Github user viirya commented on a diff in the pull request: https://github.com/apache/spark/pull/19229#discussion_r140678574 --- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/Imputer.scala --- @@ -223,20 +223,18 @@ class ImputerModel private[ml] ( override def transform(dataset: Dataset[_]): DataFrame = { transformSchema(dataset.schema, logging = true) - var outputDF = dataset val surrogates = surrogateDF.select($(inputCols).map(col): _*).head().toSeq - $(inputCols).zip($(outputCols)).zip(surrogates).foreach { + val newCols = $(inputCols).zip($(outputCols)).zip(surrogates).map { case ((inputCol, outputCol), surrogate) => val inputType = dataset.schema(inputCol).dataType val ic = col(inputCol) - outputDF = outputDF.withColumn(outputCol, - when(ic.isNull, surrogate) + when(ic.isNull, surrogate) --- End diff -- This `when` is not a call of previous line. I think it doesn't need to indent?
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org