Github user yanboliang commented on a diff in the pull request:
https://github.com/apache/spark/pull/13650#discussion_r70607457
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala
---
@@ -168,15 +173,37 @@ 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
+ private def predictVariance(features: Vector): Double = {
+ val meanSumOfPredictionsAndVariance = _trees.map { tree =>
+ val leafNode = tree.rootNode.predictImpl(features)
+ leafNode.impurityStats.calculate() + math.pow(leafNode.prediction, 2)
+ }.sum / getNumTrees
+ meanSumOfPredictionsAndVariance - math.pow(predict(features), 2)
+ }
+
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 predictVarianceUDF = udf { (features: Any) =>
+ bcastModel.value.predictVariance(features.asInstanceOf[Vector])
+ }
+ output = output.withColumn($(varianceCol),
predictVarianceUDF(col($(featuresCol))))
+ output.toDF
--- End diff --
Could we directly use ```output.withColumn($(varianceCol),
predictVarianceUDF(col($(featuresCol))))```?
---
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
