Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/9849#discussion_r45438710
--- Diff: mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala
---
@@ -129,6 +131,52 @@ class KMeansModel private[ml] (
val data = dataset.select(col($(featuresCol))).map { case Row(point:
Vector) => point }
parentModel.computeCost(data)
}
+
+ @Since("1.6.0")
+ override def write: MLWriter = new KMeansModel.KMeansModelWriter(this)
+}
+
+@Since("1.6.0")
+object KMeansModel extends MLReadable[KMeansModel] {
+
+ @Since("1.6.0")
+ override def read: MLReader[KMeansModel] = new
AFTSurvivalRegressionModelReader
+
+ @Since("1.6.0")
+ override def load(path: String): KMeansModel = super.load(path)
+
+ /** [[MLWriter]] instance for [[KMeansModel]] */
+ private[KMeansModel] class KMeansModelWriter(instance: KMeansModel)
extends MLWriter {
+
+ private case class Data(clusterCenters: Array[Vector])
+
+ override protected def saveImpl(path: String): Unit = {
+ // Save metadata and Params
+ DefaultParamsWriter.saveMetadata(instance, path, sc)
+ // Save model data: cluster centers
+ val data = Data(instance.clusterCenters)
+ val dataPath = new Path(path, "data").toString
+
sqlContext.createDataFrame(Seq(data)).repartition(1).write.parquet(dataPath)
+ }
+ }
+
+ private class AFTSurvivalRegressionModelReader extends
MLReader[KMeansModel] {
--- End diff --
`KMeansModelReader`
---
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]
