From ce8ec5456169682f27f846e7b8d51e6c4bcf75e3 Mon Sep 17 00:00:00 2001 From: Holden Karau Date: Tue, 8 Apr 2014 18:15:52 -0700 Subject: Spark 1271: Co-Group and Group-By should pass Iterable[X] Author: Holden Karau Closes #242 from holdenk/spark-1320-cogroupandgroupshouldpassiterator and squashes the following commits: f289536 [Holden Karau] Fix bad merge, should have been Iterable rather than Iterator 77048f8 [Holden Karau] Fix merge up to master d3fe909 [Holden Karau] use toSeq instead 7a092a3 [Holden Karau] switch resultitr to resultiterable eb06216 [Holden Karau] maybe I should have had a coffee first. use correct import for guava iterables c5075aa [Holden Karau] If guava 14 had iterables 2d06e10 [Holden Karau] Fix Java 8 cogroup tests for the new API 11e730c [Holden Karau] Fix streaming tests 66b583d [Holden Karau] Fix the core test suite to compile 4ed579b [Holden Karau] Refactor from iterator to iterable d052c07 [Holden Karau] Python tests now pass with iterator pandas 3bcd81d [Holden Karau] Revert "Try and make pickling list iterators work" cd1e81c [Holden Karau] Try and make pickling list iterators work c60233a [Holden Karau] Start investigating moving to iterators for python API like the Java/Scala one. tl;dr: We will have to write our own iterator since the default one doesn't pickle well 88a5cef [Holden Karau] Fix cogroup test in JavaAPISuite for streaming a5ee714 [Holden Karau] oops, was checking wrong iterator e687f21 [Holden Karau] Fix groupbykey test in JavaAPISuite of streaming ec8cc3e [Holden Karau] Fix test issues\! 4b0eeb9 [Holden Karau] Switch cast in PairDStreamFunctions fa395c9 [Holden Karau] Revert "Add a join based on the problem in SVD" ec99e32 [Holden Karau] Revert "Revert this but for now put things in list pandas" b692868 [Holden Karau] Revert 7e533f7 [Holden Karau] Fix the bug 8a5153a [Holden Karau] Revert me, but we have some stuff to debug b4e86a9 [Holden Karau] Add a join based on the problem in SVD c4510e2 [Holden Karau] Revert this but for now put things in list pandas b4e0b1d [Holden Karau] Fix style issues 71e8b9f [Holden Karau] I really need to stop calling size on iterators, it is the path of sadness. b1ae51a [Holden Karau] Fix some of the types in the streaming JavaAPI suite. Probably still needs more work 37888ec [Holden Karau] core/tests now pass 249abde [Holden Karau] org.apache.spark.rdd.PairRDDFunctionsSuite passes 6698186 [Holden Karau] Revert "I think this might be a bad rabbit hole. Started work to make CoGroupedRDD use iterator and then went crazy" fe992fe [Holden Karau] hmmm try and fix up basic operation suite 172705c [Holden Karau] Fix Java API suite caafa63 [Holden Karau] I think this might be a bad rabbit hole. Started work to make CoGroupedRDD use iterator and then went crazy 88b3329 [Holden Karau] Fix groupbykey to actually give back an iterator 4991af6 [Holden Karau] Fix some tests be50246 [Holden Karau] Calling size on an iterator is not so good if we want to use it after 687ffbc [Holden Karau] This is the it compiles point of replacing Seq with Iterator and JList with JIterator in the groupby and cogroup signatures --- .../main/scala/org/apache/spark/bagel/Bagel.scala | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) (limited to 'bagel/src/main/scala/org') diff --git a/bagel/src/main/scala/org/apache/spark/bagel/Bagel.scala b/bagel/src/main/scala/org/apache/spark/bagel/Bagel.scala index 70c7474a93..70a99b33d7 100644 --- a/bagel/src/main/scala/org/apache/spark/bagel/Bagel.scala +++ b/bagel/src/main/scala/org/apache/spark/bagel/Bagel.scala @@ -220,20 +220,23 @@ object Bagel extends Logging { */ private def comp[K: Manifest, V <: Vertex, M <: Message[K], C]( sc: SparkContext, - grouped: RDD[(K, (Seq[C], Seq[V]))], + grouped: RDD[(K, (Iterable[C], Iterable[V]))], compute: (V, Option[C]) => (V, Array[M]), storageLevel: StorageLevel ): (RDD[(K, (V, Array[M]))], Int, Int) = { var numMsgs = sc.accumulator(0) var numActiveVerts = sc.accumulator(0) - val processed = grouped.flatMapValues { - case (_, vs) if vs.size == 0 => None - case (c, vs) => + val processed = grouped.mapValues(x => (x._1.iterator, x._2.iterator)) + .flatMapValues { + case (_, vs) if !vs.hasNext => None + case (c, vs) => { val (newVert, newMsgs) = - compute(vs(0), c match { - case Seq(comb) => Some(comb) - case Seq() => None - }) + compute(vs.next, + c.hasNext match { + case true => Some(c.next) + case false => None + } + ) numMsgs += newMsgs.size if (newVert.active) { @@ -241,6 +244,7 @@ object Bagel extends Logging { } Some((newVert, newMsgs)) + } }.persist(storageLevel) // Force evaluation of processed RDD for accurate performance measurements -- cgit v1.2.3