Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/11119#discussion_r77834310
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/clustering/KMeansSuite.scala ---
@@ -139,16 +146,61 @@ class KMeansSuite extends SparkFunSuite with
MLlibTestSparkContext with DefaultR
val kmeans = new KMeans()
testEstimatorAndModelReadWrite(kmeans, dataset,
KMeansSuite.allParamSettings, checkModelData)
}
+
+ test("Initialize using given cluster centers") {
+ 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 wrong model") {
+ val kmeans = new KMeans().setK(k).setSeed(1).setMaxIter(10)
+ val wrongTypeModel = new KMeansSuite.MockModel()
+
assert(!kmeans.setInitialModel(wrongTypeModel).isSet(kmeans.initialModel))
+
+ val wrongKModel = KMeansSuite.generateKMeansModel(3, k + 1)
+ intercept[IllegalArgumentException] {
+ kmeans.setInitialModel(wrongKModel).fit(dataset)
+ }
+
+ val wrongDimModel = KMeansSuite.generateKMeansModel(4, k)
+ intercept[IllegalArgumentException] {
+ kmeans.setInitialModel(wrongDimModel).fit(dataset)
+ }
+ }
}
object KMeansSuite {
+
+ class MockModel(override val uid: String) extends Model[MockModel] {
+
+ def this() = this(Identifiable.randomUID("mockModel"))
+
+ override def copy(extra: ParamMap): MockModel = throw new
NotImplementedError()
+
+ override def transform(dataset: Dataset[_]): DataFrame = throw new
NotImplementedError()
+
+ override def transformSchema(schema: StructType): StructType = throw
new NotImplementedError()
+ }
+
def generateKMeansData(spark: SparkSession, rows: Int, dim: Int, k:
Int): DataFrame = {
val sc = spark.sparkContext
val rdd = sc.parallelize(1 to rows).map(i =>
Vectors.dense(Array.fill(dim)((i % k).toDouble)))
- .map(v => new TestRow(v))
+ .map(v => TestRow(v))
spark.createDataFrame(rdd)
}
+ def generateKMeansModel(dim: Int, k: Int, seed: Int = 42): KMeansModel =
{
--- End diff --
can we call it `generateRandomKMeansModel`?
---
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
