一.Transformation spark 常用的 Transformation 算子如下表: Transformation 算子 Meaning(含义) map(func) 对原 RDD 中每个元素运用 func 函数,并生成新的 RDD filter(func) 对原 RDD 中每个元素使用func 函数进行过滤,并生成新的 RDD flatMap(func) 与 map 类似,但是每一个输入的 item 被映射成 0 个或多个输出的 items( func 返回类型需要为 Seq ).

Spark操作算子本质-RDD的容错spark模式1.standalone master 资源调度 worker2.yarn resourcemanager 资源调度 nodemanager在一个集群中只能有一个资源调度,如果有两个资源调度的话,master和resourcemanager之间是不通信的,master分配某个资源,resourcemanager是不知道的一个application对应一个driver,driver是用来分配任务的 流程示意分布式文件系统(File system)加

package com.test; import java.util.ArrayList; import java.util.List; import java.util.Map; import org.apache.spark.Partitioner; import org.apache.spark.SparkConf; import org.apache.spark.api.java.JavaPairRDD; import org.apache.spark.api.java.JavaRDD;

算子分为value-transform, key-value-transform, action三种.f是输入给算子的函数,比如lambda x: x**2 常用算子: keys: 取pair rdd的key部分 values: 取pair rdd的value部分 map: f作用于每个元素 flatMap: f作用于每个元素.输出list,然后对list压平 mapValues: f作用于pair rdd的value部分 flatMapValues: f作用于pair rdd的value部分,

import org.apache.spark.SparkConf;import org.apache.spark.api.java.JavaRDD;import org.apache.spark.api.java.JavaSparkContext;import org.apache.spark.api.java.function.VoidFunction; import java.util.Arrays;import java.util.List; /** *sampleoperator(wi

import org.apache.spark.SparkConf;import org.apache.spark.api.java.JavaRDD;import org.apache.spark.api.java.JavaSparkContext;import org.apache.spark.api.java.function.FlatMapFunction;import org.apache.spark.api.java.function.VoidFunction;import java.

package com.test; import java.util.ArrayList; import java.util.Arrays; import java.util.Iterator; import java.util.List; import java.util.Map; import org.apache.spark.SparkConf; import org.apache.spark.api.java.JavaPairRDD; import org.apache.spark.ap

import org.apache.spark.SparkConf;import org.apache.spark.api.java.JavaRDD;import org.apache.spark.api.java.JavaSparkContext;import org.apache.spark.api.java.function.Function2;import org.apache.spark.api.java.function.VoidFunction; import java.util.

import org.apache.spark.SparkConf;import org.apache.spark.api.java.JavaRDD;import org.apache.spark.api.java.JavaSparkContext;import org.apache.spark.api.java.function.VoidFunction;import java.util.Arrays;import java.util.List; /** * union 算子: * 取两个RD

import org.apache.spark.SparkConf;import org.apache.spark.api.java.JavaRDD;import org.apache.spark.api.java.JavaSparkContext; import java.util.Arrays;import java.util.List; /** * sampleTake 算子: * 先 sample 再 take * 第一个参数:是否可以重复 * 第二个参数:返回take(n) * 第三个

import org.apache.spark.SparkConf;import org.apache.spark.api.java.JavaRDD;import org.apache.spark.api.java.JavaSparkContext; import java.util.Arrays;import java.util.List; /** * take(n) * 将RDD中的前多少数据返回过来,返回结果为数据形式 * */public class TakeOperator { pub

import org.apache.spark.SparkConf;import org.apache.spark.api.java.JavaRDD;import org.apache.spark.api.java.JavaSparkContext;import org.apache.spark.api.java.function.Function; import java.util.Arrays;import java.util.List; /** * saveastextfile 算子: *

import org.apache.spark.SparkConf;import org.apache.spark.api.java.JavaRDD;import org.apache.spark.api.java.JavaSparkContext;import org.apache.spark.api.java.function.Function2;import org.apache.spark.api.java.function.VoidFunction; import java.util.

import org.apache.spark.SparkConf;import org.apache.spark.api.java.JavaRDD;import org.apache.spark.api.java.JavaSparkContext;import org.apache.spark.api.java.function.Function2; import java.util.Arrays;import java.util.List; /** * reduce(fun) 算子: * 每

import org.apache.spark.SparkConf;import org.apache.spark.api.java.JavaRDD;import org.apache.spark.api.java.JavaSparkContext;import org.apache.spark.api.java.function.Function;import org.apache.spark.api.java.function.VoidFunction; import java.util.A

import org.apache.spark.SparkConf;import org.apache.spark.api.java.JavaPairRDD;import org.apache.spark.api.java.JavaSparkContext;import org.apache.spark.api.java.function.VoidFunction;import scala.Tuple2; import java.util.Arrays;import java.util.List

import org.apache.spark.SparkConf;import org.apache.spark.api.java.JavaRDD;import org.apache.spark.api.java.JavaSparkContext;import org.apache.spark.api.java.function.VoidFunction; import java.util.Arrays;import java.util.List; /** * intersection 算子:

import org.apache.spark.SparkConf;import org.apache.spark.api.java.JavaPairRDD;import org.apache.spark.api.java.JavaSparkContext;import org.apache.spark.api.java.function.VoidFunction;import scala.Tuple2; import java.util.Arrays;import java.util.List

import org.apache.spark.SparkConf;import org.apache.spark.api.java.JavaRDD;import org.apache.spark.api.java.JavaSparkContext; import java.util.Arrays;import java.util.List; /** * frist 算子: * * 取RDD的第一个元素 * */public class FristOperator { public static

import org.apache.spark.SparkConf;import org.apache.spark.api.java.JavaRDD;import org.apache.spark.api.java.JavaSparkContext;import org.apache.spark.api.java.function.Function;import org.apache.spark.api.java.function.VoidFunction; import java.util.A

import org.apache.spark.SparkConf;import org.apache.spark.api.java.JavaRDD;import org.apache.spark.api.java.JavaSparkContext;import org.apache.spark.api.java.function.VoidFunction; import java.util.Arrays;import java.util.List; /** * distinct 算子: * 简