spark中产生shuffle的算子

Spark中产生shuffle的算子

作用	算子名	能否替换，由谁替换
去重	distinct()	不能
聚合	reduceByKey()	groupByKey
	groupBy()
	groupByKey()	reduceByKey
	aggregateByKey()
	combineByKey()
排序	sortByKey()
	sortBy()
重分区	coalesce()
	repartition()
集合或者表操作	Intersection()
	Substract()
	SubstractByKey()
	Join()
	LeftOutJoin()

https://www.cnblogs.com/Alex-zqzy/p/9949117.html

去重

def distinct()

def distinct(numPartitions: Int)

聚合

def reduceByKey(func: (V, V) => V, numPartitions: Int): RDD[(K, V)]

def reduceByKey(partitioner: Partitioner, func: (V, V) => V): RDD[(K, V)]

def groupBy[K](f: T => K, p: Partitioner):RDD[(K, Iterable[V])]

def groupByKey(partitioner: Partitioner):RDD[(K, Iterable[V])]

def aggregateByKey[U: ClassTag](zeroValue: U, partitioner: Partitioner): RDD[(K, U)]

def aggregateByKey[U: ClassTag](zeroValue: U, numPartitions: Int): RDD[(K, U)]

def combineByKey[C](createCombiner: V => C, mergeValue: (C, V) => C, mergeCombiners: (C, C) => C): RDD[(K, C)]

def combineByKey[C](createCombiner: V => C, mergeValue: (C, V) => C, mergeCombiners: (C, C) => C, numPartitions: Int): RDD[(K, C)]

def combineByKey[C](createCombiner: V => C, mergeValue: (C, V) => C, mergeCombiners: (C, C) => C, partitioner: Partitioner, mapSideCombine: Boolean = true, serializer: Serializer = null): RDD[(K, C)]

排序

def sortByKey(ascending: Boolean = true, numPartitions: Int = self.partitions.length): RDD[(K, V)]

def sortBy[K](f: (T) => K, ascending: Boolean = true, numPartitions: Int = this.partitions.length)(implicit ord: Ordering[K], ctag: ClassTag[K]): RDD[T]

重分区

def coalesce(numPartitions: Int, shuffle: Boolean = false, partitionCoalescer: Option[PartitionCoalescer] = Option.empty)

def repartition(numPartitions: Int)(implicit ord: Ordering[T] = null)

集合或者表操作

def intersection(other: RDD[T]): RDD[T]

def intersection(other: RDD[T], partitioner: Partitioner)(implicit ord: Ordering[T] = null): RDD[T]

def intersection(other: RDD[T], numPartitions: Int): RDD[T]

def subtract(other: RDD[T], numPartitions: Int): RDD[T]

def subtract(other: RDD[T], p: Partitioner)(implicit ord: Ordering[T] = null): RDD[T]

def subtractByKey[W: ClassTag](other: RDD[(K, W)]): RDD[(K, V)]

def subtractByKey[W: ClassTag](other: RDD[(K, W)], numPartitions: Int): RDD[(K, V)]

def subtractByKey[W: ClassTag](other: RDD[(K, W)], p: Partitioner): RDD[(K, V)]

def join[W](other: RDD[(K, W)], partitioner: Partitioner): RDD[(K, (V, W))]

def join[W](other: RDD[(K, W)]): RDD[(K, (V, W))]

def join[W](other: RDD[(K, W)], numPartitions: Int): RDD[(K, (V, W))]

def leftOuterJoin[W](other: RDD[(K, W)]): RDD[(K, (V, Option[W]))]