Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/11119#discussion_r82489783
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/clustering/KMeansSuite.scala ---
@@ -137,18 +143,64 @@ 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)
+
+ 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 if K is unset") {
+ val kmeans = new KMeans()
+ val testNewK = 10
+ val randomModel = KMeansSuite.generateRandomKMeansModel(dim, testNewK)
+ assert(kmeans.setInitialModel(randomModel).getK === testNewK)
+ }
+
+ test("Initialize using a model with wrong K if K is set") {
+ val kmeans = new KMeans().setK(k).setSeed(1).setMaxIter(1)
+
+ val wrongKModel = KMeansSuite.generateRandomKMeansModel(3, k + 1)
+ val wrongKModelThrown = intercept[IllegalArgumentException] {
+ kmeans.setInitialModel(wrongKModel).fit(dataset)
--- End diff --
How about a user trains a model with inititalModel1, and then want to train
another one with initalModel2 with different k? For the first case, do we
really need to throw an error instead of warning?
---
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]
