Derive multiple columns from a single column in a Spark DataFrame

Question

I have a DF with a huge parseable metadata as a single string column in a Dataframe, lets call it DFA, with ColmnA.

I would like to break this column, ColmnA into mu

Answer 1

I opted to create a function to flatten one column and then just call it simultaneously with the udf.

First define this:

implicit class DfOperations(df: DataFrame) {

  def flattenColumn(col: String) = {
    def addColumns(df: DataFrame, cols: Array[String]): DataFrame = {
      if (cols.isEmpty) df
      else addColumns(
        df.withColumn(col + "_" + cols.head, df(col + "." + cols.head)),
        cols.tail
      )
    }

    val field = df.select(col).schema.fields(0)
    val newCols = field.dataType.asInstanceOf[StructType].fields.map(x => x.name)

    addColumns(df, newCols).drop(col)
  }

  def withColumnMany(colName: String, col: Column) = {
    df.withColumn(colName, col).flattenColumn(colName)
  }

}

Then usage is very simple:

case class MyClass(a: Int, b: Int)

val df = sc.parallelize(Seq(
  (0),
  (1)
)).toDF("x")

val f = udf((x: Int) => MyClass(x*2,x*3))

df.withColumnMany("test", f($"x")).show()

//  +---+------+------+
//  |  x|test_a|test_b|
//  +---+------+------+
//  |  0|     0|     0|
//  |  1|     2|     3|
//  +---+------+------+