Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/11119#discussion_r83521481
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/clustering/KMeansSuite.scala ---
@@ -137,18 +143,69 @@ class KMeansSuite extends SparkFunSuite with
MLlibTestSparkContext with DefaultR
assert(model.clusterCenters === model2.clusterCenters)
}
val kmeans = new KMeans()
- testEstimatorAndModelReadWrite(kmeans, dataset,
KMeansSuite.allParamSettings, checkModelData)
+ testEstimatorAndModelReadWrite(kmeans, dataset,
KMeansSuite.allParamSettings, checkModelData,
+ Map("initialModel" -> (checkModelData _).asInstanceOf[(Any, Any) =>
Unit]))
+ }
+
+ test("Initialize using a trained model") {
+ val kmeans = new KMeans().setK(k).setSeed(1).setMaxIter(1)
+ val oneIterModel = kmeans.fit(dataset)
+ val twoIterModel = kmeans.copy(ParamMap(ParamPair(kmeans.maxIter,
2))).fit(dataset)
+ val oneMoreIterModel =
kmeans.setInitialModel(oneIterModel).fit(dataset)
+
+ assert(oneMoreIterModel.getK === k)
+
+ twoIterModel.clusterCenters.zip(oneMoreIterModel.clusterCenters)
+ .foreach { case (center1, center2) => assert(center1 ~== center2
absTol 1E-8) }
+ }
+
+ test("Initialize using a model with wrong dimension of cluster centers")
{
+ val kmeans = new KMeans().setK(k).setSeed(1).setMaxIter(1)
+
+ val wrongDimModel = KMeansSuite.generateRandomKMeansModel(4, k)
+ val wrongDimModelThrown = intercept[IllegalArgumentException] {
+ kmeans.setInitialModel(wrongDimModel).fit(dataset)
+ }
+ assert(wrongDimModelThrown.getMessage.contains("mismatched dimension"))
+ }
+
+ test("Infer K from an initial model") {
+ val kmeans = new KMeans().setK(5)
+ val testNewK = 10
+ val randomModel = KMeansSuite.generateRandomKMeansModel(dim, testNewK)
+ assert(kmeans.setInitialModel(randomModel).getK === testNewK)
+
+ val differentKRandomModel = KMeansSuite.generateRandomKMeansModel(dim,
testNewK + 1)
+ assert(kmeans.setInitialModel(differentKRandomModel).getK === testNewK
+ 1)
--- End diff --
I don't see what this does. Seems to test exactly the same thing as above.
I think we should add a test case to first set `k` then set `initialModel` with
a different `k`, then check if `getK === initialModelK`. To make sure we
override the first one.
---
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
