val pdata = sqlContext.load("/home/rxin/ints.parquet").select("a", "num")

val sum_count = pdata.map { row => (row.getInt(0), (row.getInt(1), 1)) }
  .reduceByKey { (a, b) =>
    (a._1 + b._1, a._2 + b._2)
  }.collect()

sum_count.foreach { case (a, (sum, count)) => println(s"$a: ${sum/count}") }