http://stackoverflow.com/questions/40549443

answer.scala

val input = sc.parallelize(Seq(
  (43.45, 19840, "A345", Seq("2014-12-26", "2013-12-12"), Seq("232323","45466"), Seq("123", "234")),
  (43.45, 19840, "A345", Seq("2010-03-16", "2013-16-12"), Seq("34343","45454"), Seq("345", "456"))
)).toDF("amt", "id", "num", "start_date", "identifier", "another_column")

val zipArrays = udf { seqs: Seq[Seq[String]] =>
  for(i <- seqs.head.indices) yield seqs.fold(Seq.empty)((accu, seq) => accu :+ seq(i))
}

val columnsToSelect = Seq($"amt", $"id", $"num")
val columnsToZip = Seq($"start_date", $"identifier", $"another_column")
val outputColumns = columnsToSelect ++ columnsToZip.zipWithIndex.map { case (column, index) =>
  $"col".getItem(index).as(column.toString())
}

val output = input.select($"amt", $"id", $"num", explode(zipArrays(array(columnsToZip: _*)))).select(outputColumns: _*)

output.show()

/*
+-----+-----+----+----------+----------+--------------+
|  amt|   id| num|start_date|identifier|another_column|
+-----+-----+----+----------+----------+--------------+
|43.45|19840|A345|2014-12-26|    232323|           123|
|43.45|19840|A345|2013-12-12|     45466|           234|
|43.45|19840|A345|2010-03-16|     34343|           345|
|43.45|19840|A345|2013-16-12|     45454|           456|
+-----+-----+----+----------+----------+--------------+
*/