Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/21081#discussion_r181846789
--- Diff: mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala
---
@@ -123,8 +128,15 @@ class KMeansModel private[ml] (
@Since("2.0.0")
override def transform(dataset: Dataset[_]): DataFrame = {
transformSchema(dataset.schema, logging = true)
- val predictUDF = udf((vector: Vector) => predict(vector))
- dataset.withColumn($(predictionCol), predictUDF(col($(featuresCol))))
+ // val predictUDF = udf((vector: Vector) => predict(vector))
+ if (dataset.schema($(featuresCol)).dataType.equals(new VectorUDT)) {
--- End diff --
tip: This can be more succinct if written as:
```
val predictUDF = if (dataset.schema(...).dataType.equals(...)) { A } else {
B }
dataset.withColumn($(predictionCol), predictUDF(col($(featuresCol)))) //
so this line is only written once
```
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
