Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/4951#discussion_r26173165
--- Diff:
mllib/src/test/scala/org/apache/spark/mllib/clustering/KMeansSuite.scala ---
@@ -257,6 +258,54 @@ class KMeansSuite extends FunSuite with
MLlibTestSparkContext {
assert(predicts(0) != predicts(3))
}
}
+
+ test("model save/load") {
+ val tempDir = Utils.createTempDir()
+ val path = tempDir.toURI.toString
+
+ Array(true, false).foreach { case selector =>
+ val model = KMeansSuite.createModel(10, 3, selector)
+ // Save model, load it back, and compare.
+ try {
+ model.save(sc, path)
+ val sameModel = KMeansModel.load(sc, path)
+ KMeansSuite.checkEqual(model, sameModel, selector)
+ } finally {
+ Utils.deleteRecursively(tempDir)
+ }
+ }
+ }
+}
+
+object KMeansSuite extends FunSuite {
+ def createModel(dim: Int, k: Int, isSparse: Boolean): KMeansModel = {
+ val singlePoint = isSparse match {
+ case true =>
+ Vectors.sparse(dim, Array.empty[Int], Array.empty[Double])
+ case _ =>
+ Vectors.dense(Array.fill[Double](dim)(0.0))
+ }
+ new KMeansModel(Array.fill[Vector](k)(singlePoint))
+ }
+
+ def checkEqual(a: KMeansModel, b: KMeansModel, isSparse: Boolean): Unit
= {
+ assert(a.k === b.k)
+ isSparse match {
+ case true =>
--- End diff --
I suggest removing `isSparse` and using the following:
~~~scala
a.clusterCenters.zip(b.clusterCenters).foreach {
case (ca: SparseVector, cb: SparseVector) =>
assert(ca === cb)
case (ca: DenseVector, cb: DenseVector) =>
assert(ca === cb)
case _ =>
throw ...
}
~~~
---
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]
