/
RDD.scala
1831 lines (1666 loc) · 74 KB
/
RDD.scala
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.spark.rdd
import java.util.Random
import scala.collection.{mutable, Map}
import scala.collection.mutable.ArrayBuffer
import scala.language.implicitConversions
import scala.reflect.{classTag, ClassTag}
import com.clearspring.analytics.stream.cardinality.HyperLogLogPlus
import org.apache.hadoop.io.{BytesWritable, NullWritable, Text}
import org.apache.hadoop.io.compress.CompressionCodec
import org.apache.hadoop.mapred.TextOutputFormat
import org.apache.spark._
import org.apache.spark.Partitioner._
import org.apache.spark.annotation.{DeveloperApi, Since}
import org.apache.spark.api.java.JavaRDD
import org.apache.spark.internal.Logging
import org.apache.spark.partial.BoundedDouble
import org.apache.spark.partial.CountEvaluator
import org.apache.spark.partial.GroupedCountEvaluator
import org.apache.spark.partial.PartialResult
import org.apache.spark.storage.{RDDBlockId, StorageLevel}
import org.apache.spark.util.{BoundedPriorityQueue, Utils}
import org.apache.spark.util.collection.OpenHashMap
import org.apache.spark.util.random.{BernoulliCellSampler, BernoulliSampler, PoissonSampler,
SamplingUtils}
/**
* A Resilient Distributed Dataset (RDD), the basic abstraction in Spark. Represents an immutable,
* partitioned collection of elements that can be operated on in parallel. This class contains the
* basic operations available on all RDDs, such as `map`, `filter`, and `persist`. In addition,
* [[org.apache.spark.rdd.PairRDDFunctions]] contains operations available only on RDDs of key-value
* pairs, such as `groupByKey` and `join`;
* [[org.apache.spark.rdd.DoubleRDDFunctions]] contains operations available only on RDDs of
* Doubles; and
* [[org.apache.spark.rdd.SequenceFileRDDFunctions]] contains operations available on RDDs that
* can be saved as SequenceFiles.
* All operations are automatically available on any RDD of the right type (e.g. RDD[(Int, Int)]
* through implicit.
*
* Internally, each RDD is characterized by five main properties:
*
* - A list of partitions
* - A function for computing each split
* - A list of dependencies on other RDDs
* - Optionally, a Partitioner for key-value RDDs (e.g. to say that the RDD is hash-partitioned)
* - Optionally, a list of preferred locations to compute each split on (e.g. block locations for
* an HDFS file)
*
* All of the scheduling and execution in Spark is done based on these methods, allowing each RDD
* to implement its own way of computing itself. Indeed, users can implement custom RDDs (e.g. for
* reading data from a new storage system) by overriding these functions. Please refer to the
* [[http://www.cs.berkeley.edu/~matei/papers/2012/nsdi_spark.pdf Spark paper]] for more details
* on RDD internals.
*/
abstract class RDD[T: ClassTag](
@transient private var _sc: SparkContext,
@transient private var deps: Seq[Dependency[_]]
) extends Serializable with Logging {
if (classOf[RDD[_]].isAssignableFrom(elementClassTag.runtimeClass)) {
// This is a warning instead of an exception in order to avoid breaking user programs that
// might have defined nested RDDs without running jobs with them.
logWarning("Spark does not support nested RDDs (see SPARK-5063)")
}
private def sc: SparkContext = {
if (_sc == null) {
throw new SparkException(
"This RDD lacks a SparkContext. It could happen in the following cases: \n(1) RDD " +
"transformations and actions are NOT invoked by the driver, but inside of other " +
"transformations; for example, rdd1.map(x => rdd2.values.count() * x) is invalid " +
"because the values transformation and count action cannot be performed inside of the " +
"rdd1.map transformation. For more information, see SPARK-5063.\n(2) When a Spark " +
"Streaming job recovers from checkpoint, this exception will be hit if a reference to " +
"an RDD not defined by the streaming job is used in DStream operations. For more " +
"information, See SPARK-13758.")
}
_sc
}
/** Construct an RDD with just a one-to-one dependency on one parent */
def this(@transient oneParent: RDD[_]) =
this(oneParent.context, List(new OneToOneDependency(oneParent)))
private[spark] def conf = sc.conf
// =======================================================================
// Methods that should be implemented by subclasses of RDD
// =======================================================================
/**
* :: DeveloperApi ::
* Implemented by subclasses to compute a given partition.
*/
@DeveloperApi
def compute(split: Partition, context: TaskContext): Iterator[T]
/**
* Implemented by subclasses to return the set of partitions in this RDD. This method will only
* be called once, so it is safe to implement a time-consuming computation in it.
