Github user srowen commented on a diff in the pull request: https://github.com/apache/spark/pull/2455#discussion_r18124383 --- Diff: core/src/main/scala/org/apache/spark/util/random/RandomSampler.scala --- @@ -53,56 +81,237 @@ trait RandomSampler[T, U] extends Pseudorandom with Cloneable with Serializable * @tparam T item type */ @DeveloperApi -class BernoulliSampler[T](lb: Double, ub: Double, complement: Boolean = false) +class BernoulliPartitionSampler[T](lb: Double, ub: Double, complement: Boolean = false) extends RandomSampler[T, T] { - private[random] var rng: Random = new XORShiftRandom + // epsilon slop to avoid failure from floating point jitter + @transient val eps: Double = RandomSampler.epsArgs + require(lb <= (ub + eps), "Lower bound (lb) must be <= upper bound (ub)") + require(lb >= (0d - eps), "Lower bound (lb) must be >= 0.0") + require(ub <= (1d + eps), "Upper bound (ub) must be <= 1.0") - def this(ratio: Double) = this(0.0d, ratio) + private val rng: Random = new XORShiftRandom override def setSeed(seed: Long) = rng.setSeed(seed) override def sample(items: Iterator[T]): Iterator[T] = { - items.filter { item => - val x = rng.nextDouble() - (x >= lb && x < ub) ^ complement + ub-lb match { --- End diff -- I believe someone else made this same comment elsewhere, but, is it not faster and maybe as clear to write `rng.nextDouble() <= ub - lb`? There is no need for conditionals.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org