Github user MechCoder commented on a diff in the pull request:
https://github.com/apache/spark/pull/13650#discussion_r68985017
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala
---
@@ -168,15 +173,39 @@ class RandomForestRegressionModel private[ml] (
// Note: We may add support for weights (based on tree performance)
later on.
private lazy val _treeWeights: Array[Double] =
Array.fill[Double](_trees.length)(1.0)
+ @Since("2.1.0")
+ /** @group getParam */
+ def setVarianceCol(value: String): this.type = set(varianceCol, value)
+
@Since("1.4.0")
override def treeWeights: Array[Double] = _treeWeights
override protected def transformImpl(dataset: Dataset[_]): DataFrame = {
val bcastModel = dataset.sparkSession.sparkContext.broadcast(this)
+
+ var output = dataset
+
val predictUDF = udf { (features: Any) =>
bcastModel.value.predict(features.asInstanceOf[Vector])
}
- dataset.withColumn($(predictionCol), predictUDF(col($(featuresCol))))
+ val predictions = predictUDF(col($(featuresCol)))
+ output = dataset.withColumn($(predictionCol), predictions)
+
+ val varianceUDF = udf { (features: Any) =>
+ val leafNodes =
bcastModel.value.returnLeafNodes(features.asInstanceOf[Vector])
+ leafNodes.map { leafNode =>
--- End diff --
Nice! I'll address this for the `RandomForest` here and we can move the
decision tree test strengthening to another PR.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