*
* The partitions in this array must satisfy the following property:
* `rdd.partitions.zipWithIndex.forall { case (partition, index) => partition.index == index }`
*/
protected def getPartitions: Array[Partition]
/**
* Implemented by subclasses to return how this RDD depends on parent RDDs. This method will only
* be called once, so it is safe to implement a time-consuming computation in it.
*/
protected def getDependencies: Seq[Dependency[_]] = deps
/**
* Optionally overridden by subclasses to specify placement preferences.
*/
protected def getPreferredLocations(split: Partition): Seq[String] = Nil
/** Optionally overridden by subclasses to specify how they are partitioned. */
@transient val partitioner: Option[Partitioner] = None
// =======================================================================
// Methods and fields available on all RDDs
// =======================================================================
/** The SparkContext that created this RDD. */
def sparkContext: SparkContext = sc
/** A unique ID for this RDD (within its SparkContext). */
val id: Int = sc.newRddId()
/** A friendly name for this RDD */
@transient var name: String = null
/** Assign a name to this RDD */
def setName(_name: String): this.type = {
name = _name
this
}
/**
* Mark this RDD for persisting using the specified level.
*
* @param newLevel the target storage level
* @param allowOverride whether to override any existing level with the new one
*/
private def persist(newLevel: StorageLevel, allowOverride: Boolean): this.type = {
// TODO: Handle changes of StorageLevel
if (storageLevel != StorageLevel.NONE && newLevel != storageLevel && !allowOverride) {
throw new UnsupportedOperationException(
"Cannot change storage level of an RDD after it was already assigned a level")
}
// If this is the first time this RDD is marked for persisting, register it
// with the SparkContext for cleanups and accounting. Do this only once.
if (storageLevel == StorageLevel.NONE) {
sc.cleaner.foreach(_.registerRDDForCleanup(this))
sc.persistRDD(this)
}
storageLevel = newLevel
this
}
/**
* Set this RDD's storage level to persist its values across operations after the first time
* it is computed. This can only be used to assign a new storage level if the RDD does not
* have a storage level set yet. Local checkpointing is an exception.
*/
def persist(newLevel: StorageLevel): this.type = {
if (isLocallyCheckpointed) {
// This means the user previously called localCheckpoint(), which should have already
// marked this RDD for persisting. Here we should override the old storage level with
// one that is explicitly requested by the user (after adapting it to use disk).
persist(LocalRDDCheckpointData.transformStorageLevel(newLevel), allowOverride = true)
} else {
persist(newLevel, allowOverride = false)
}
}
/** Persist this RDD with the default storage level (`MEMORY_ONLY`). */
def persist(): this.type = persist(StorageLevel.MEMORY_ONLY)
/** Persist this RDD with the default storage level (`MEMORY_ONLY`). */
def cache(): this.type = persist()
/**
* Mark the RDD as non-persistent, and remove all blocks for it from memory and disk.
*
* @param blocking Whether to block until all blocks are deleted.
* @return This RDD.
*/
def unpersist(blocking: Boolean = true): this.type = {
logInfo("Removing RDD " + id + " from persistence list")
sc.unpersistRDD(id, blocking)
storageLevel = StorageLevel.NONE
this
}
/** Get the RDD's current storage level, or StorageLevel.NONE if none is set. */
def getStorageLevel: StorageLevel = storageLevel
// Our dependencies and partitions will be gotten by calling subclass's methods below, and will
// be overwritten when we're checkpointed
private var dependencies_ : Seq[Dependency[_]] = null
@transient private var partitions_ : Array[Partition] = null
/** An Option holding our checkpoint RDD, if we are checkpointed */
private def checkpointRDD: Option[CheckpointRDD[T]] = checkpointData.flatMap(_.checkpointRDD)
/**
* Get the list of dependencies of this RDD, taking into account whether the
* RDD is checkpointed or not.
*/
final def dependencies: Seq[Dependency[_]] = {
checkpointRDD.map(r => List(new OneToOneDependency(r))).getOrElse {
if (dependencies_ == null) {
dependencies_ = getDependencies
}
dependencies_
}
}
/**
* Get the array of partitions of this RDD, taking into account whether the
* RDD is checkpointed or not.
*/
final def partitions: Array[Partition] = {
checkpointRDD.map(_.partitions).getOrElse {
if (partitions_ == null) {
partitions_ = getPartitions
partitions_.zipWithIndex.foreach { case (partition, index) =>
require(partition.index == index,
s"partitions($index).partition == ${partition.index}, but it should equal $index")
}
}
partitions_
}
}
/**
* Returns the number of partitions of this RDD.
