Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/12118#discussion_r58296743
--- Diff: mllib/src/main/scala/org/apache/spark/ml/tree/treeModels.scala ---
@@ -358,3 +376,100 @@ private[ml] object DecisionTreeModelReadWrite {
finalNodes.head
}
}
+
+private[ml] object EnsembleModelReadWrite {
+
+ /**
+ * Helper method for saving a tree ensemble to disk.
+ *
+ * @param instance Tree ensemble model
+ * @param path Path to which to save the ensemble model.
+ * @param extraMetadata Metadata such as numFeatures, numClasses,
numTrees.
+ */
+ def saveImpl[M <: Params with TreeEnsembleModel](
+ instance: M,
+ path: String,
+ sql: SQLContext,
+ extraMetadata: JObject): Unit = {
+ DefaultParamsWriter.saveMetadata(instance, path, sql.sparkContext,
Some(extraMetadata))
+ val treesMetadataJson: Array[(Int, String)] =
instance.trees.zipWithIndex.map {
+ case (tree, treeID) =>
+ treeID ->
DefaultParamsWriter.getMetadataToSave(tree.asInstanceOf[Params],
sql.sparkContext)
+ }
+ val treesMetadataPath = new Path(path, "treesMetadata").toString
+ sql.createDataFrame(treesMetadataJson).toDF("treeID", "metadata")
+ .write.parquet(treesMetadataPath)
+ val dataPath = new Path(path, "data").toString
+ val nodeDataRDD =
sql.sparkContext.parallelize(instance.trees.zipWithIndex).flatMap {
--- End diff --
This is a single RDD. The flatMap maps every element of the original RDD
to multiple elements in a new RDD. It should be fine.
---
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
