pi !~= overSampledModel.pi relTol 0.001)
- }
-
- test("Naive Bayes Bernoulli with weighted samples") {
- val nPoints = 10000
- val piArray = Array(0.5, 0.3, 0.2).map(math.log)
- val thetaArray = Array(
- Array(0.50, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02,
0.02, 0.40), // label 0
- Array(0.02, 0.70, 0.10, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02,
0.02, 0.02), // label 1
- Array(0.02, 0.02, 0.60, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02,
0.02, 0.30) // label 2
- ).map(_.map(math.log))
-
- val testData = generateNaiveBayesInput(piArray, thetaArray, nPoints,
42, "bernoulli").toDF()
- val (overSampledData, weightedData) =
- MLTestingUtils.genEquivalentOversampledAndWeightedInstances(testData,
- "label", "features", 42L)
- val nb = new NaiveBayes().setModelType("bernoulli")
- val unweightedModel = nb.fit(weightedData)
- val overSampledModel = nb.fit(overSampledData)
- val weightedModel = nb.setWeightCol("weight").fit(weightedData)
- assert(weightedModel.theta ~== overSampledModel.theta relTol 0.001)
- assert(weightedModel.pi ~== overSampledModel.pi relTol 0.001)
- assert(unweightedModel.theta !~= overSampledModel.theta relTol 0.001)
- assert(unweightedModel.pi !~= overSampledModel.pi relTol 0.001)
+ test("Naive Bayes with weighted samples") {
+ val numClasses = 3
+ def modelEquals(m1: NaiveBayesModel, m2: NaiveBayesModel): Unit = {
+ assert(m1.pi ~== m2.pi relTol 0.01)
+ assert(m1.theta ~== m2.theta relTol 0.01)
+ }
+ val testParams = Seq(
+ ("bernoulli", bernoulliDataset),
+ ("multinomial", dataset)
+ )
+ testParams.foreach { case (family, dataset) =>
+ // NaiveBayes is sensitive to constant scaling of the weights unless
smoothing is set to 0
+ val estimator = new
NaiveBayes().setSmoothing(0.0).setModelType(family)
--- End diff --
I think the test with smoothing as 0.0 is a nice check on the weighting
algorithm for Naive Bayes, so I prefer to keep it. I made separate smoothing/no
smoothing estimators.
---
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