*/
@Since("1.6.0")
final def getNumPartitions: Int = partitions.length
/**
* Get the preferred locations of a partition, taking into account whether the
* RDD is checkpointed.
*/
final def preferredLocations(split: Partition): Seq[String] = {
checkpointRDD.map(_.getPreferredLocations(split)).getOrElse {
getPreferredLocations(split)
}
}
/**
* Internal method to this RDD; will read from cache if applicable, or otherwise compute it.
* This should ''not'' be called by users directly, but is available for implementors of custom
* subclasses of RDD.
*/
final def iterator(split: Partition, context: TaskContext): Iterator[T] = {
if (storageLevel != StorageLevel.NONE) {
getOrCompute(split, context)
} else {
computeOrReadCheckpoint(split, context)
}
}
/**
* Return the ancestors of the given RDD that are related to it only through a sequence of
* narrow dependencies. This traverses the given RDD's dependency tree using DFS, but maintains
* no ordering on the RDDs returned.
*/
private[spark] def getNarrowAncestors: Seq[RDD[_]] = {
val ancestors = new mutable.HashSet[RDD[_]]
def visit(rdd: RDD[_]) {
val narrowDependencies = rdd.dependencies.filter(_.isInstanceOf[NarrowDependency[_]])
val narrowParents = narrowDependencies.map(_.rdd)
val narrowParentsNotVisited = narrowParents.filterNot(ancestors.contains)
narrowParentsNotVisited.foreach { parent =>
ancestors.add(parent)
visit(parent)
}
}
visit(this)
// In case there is a cycle, do not include the root itself
ancestors.filterNot(_ == this).toSeq
}
/**
* Compute an RDD partition or read it from a checkpoint if the RDD is checkpointing.
*/
private[spark] def computeOrReadCheckpoint(split: Partition, context: TaskContext): Iterator[T] =
{
if (isCheckpointedAndMaterialized) {
firstParent[T].iterator(split, context)
} else {
compute(split, context)
}
}
/**
* Gets or computes an RDD partition. Used by RDD.iterator() when an RDD is cached.
*/
private[spark] def getOrCompute(partition: Partition, context: TaskContext): Iterator[T] = {
val blockId = RDDBlockId(id, partition.index)
var readCachedBlock = true
// This method is called on executors, so we need call SparkEnv.get instead of sc.env.
SparkEnv.get.blockManager.getOrElseUpdate(blockId, storageLevel, elementClassTag, () => {
readCachedBlock = false
computeOrReadCheckpoint(partition, context)
}) match {
case Left(blockResult) =>
if (readCachedBlock) {
val existingMetrics = context.taskMetrics().inputMetrics
existingMetrics.incBytesRead(blockResult.bytes)
new InterruptibleIterator[T](context, blockResult.data.asInstanceOf[Iterator[T]]) {
override def next(): T = {
existingMetrics.incRecordsRead(1)
delegate.next()
}
}
} else {
new InterruptibleIterator(context, blockResult.data.asInstanceOf[Iterator[T]])
}
case Right(iter) =>
new InterruptibleIterator(context, iter.asInstanceOf[Iterator[T]])
}
}
/**
* Execute a block of code in a scope such that all new RDDs created in this body will
* be part of the same scope. For more detail, see {{org.apache.spark.rdd.RDDOperationScope}}.
*
* Note: Return statements are NOT allowed in the given body.
*/
private[spark] def withScope[U](body: => U): U = RDDOperationScope.withScope[U](sc)(body)
// Transformations (return a new RDD)
/**
* Return a new RDD by applying a function to all elements of this RDD.
*/
def map[U: ClassTag](f: T => U): RDD[U] = withScope {
val cleanF = sc.clean(f)
new MapPartitionsRDD[U, T](this, (context, pid, iter) => iter.map(cleanF))
}
/**
* Return a new RDD by first applying a function to all elements of this
* RDD, and then flattening the results.
*/
def flatMap[U: ClassTag](f: T => TraversableOnce[U]): RDD[U] = withScope {
val cleanF = sc.clean(f)
new MapPartitionsRDD[U, T](this, (context, pid, iter) => iter.flatMap(cleanF))
}
/**
* Return a new RDD containing only the elements that satisfy a predicate.
*/
def filter(f: T => Boolean): RDD[T] = withScope {
val cleanF = sc.clean(f)
new MapPartitionsRDD[T, T](
this,
(context, pid, iter) => iter.filter(cleanF),
preservesPartitioning = true)
}
/**
* Return a new RDD containing the distinct elements in this RDD.
