1 files changed, 19 insertions, 3 deletions
diff --git a/mllib/src/test/scala/org/apache/spark/ml/clustering/KMeansSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/clustering/KMeansSuite.scala
index c684bc11cc..2ca386e422 100644
--- a/mllib/src/test/scala/org/apache/spark/ml/clustering/KMeansSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/ml/clustering/KMeansSuite.scala
@@ -22,14 +22,14 @@ import org.apache.spark.ml.util.DefaultReadWriteTest
 import org.apache.spark.mllib.clustering.{KMeans => MLlibKMeans}
 import org.apache.spark.mllib.linalg.{Vector, Vectors}
 import org.apache.spark.mllib.util.MLlibTestSparkContext
-import org.apache.spark.sql.{DataFrame, SQLContext}
+import org.apache.spark.sql.{DataFrame, Dataset, SQLContext}
 
 private[clustering] case class TestRow(features: Vector)
 
 class KMeansSuite extends SparkFunSuite with MLlibTestSparkContext with DefaultReadWriteTest {
 
   final val k = 5
-  @transient var dataset: DataFrame = _
+  @transient var dataset: Dataset[_] = _
 
   override def beforeAll(): Unit = {
     super.beforeAll()
@@ -82,7 +82,7 @@ class KMeansSuite extends SparkFunSuite with MLlibTestSparkContext with DefaultR
     }
   }
 
-  test("fit & transform") {
+  test("fit, transform, and summary") {
     val predictionColName = "kmeans_prediction"
     val kmeans = new KMeans().setK(k).setPredictionCol(predictionColName).setSeed(1)
     val model = kmeans.fit(dataset)
@@ -99,6 +99,22 @@ class KMeansSuite extends SparkFunSuite with MLlibTestSparkContext with DefaultR
     assert(clusters === Set(0, 1, 2, 3, 4))
     assert(model.computeCost(dataset) < 0.1)
     assert(model.hasParent)
+
+    // Check validity of model summary
+    val numRows = dataset.count()
+    assert(model.hasSummary)
+    val summary: KMeansSummary = model.summary
+    assert(summary.predictionCol === predictionColName)
+    assert(summary.featuresCol === "features")
+    assert(summary.predictions.count() === numRows)
+    for (c <- Array(predictionColName, "features")) {
+      assert(summary.predictions.columns.contains(c))
+    }
+    assert(summary.cluster.columns === Array(predictionColName))
+    val clusterSizes = summary.clusterSizes
+    assert(clusterSizes.length === k)
+    assert(clusterSizes.sum === numRows)
+    assert(clusterSizes.forall(_ >= 0))
   }
 
   test("read/write") {