Drop duplicate columns on a dataframe in spark

spark_udf_dataframe_dropDuplicateCols.scala

import org.apache.spark.sql.DataFrame
import scala.annotation.tailrec

implicit class DataFrameOperations(df: DataFrame) {
  def dropDuplicateCols(rmvDF: DataFrame): DataFrame = {
    val cols = df.columns.groupBy(identity).mapValues(_.size).filter(_._2 > 1).keySet.toSeq

    @tailrec
    def deleteCol(df: DataFrame, cols: Seq[String]): DataFrame = {
      if (cols.size == 0) df else deleteCol(df.drop(rmvDF(cols.head)), cols.tail)
    }
    deleteCol(df, cols)
  }
}

val dupDF = rdd1.join(rdd2,"id").dropDuplicateCols(rdd1)

How is identity defined?