*/
def distinct(numPartitions: Int)(implicit ord: Ordering[T] = null): RDD[T] = withScope {
map(x => (x, null)).reduceByKey((x, y) => x, numPartitions).map(_._1)
}
/**
* Return a new RDD containing the distinct elements in this RDD.
*/
def distinct(): RDD[T] = withScope {
distinct(partitions.length)
}
/**
* Return a new RDD that has exactly numPartitions partitions.
*
* Can increase or decrease the level of parallelism in this RDD. Internally, this uses
* a shuffle to redistribute data.
*
* If you are decreasing the number of partitions in this RDD, consider using `coalesce`,
* which can avoid performing a shuffle.
*/
def repartition(numPartitions: Int)(implicit ord: Ordering[T] = null): RDD[T] = withScope {
coalesce(numPartitions, shuffle = true)
}
/**
* Return a new RDD that is reduced into `numPartitions` partitions.
*
* This results in a narrow dependency, e.g. if you go from 1000 partitions
* to 100 partitions, there will not be a shuffle, instead each of the 100
* new partitions will claim 10 of the current partitions.
*
* However, if you're doing a drastic coalesce, e.g. to numPartitions = 1,
* this may result in your computation taking place on fewer nodes than
* you like (e.g. one node in the case of numPartitions = 1). To avoid this,
* you can pass shuffle = true. This will add a shuffle step, but means the
* current upstream partitions will be executed in parallel (per whatever
* the current partitioning is).
*
* Note: With shuffle = true, you can actually coalesce to a larger number
* of partitions. This is useful if you have a small number of partitions,
* say 100, potentially with a few partitions being abnormally large. Calling
* coalesce(1000, shuffle = true) will result in 1000 partitions with the
* data distributed using a hash partitioner.
*/
def coalesce(numPartitions: Int, shuffle: Boolean = false,
partitionCoalescer: Option[PartitionCoalescer] = Option.empty)
(implicit ord: Ordering[T] = null)
: RDD[T] = withScope {
if (shuffle) {
/** Distributes elements evenly across output partitions, starting from a random partition. */
val distributePartition = (index: Int, items: Iterator[T]) => {
var position = (new Random(index)).nextInt(numPartitions)
items.map { t =>
// Note that the hash code of the key will just be the key itself. The HashPartitioner
// will mod it with the number of total partitions.
position = position + 1
(position, t)
}
} : Iterator[(Int, T)]
// include a shuffle step so that our upstream tasks are still distributed
new CoalescedRDD(
new ShuffledRDD[Int, T, T](mapPartitionsWithIndex(distributePartition),
new HashPartitioner(numPartitions)),
numPartitions,
partitionCoalescer).values
} else {
new CoalescedRDD(this, numPartitions, partitionCoalescer)
}
}
/**
* Return a sampled subset of this RDD.
*
* @param withReplacement can elements be sampled multiple times (replaced when sampled out)
* @param fraction expected size of the sample as a fraction of this RDD's size
* without replacement: probability that each element is chosen; fraction must be [0, 1]
* with replacement: expected number of times each element is chosen; fraction must be >= 0
* @param seed seed for the random number generator
*/
def sample(
withReplacement: Boolean,
fraction: Double,
seed: Long = Utils.random.nextLong): RDD[T] = withScope {
require(fraction >= 0.0, "Negative fraction value: " + fraction)
if (withReplacement) {
new PartitionwiseSampledRDD[T, T](this, new PoissonSampler[T](fraction), true, seed)
} else {
new PartitionwiseSampledRDD[T, T](this, new BernoulliSampler[T](fraction), true, seed)
}
}
/**
* Randomly splits this RDD with the provided weights.
*
* @param weights weights for splits, will be normalized if they don't sum to 1
* @param seed random seed
*
* @return split RDDs in an array
*/
def randomSplit(
weights: Array[Double],
seed: Long = Utils.random.nextLong): Array[RDD[T]] = withScope {
val sum = weights.sum
val normalizedCumWeights = weights.map(_ / sum).scanLeft(0.0d)(_ + _)
normalizedCumWeights.sliding(2).map { x =>
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] = {
this.mapPartitionsWithIndex( { (index, partition) =>
val sampler = new BernoulliCellSampler[T](lb, ub)
sampler.setSeed(seed + index)
sampler.sample(partition)
}, preservesPartitioning = true)
}
/**
* Return a fixed-size sampled subset of this RDD in an array
*
* @note this method should only be used if the resulting array is expected to be small, as
* all the data is loaded into the driver's memory.
