Custom UnaryTransformer

UpperTransformer.scala

import org.apache.spark.ml._
import org.apache.spark.ml.util.Identifiable
import org.apache.spark.sql.types._

val df = Seq(
  (0, "a"), (1, "b"),
  (2, "c"), (3, "a"),
  (4, "a"), (5, "c"))
  .toDF("label", "category")

class UpperTransformer(override val uid: String)
    extends UnaryTransformer[String, String, UpperTransformer] {

  def this() = this(Identifiable.randomUID("upper"))

  override protected def validateInputType(inputType: DataType): Unit = {
    require(inputType == StringType)
  }

  protected def createTransformFunc: String => String = {
    _.toUpperCase
  }

  protected def outputDataType: DataType = StringType
}

val upper = new UpperTransformer
//upper.setInputCol("text").transform(df).show
upper.setInputCol("category").transform(df).show