Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/17117#discussion_r104092158
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/clustering/KMeansSuite.scala ---
@@ -22,22 +22,28 @@ import scala.util.Random
import org.apache.spark.SparkFunSuite
import org.apache.spark.ml.linalg.{Vector, Vectors}
import org.apache.spark.ml.param.ParamMap
-import org.apache.spark.ml.util.{DefaultReadWriteTest, MLTestingUtils}
-import org.apache.spark.mllib.clustering.{KMeans => MLlibKMeans}
+import org.apache.spark.ml.util.{DefaultReadWriteTest, Identifiable,
MLTestingUtils}
+import org.apache.spark.ml.util.TestingUtils._
+import org.apache.spark.mllib.clustering.{KMeans => MLlibKMeans,
KMeansModel => MLlibKMeansModel}
+import org.apache.spark.mllib.linalg.{Vectors => MLlibVectors}
import org.apache.spark.mllib.util.MLlibTestSparkContext
import org.apache.spark.sql.{DataFrame, Dataset, SparkSession}
private[clustering] case class TestRow(features: Vector)
class KMeansSuite extends SparkFunSuite with MLlibTestSparkContext with
DefaultReadWriteTest {
+ import testImplicits._
+
final val k = 5
@transient var dataset: Dataset[_] = _
+ @transient var rData: Dataset[_] = _
override def beforeAll(): Unit = {
super.beforeAll()
dataset = KMeansSuite.generateKMeansData(spark, 50, 3, k)
+ rData =
GaussianMixtureSuite.rData.map(GaussianMixtureSuite.FeatureData).toDF()
--- End diff --
`GaussianMixtureSuite.rData.map(Tuple1.apply).toDF()` ? Mapping the dummy
case class from another test suite is less clear.
---
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]