*
* @param withReplacement whether sampling is done with replacement
* @param num size of the returned sample
* @param seed seed for the random number generator
* @return sample of specified size in an array
*/
def takeSample(
withReplacement: Boolean,
num: Int,
seed: Long = Utils.random.nextLong): Array[T] = withScope {
val numStDev = 10.0
require(num >= 0, "Negative number of elements requested")
require(num <= (Int.MaxValue - (numStDev * math.sqrt(Int.MaxValue)).toInt),
"Cannot support a sample size > Int.MaxValue - " +
s"$numStDev * math.sqrt(Int.MaxValue)")
if (num == 0) {
new Array[T](0)
} else {
val initialCount = this.count()
if (initialCount == 0) {
new Array[T](0)
} else {
val rand = new Random(seed)
if (!withReplacement && num >= initialCount) {
Utils.randomizeInPlace(this.collect(), rand)
} else {
val fraction = SamplingUtils.computeFractionForSampleSize(num, initialCount,
withReplacement)
var samples = this.sample(withReplacement, fraction, rand.nextInt()).collect()
// If the first sample didn't turn out large enough, keep trying to take samples;
// this shouldn't happen often because we use a big multiplier for the initial size
var numIters = 0
while (samples.length < num) {
logWarning(s"Needed to re-sample due to insufficient sample size. Repeat #$numIters")
samples = this.sample(withReplacement, fraction, rand.nextInt()).collect()
numIters += 1
}
Utils.randomizeInPlace(samples, rand).take(num)
}
}
}
}
/**
* Return the union of this RDD and another one. Any identical elements will appear multiple
* times (use `.distinct()` to eliminate them).
*/
def union(other: RDD[T]): RDD[T] = withScope {
sc.union(this, other)
}
/**
* Return the union of this RDD and another one. Any identical elements will appear multiple
* times (use `.distinct()` to eliminate them).
*/
def ++(other: RDD[T]): RDD[T] = withScope {
this.union(other)
}
/**
* Return this RDD sorted by the given key function.
*/
def sortBy[K](
f: (T) => K,
ascending: Boolean = true,
numPartitions: Int = this.partitions.length)
(implicit ord: Ordering[K], ctag: ClassTag[K]): RDD[T] = withScope {
this.keyBy[K](f)
.sortByKey(ascending, numPartitions)
.values
}
/**
* Return the intersection of this RDD and another one. The output will not contain any duplicate
* elements, even if the input RDDs did.
*
* Note that this method performs a shuffle internally.
*/
def intersection(other: RDD[T]): RDD[T] = withScope {
this.map(v => (v, null)).cogroup(other.map(v => (v, null)))
.filter { case (_, (leftGroup, rightGroup)) => leftGroup.nonEmpty && rightGroup.nonEmpty }
.keys
}
/**
* Return the intersection of this RDD and another one. The output will not contain any duplicate
* elements, even if the input RDDs did.
*
* Note that this method performs a shuffle internally.
*
* @param partitioner Partitioner to use for the resulting RDD
*/
def intersection(
other: RDD[T],
partitioner: Partitioner)(implicit ord: Ordering[T] = null): RDD[T] = withScope {
this.map(v => (v, null)).cogroup(other.map(v => (v, null)), partitioner)
.filter { case (_, (leftGroup, rightGroup)) => leftGroup.nonEmpty && rightGroup.nonEmpty }
.keys
}
/**
* Return the intersection of this RDD and another one. The output will not contain any duplicate
* elements, even if the input RDDs did. Performs a hash partition across the cluster
*
* Note that this method performs a shuffle internally.
*
* @param numPartitions How many partitions to use in the resulting RDD
*/
def intersection(other: RDD[T], numPartitions: Int): RDD[T] = withScope {
intersection(other, new HashPartitioner(numPartitions))
}
/**
* Return an RDD created by coalescing all elements within each partition into an array.
*/
def glom(): RDD[Array[T]] = withScope {
new MapPartitionsRDD[Array[T], T](this, (context, pid, iter) => Iterator(iter.toArray))
}
/**
* Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of
* elements (a, b) where a is in `this` and b is in `other`.
*/
def cartesian[U: ClassTag](other: RDD[U]): RDD[(T, U)] = withScope {
new CartesianRDD(sc, this, other)
}
/**
* Return an RDD of grouped items. Each group consists of a key and a sequence of elements
* mapping to that key. The ordering of elements within each group is not guaranteed, and
* may even differ each time the resulting RDD is evaluated.
*
* Note: This operation may be very expensive. If you are grouping in order to perform an
* aggregation (such as a sum or average) over each key, using [[PairRDDFunctions.aggregateByKey]]
* or [[PairRDDFunctions.reduceByKey]] will provide much better performance.
