Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/21204#discussion_r185325228
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala
---
@@ -97,9 +97,10 @@ class DecisionTreeClassifier @Since("1.4.0") (
override def setSeed(value: Long): this.type = set(seed, value)
override protected def train(dataset: Dataset[_]):
DecisionTreeClassificationModel = {
+ val instr = Instrumentation.create(this, dataset)
val categoricalFeatures: Map[Int, Int] =
MetadataUtils.getCategoricalFeatures(dataset.schema($(featuresCol)))
- val numClasses: Int = getNumClasses(dataset)
+ val numClasses: Int = getNumClasses(dataset, instr =
OptionalInstrumentation.create(instr))
--- End diff --
Also see what else you can log easily (e.g., numFeatures)
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]