DataFrame simple aggregation performance benchmark

df.py

data = sqlContext.load("/home/rxin/ints.parquet")
data.groupBy("a").agg(col("a"), avg("num")).collect()

df.scala

val data = sqlContext.load("/home/rxin/ints.parquet")
data.groupBy("a").agg(col("a"), avg("num")).collect()

generatedata.py

import random
from pyspark.sql import Row

data = sc.parallelize(xrange(1000)).flatMap(lambda x: [Row(a=random.randint(1, 10), num=random.randint(1, 100), str=("a" * random.randint(1, 30))) for i in xrange(10000)])
dataTable = sqlContext.createDataFrame(data)
dataTable.saveAsParquetFile("/home/rxin/ints.parquet")

rdd.py

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]

rdd.scala

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}") }

Here you can find some analysis of this benchmark and its code: http://0x0fff.com/spark-dataframes-are-faster-arent-they/

it is confusing , since in data science machine learning we need real life algorithms comparison. Take random forest from sci kit learn (not from spark ML very poor library) or deep neural network and run.