*/
def groupBy[K](f: T => K)(implicit kt: ClassTag[K]): RDD[(K, Iterable[T])] = withScope {
groupBy[K](f, defaultPartitioner(this))
}
/**
* Return an RDD of grouped elements. Each group consists of a key and a sequence of elements
* mapping to that key. The ordering of elements within each group is not guaranteed, and
* may even differ each time the resulting RDD is evaluated.
*
* Note: This operation may be very expensive. If you are grouping in order to perform an
* aggregation (such as a sum or average) over each key, using [[PairRDDFunctions.aggregateByKey]]
* or [[PairRDDFunctions.reduceByKey]] will provide much better performance.
*/
def groupBy[K](
f: T => K,
numPartitions: Int)(implicit kt: ClassTag[K]): RDD[(K, Iterable[T])] = withScope {
groupBy(f, new HashPartitioner(numPartitions))
}
/**
* Return an RDD of grouped items. Each group consists of a key and a sequence of elements
* mapping to that key. The ordering of elements within each group is not guaranteed, and
* may even differ each time the resulting RDD is evaluated.
*
* Note: This operation may be very expensive. If you are grouping in order to perform an
* aggregation (such as a sum or average) over each key, using [[PairRDDFunctions.aggregateByKey]]
* or [[PairRDDFunctions.reduceByKey]] will provide much better performance.
*/
def groupBy[K](f: T => K, p: Partitioner)(implicit kt: ClassTag[K], ord: Ordering[K] = null)
: RDD[(K, Iterable[T])] = withScope {
val cleanF = sc.clean(f)
this.map(t => (cleanF(t), t)).groupByKey(p)
}
/**
* Return an RDD created by piping elements to a forked external process.
*/
def pipe(command: String): RDD[String] = withScope {
new PipedRDD(this, command)
}
/**
* Return an RDD created by piping elements to a forked external process.
*/
def pipe(command: String, env: Map[String, String]): RDD[String] = withScope {
new PipedRDD(this, command, env)
}
/**
* Return an RDD created by piping elements to a forked external process.
* The print behavior can be customized by providing two functions.
*
* @param command command to run in forked process.
* @param env environment variables to set.
* @param printPipeContext Before piping elements, this function is called as an opportunity
* to pipe context data. Print line function (like out.println) will be
* passed as printPipeContext's parameter.
* @param printRDDElement Use this function to customize how to pipe elements. This function
* will be called with each RDD element as the 1st parameter, and the
* print line function (like out.println()) as the 2nd parameter.
* An example of pipe the RDD data of groupBy() in a streaming way,
* instead of constructing a huge String to concat all the elements:
* def printRDDElement(record:(String, Seq[String]), f:String=>Unit) =
* for (e <- record._2) {f(e)}
* @param separateWorkingDir Use separate working directories for each task.
* @param bufferSize Buffer size for the stdin writer for the piped process.
* @return the result RDD
*/
def pipe(
command: Seq[String],
env: Map[String, String] = Map(),
printPipeContext: (String => Unit) => Unit = null,
printRDDElement: (T, String => Unit) => Unit = null,
separateWorkingDir: Boolean = false,
bufferSize: Int = 8192): RDD[String] = withScope {
new PipedRDD(this, command, env,
if (printPipeContext ne null) sc.clean(printPipeContext) else null,
if (printRDDElement ne null) sc.clean(printRDDElement) else null,
separateWorkingDir,
bufferSize)
}
/**
* Return a new RDD by applying a function to each partition of this RDD.
*
* `preservesPartitioning` indicates whether the input function preserves the partitioner, which
* should be `false` unless this is a pair RDD and the input function doesn't modify the keys.
*/
def mapPartitions[U: ClassTag](
f: Iterator[T] => Iterator[U],
preservesPartitioning: Boolean = false): RDD[U] = withScope {
val cleanedF = sc.clean(f)
new MapPartitionsRDD(
this,
(context: TaskContext, index: Int, iter: Iterator[T]) => cleanedF(iter),
preservesPartitioning)
}
/**
* [performance] Spark's internal mapPartitions method which skips closure cleaning. It is a
* performance API to be used carefully only if we are sure that the RDD elements are
* serializable and don't require closure cleaning.
*
* @param preservesPartitioning indicates whether the input function preserves the partitioner,
* which should be `false` unless this is a pair RDD and the input function doesn't modify
* the keys.
