Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/4951#discussion_r26062595
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala ---
@@ -58,4 +65,49 @@ class KMeansModel (val clusterCenters: Array[Vector])
extends Serializable {
private def clusterCentersWithNorm: Iterable[VectorWithNorm] =
clusterCenters.map(new VectorWithNorm(_))
+
+ override def save(sc: SparkContext, path: String): Unit = {
+ KMeansModel.SaveLoadV1_0.save(sc, this, path)
+ }
+
+ override protected def formatVersion: String = "1.0"
+}
+
+object KMeansModel extends Loader[KMeansModel] {
+ override def load(sc: SparkContext, path: String): KMeansModel = {
+ KMeansModel.SaveLoadV1_0.load(sc, path)
+ }
+
+ private[clustering]
+ object SaveLoadV1_0 {
+
+ private val thisFormatVersion = "1.0"
+
+ private[clustering]
+ val thisClassName = "org.apache.spark.mllib.clustering.KMeansModel"
+
+ def save(sc: SparkContext, model: KMeansModel, path: String): Unit = {
+ val sqlContext = new SQLContext(sc)
+ val wrapper = new VectorUDT()
+ val metadata = compact(render(
+ ("class" -> thisClassName) ~ ("version" -> thisFormatVersion) ~
("k" -> model.k)))
+ sc.parallelize(Seq(metadata),
1).saveAsTextFile(Loader.metadataPath(path))
+ val dataRDD =
sc.parallelize(model.clusterCenters).map(wrapper.serialize)
--- End diff --
* We don't need `wrapper.serialize` for vectors.
* We need to store cluster indices. If the centers are saved to more than
one partitions, we cannot easily load them back in the original order.
---
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
