Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/5761#discussion_r29295784
--- Diff: core/src/main/scala/org/apache/spark/rdd/RDD.scala ---
@@ -407,12 +407,28 @@ abstract class RDD[T: ClassTag](
val sum = weights.sum
val normalizedCumWeights = weights.map(_ / sum).scanLeft(0.0d)(_ + _)
normalizedCumWeights.sliding(2).map { x =>
- new PartitionwiseSampledRDD[T, T](
- this, new BernoulliCellSampler[T](x(0), x(1)), true, seed)
+ randomSampleWithRange(x(0), x(1), seed)
}.toArray
}
/**
+ * Internal method exposed for Random Splits in DataFrames. Samples an
RDD given a probability
+ * range.
+ * @param lb lower bound to use for the Bernoulli sampler
+ * @param ub upper bound to use for the Bernoulli sampler
+ * @param seed the seed for the Random number generator
+ * @return A random sub-sample of the RDD without replacement.
+ */
+ private[spark] def randomSampleWithRange(lb: Double, ub: Double, seed:
Long): RDD[T] = {
+ val random = new Random(seed)
+ this.mapPartitions { partition =>
+ val sampler = new BernoulliCellSampler[T](lb, ub)
+ sampler.setSeed(random.nextLong)
--- End diff --
add the partition id here so each partition has its own seed
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