*/
private[spark] def mapPartitionsInternal[U: ClassTag](
f: Iterator[T] => Iterator[U],
preservesPartitioning: Boolean = false): RDD[U] = withScope {
new MapPartitionsRDD(
this,
(context: TaskContext, index: Int, iter: Iterator[T]) => f(iter),
preservesPartitioning)
}
/**
* Return a new RDD by applying a function to each partition of this RDD, while tracking the index
* of the original partition.
*
* `preservesPartitioning` indicates whether the input function preserves the partitioner, which
* should be `false` unless this is a pair RDD and the input function doesn't modify the keys.
*/
def mapPartitionsWithIndex[U: ClassTag](
f: (Int, Iterator[T]) => Iterator[U],
preservesPartitioning: Boolean = false): RDD[U] = withScope {
val cleanedF = sc.clean(f)
new MapPartitionsRDD(
this,
(context: TaskContext, index: Int, iter: Iterator[T]) => cleanedF(index, iter),
preservesPartitioning)
}
/**
* Zips this RDD with another one, returning key-value pairs with the first element in each RDD,
* second element in each RDD, etc. Assumes that the two RDDs have the *same number of
* partitions* and the *same number of elements in each partition* (e.g. one was made through
* a map on the other).
*/
def zip[U: ClassTag](other: RDD[U]): RDD[(T, U)] = withScope {
zipPartitions(other, preservesPartitioning = false) { (thisIter, otherIter) =>
new Iterator[(T, U)] {
def hasNext: Boolean = (thisIter.hasNext, otherIter.hasNext) match {
case (true, true) => true
case (false, false) => false
case _ => throw new SparkException("Can only zip RDDs with " +
"same number of elements in each partition")
}
def next(): (T, U) = (thisIter.next(), otherIter.next())
}
}
}
/**
* Zip this RDD's partitions with one (or more) RDD(s) and return a new RDD by
* applying a function to the zipped partitions. Assumes that all the RDDs have the
* *same number of partitions*, but does *not* require them to have the same number
* of elements in each partition.
*/
def zipPartitions[B: ClassTag, V: ClassTag]
(rdd2: RDD[B], preservesPartitioning: Boolean)
(f: (Iterator[T], Iterator[B]) => Iterator[V]): RDD[V] = withScope {
new ZippedPartitionsRDD2(sc, sc.clean(f), this, rdd2, preservesPartitioning)
}
def zipPartitions[B: ClassTag, V: ClassTag]
(rdd2: RDD[B])
(f: (Iterator[T], Iterator[B]) => Iterator[V]): RDD[V] = withScope {
zipPartitions(rdd2, preservesPartitioning = false)(f)
}
def zipPartitions[B: ClassTag, C: ClassTag, V: ClassTag]
(rdd2: RDD[B], rdd3: RDD[C], preservesPartitioning: Boolean)
(f: (Iterator[T], Iterator[B], Iterator[C]) => Iterator[V]): RDD[V] = withScope {
new ZippedPartitionsRDD3(sc, sc.clean(f), this, rdd2, rdd3, preservesPartitioning)
}
def zipPartitions[B: ClassTag, C: ClassTag, V: ClassTag]
(rdd2: RDD[B], rdd3: RDD[C])
(f: (Iterator[T], Iterator[B], Iterator[C]) => Iterator[V]): RDD[V] = withScope {
zipPartitions(rdd2, rdd3, preservesPartitioning = false)(f)
}
def zipPartitions[B: ClassTag, C: ClassTag, D: ClassTag, V: ClassTag]
(rdd2: RDD[B], rdd3: RDD[C], rdd4: RDD[D], preservesPartitioning: Boolean)
(f: (Iterator[T], Iterator[B], Iterator[C], Iterator[D]) => Iterator[V]): RDD[V] = withScope {
new ZippedPartitionsRDD4(sc, sc.clean(f), this, rdd2, rdd3, rdd4, preservesPartitioning)
}
def zipPartitions[B: ClassTag, C: ClassTag, D: ClassTag, V: ClassTag]
(rdd2: RDD[B], rdd3: RDD[C], rdd4: RDD[D])
(f: (Iterator[T], Iterator[B], Iterator[C], Iterator[D]) => Iterator[V]): RDD[V] = withScope {
zipPartitions(rdd2, rdd3, rdd4, preservesPartitioning = false)(f)
}
// Actions (launch a job to return a value to the user program)
/**
* Applies a function f to all elements of this RDD.
*/
def foreach(f: T => Unit): Unit = withScope {
val cleanF = sc.clean(f)
sc.runJob(this, (iter: Iterator[T]) => iter.foreach(cleanF))
}
/**
* Applies a function f to each partition of this RDD.
*/
def foreachPartition(f: Iterator[T] => Unit): Unit = withScope {
val cleanF = sc.clean(f)
sc.runJob(this, (iter: Iterator[T]) => cleanF(iter))
}
/**
* Return an array that contains all of the elements in this RDD.
