Randomly shuffle column in Spark RDD or dataframe

Question

Is there anyway I can shuffle a column of an RDD or dataframe such that the entries in that column appear in random order? I\'m not sure which APIs I could use to accomplish

Answer 1

What about selecting the column to shuffle, orderBy(rand) the column and zip it by index to the existing dataframe?

import org.apache.spark.sql.functions.rand

def addIndex(df: DataFrame) = spark.createDataFrame(
  // Add index
  df.rdd.zipWithIndex.map{case (r, i) => Row.fromSeq(r.toSeq :+ i)},
  // Create schema
  StructType(df.schema.fields :+ StructField("_index", LongType, false))
)

case class Entry(name: String, salary: Double)

val r1 = Entry("Max", 2001.21)
val r2 = Entry("Zhang", 3111.32)
val r3 = Entry("Bob", 1919.21)
val r4 = Entry("Paul", 3001.5)

val df = addIndex(spark.createDataFrame(Seq(r1, r2, r3, r4)))
val df_shuffled = addIndex(df
  .select(col("salary").as("salary_shuffled"))
  .orderBy(rand))

df.join(df_shuffled, Seq("_index"))
  .drop("_index")
  .show(false) 

+-----+-------+---------------+
|name |salary |salary_shuffled|
+-----+-------+---------------+
|Max  |2001.21|3001.5         |
|Zhang|3111.32|3111.32        |
|Paul |3001.5 |2001.21        |
|Bob  |1919.21|1919.21        |
+-----+-------+---------------+