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

sum_count = (
  pdata.map(lambda x: (x.a, [x.num, 1]))
    .reduceByKey(lambda x, y:
		  [x[0] + y[0], x[1] + y[1]])
    .collect())
[(x[0], float(x[1][0]) / x[1][1]) for x in sum_count]