*
* @note this method should only be used if the resulting array is expected to be small, as
* all the data is loaded into the driver's memory.
*/
def collect(): Array[T] = withScope {
val results = sc.runJob(this, (iter: Iterator[T]) => iter.toArray)
Array.concat(results: _*)
}
/**
* Return an iterator that contains all of the elements in this RDD.
*
* The iterator will consume as much memory as the largest partition in this RDD.
*
* Note: this results in multiple Spark jobs, and if the input RDD is the result
* of a wide transformation (e.g. join with different partitioners), to avoid
* recomputing the input RDD should be cached first.
*/
def toLocalIterator: Iterator[T] = withScope {
def collectPartition(p: Int): Array[T] = {
sc.runJob(this, (iter: Iterator[T]) => iter.toArray, Seq(p)).head
}
(0 until partitions.length).iterator.flatMap(i => collectPartition(i))
}
/**
* Return an RDD that contains all matching values by applying `f`.
*/
def collect[U: ClassTag](f: PartialFunction[T, U]): RDD[U] = withScope {
val cleanF = sc.clean(f)
filter(cleanF.isDefinedAt).map(cleanF)
}
/**
* Return an RDD with the elements from `this` that are not in `other`.
*
* Uses `this` partitioner/partition size, because even if `other` is huge, the resulting
* RDD will be <= us.
*/
def subtract(other: RDD[T]): RDD[T] = withScope {
subtract(other, partitioner.getOrElse(new HashPartitioner(partitions.length)))
}
/**
* Return an RDD with the elements from `this` that are not in `other`.
*/
def subtract(other: RDD[T], numPartitions: Int): RDD[T] = withScope {
subtract(other, new HashPartitioner(numPartitions))
}
/**
* Return an RDD with the elements from `this` that are not in `other`.
*/
def subtract(
other: RDD[T],
p: Partitioner)(implicit ord: Ordering[T] = null): RDD[T] = withScope {
if (partitioner == Some(p)) {
// Our partitioner knows how to handle T (which, since we have a partitioner, is
// really (K, V)) so make a new Partitioner that will de-tuple our fake tuples
val p2 = new Partitioner() {
override def numPartitions: Int = p.numPartitions
override def getPartition(k: Any): Int = p.getPartition(k.asInstanceOf[(Any, _)]._1)
}
// Unfortunately, since we're making a new p2, we'll get ShuffleDependencies
// anyway, and when calling .keys, will not have a partitioner set, even though
// the SubtractedRDD will, thanks to p2's de-tupled partitioning, already be
// partitioned by the right/real keys (e.g. p).
this.map(x => (x, null)).subtractByKey(other.map((_, null)), p2).keys
} else {
this.map(x => (x, null)).subtractByKey(other.map((_, null)), p).keys
}
}
/**
* Reduces the elements of this RDD using the specified commutative and
* associative binary operator.
*/
def reduce(f: (T, T) => T): T = withScope {
val cleanF = sc.clean(f)
val reducePartition: Iterator[T] => Option[T] = iter => {
if (iter.hasNext) {
Some(iter.reduceLeft(cleanF))
} else {
None
}
}
var jobResult: Option[T] = None
val mergeResult = (index: Int, taskResult: Option[T]) => {
if (taskResult.isDefined) {
jobResult = jobResult match {
case Some(value) => Some(f(value, taskResult.get))
case None => taskResult
}
}
}
sc.runJob(this, reducePartition, mergeResult)
// Get the final result out of our Option, or throw an exception if the RDD was empty
jobResult.getOrElse(throw new UnsupportedOperationException("empty collection"))
}
/**
* Reduces the elements of this RDD in a multi-level tree pattern.
*
* @param depth suggested depth of the tree (default: 2)
* @see [[org.apache.spark.rdd.RDD#reduce]]
*/
def treeReduce(f: (T, T) => T, depth: Int = 2): T = withScope {
require(depth >= 1, s"Depth must be greater than or equal to 1 but got $depth.")
val cleanF = context.clean(f)
val reducePartition: Iterator[T] => Option[T] = iter => {
if (iter.hasNext) {
Some(iter.reduceLeft(cleanF))
} else {
None
}
}
val partiallyReduced = mapPartitions(it => Iterator(reducePartition(it)))
val op: (Option[T], Option[T]) => Option[T] = (c, x) => {
if (c.isDefined && x.isDefined) {
Some(cleanF(c.get, x.get))
} else if (c.isDefined) {
c
} else if (x.isDefined) {