zoukankan      html  css  js  c++  java
  • Spark会产生shuffle的算子

    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]))]
  • 相关阅读:
    用AjaxMethod 方法实现动态加载地图
    C#中HashTable的使用(转)
    ArcGIS Server 中的动态文字标注
    ArcGIS Server .Net Web ADF之几何类型的相互转换(转)
    ArcGIS Server连接远程地图服务器
    sqlplus环境配置(login.sql)
    Oracle从软件安装到运行的全流程
    【转载】linux中误删除oracle数据文件的恢复操作
    “大淘宝战略”下集市定位,将决定马云和未来淘宝的命运
    男人如何对待抱怨自己的女人
  • 原文地址:https://www.cnblogs.com/blazeZzz/p/9949117.html
Copyright © 2011-2022 走看看