Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/12023#discussion_r57788687
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala
---
@@ -240,12 +250,66 @@ final class RandomForestClassificationModel
private[ml] (
private[ml] def toOld: OldRandomForestModel = {
new OldRandomForestModel(OldAlgo.Classification, _trees.map(_.toOld))
}
+
+ @Since("2.0.0")
+ override def write: MLWriter =
+ new
RandomForestClassificationModel.RandomForestClassificationModelWriter(this)
+
+ @Since("2.0.0")
+ override def read: MLReader =
+ new
RandomForestClassificationModel.RandomForestClassificationModelReader(this)
}
-private[ml] object RandomForestClassificationModel {
+@Since("2.0.0")
+object RandomForestClassificationModel extends
MLReadable[RandomForestClassificationModel] {
+
+
+ @Since("2.0.0")
+ override def load(path: String): RandomForestClassificationModel =
super.load(path)
+
+ private[RandomForestClassificationModel]
+ class RandomForestClassificationModelWriter(instance:
RandomForestClassificationModel)
+ extends MLWriter {
+
+ override protected def saveImpl(path: String): Unit = {
+ val extraMetadata: JObject = Map(
+ "numFeatures" -> instance.numFeatures,
+ "numClasses" -> instance.numClasses)
+ DefaultParamsWriter.saveMetadata(instance, path, sc,
Some(extraMetadata))
+ for(treeIndex <- 1 to instance.getNumTrees) {
--- End diff --
Ok thanks--that should be much more efficient.
---
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]
