Github user zhengruifeng commented on a diff in the pull request:
https://github.com/apache/spark/pull/21563#discussion_r197600500
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/evaluation/ClusteringEvaluator.scala
---
@@ -107,15 +106,18 @@ class ClusteringEvaluator @Since("2.3.0")
(@Since("2.3.0") override val uid: Str
@Since("2.3.0")
override def evaluate(dataset: Dataset[_]): Double = {
- SchemaUtils.checkColumnType(dataset.schema, $(featuresCol), new
VectorUDT)
+ SchemaUtils.validateVectorCompatibleColumn(dataset.schema,
$(featuresCol))
SchemaUtils.checkNumericType(dataset.schema, $(predictionCol))
+ val vectorCol = DatasetUtils.columnToVector(dataset, $(featuresCol))
+ val df = dataset.select(col($(predictionCol)),
--- End diff --
@mgaido91 I think it maybe nice to first add a name getter for column
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
