Sorting a Dataframe before writing it out in Spark to compare file sizes

build.sbt

lazy val root = (project in file("."))
  .settings(
    name := "Scala",
    libraryDependencies += "org.apache.spark" %% "spark-sql" % "3.3.0",
  )

RLESpark.scala

package main

import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.SaveMode

case class User(id: Int, `type`: String)

object Main {
  val spark = SparkSession
    .builder()
    .appName("Spark SQL basic example")
    .master("local[*]")
    .getOrCreate()
  def main(args: Array[String]): Unit = {
    val df = spark.createDataFrame(Stream.range(0, 10000).map(i => User(id=i, `type`=i%3 match {
        case 1 => "EXISTING"
        case 2 => "RETURNING"
        case default => "NEW"
    })))

    df.sort("type").write.mode(SaveMode.Overwrite).option("compression", "none").parquet("/tmp/sorted.parquet")
    df.write.mode(SaveMode.Overwrite).option("compression", "none").parquet("/tmp/unsorted.parquet")
  }
}