Github user hhbyyh commented on a diff in the pull request:
https://github.com/apache/spark/pull/12118#discussion_r58312723
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala
---
@@ -236,12 +255,66 @@ 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)
}
-private[ml] object RandomForestClassificationModel {
+@Since("2.0.0")
+object RandomForestClassificationModel extends
MLReadable[RandomForestClassificationModel] {
+
+ @Since("2.0.0")
+ override def read: MLReader[RandomForestClassificationModel] =
+ new RandomForestClassificationModelReader
+
+ @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 = {
+ // Note: numTrees is not currently used, but could be nice to store
for fast querying.
+ val extraMetadata: JObject = Map(
+ "numFeatures" -> instance.numFeatures,
+ "numClasses" -> instance.numClasses,
+ "numTrees" -> instance.getNumTrees)
+ EnsembleModelReadWrite.saveImpl(instance, path, sqlContext,
extraMetadata)
+ }
+ }
+
+ private class RandomForestClassificationModelReader
+ extends MLReader[RandomForestClassificationModel] {
+
+ /** Checked against metadata when loading model */
+ private val className =
classOf[RandomForestClassificationModel].getName
+ private val treeClassName =
classOf[DecisionTreeClassificationModel].getName
+
+ override def load(path: String): RandomForestClassificationModel = {
+ implicit val format = DefaultFormats
+ val (metadata: Metadata, treesData: Array[(Metadata, Node)]) =
+ EnsembleModelReadWrite.loadImpl(path, sqlContext, className,
treeClassName)
+ val numFeatures = (metadata.metadata \ "numFeatures").extract[Int]
+ val numClasses = (metadata.metadata \ "numClasses").extract[Int]
+
--- End diff --
just IMO, maybe check numTrees == trees.length since there's redundant
information.
---
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]
