def time[A](f: ⇒ A) = {
    val s = System.nanoTime
    val ret = f
    println("time: " + (System.nanoTime - s) / 1e9 + " seconds")
    ret
}

import org.apache.spark.sql.DataFrame
def materialize(df: DataFrame, tempStorage: String = "hdfs:///spark/tmp") = {
   df.write.mode("overwrite").parquet(tempStorage)
   spark.read.parquet(tempStorage)
}