/**
* sample采样倾斜key单独进行join
*/ JavaPairRDD<Long, String> sampledRDD = userid2PartAggrInfoRDD.sample(false, 0.1, 9); JavaPairRDD<Long, Long> mappedSampledRDD = sampledRDD.mapToPair( new PairFunction<Tuple2<Long,String>, Long, Long>() { private static final long serialVersionUID = 1L; @Override
public Tuple2<Long, Long> call(Tuple2<Long, String> tuple)
throws Exception {
return new Tuple2<Long, Long>(tuple._1, 1L);
} }); JavaPairRDD<Long, Long> computedSampledRDD = mappedSampledRDD.reduceByKey( new Function2<Long, Long, Long>() { private static final long serialVersionUID = 1L; @Override
public Long call(Long v1, Long v2) throws Exception {
return v1 + v2;
} }); JavaPairRDD<Long, Long> reversedSampledRDD = computedSampledRDD.mapToPair( new PairFunction<Tuple2<Long,Long>, Long, Long>() { private static final long serialVersionUID = 1L; @Override
public Tuple2<Long, Long> call(Tuple2<Long, Long> tuple)
throws Exception {
return new Tuple2<Long, Long>(tuple._2, tuple._1);
} }); final Long skewedUserid = reversedSampledRDD.sortByKey(false).take(1).get(0)._2; JavaPairRDD<Long, String> skewedRDD = userid2PartAggrInfoRDD.filter( new Function<Tuple2<Long,String>, Boolean>() { private static final long serialVersionUID = 1L; @Override
public Boolean call(Tuple2<Long, String> tuple) throws Exception {
return tuple._1.equals(skewedUserid);
} }); JavaPairRDD<Long, String> commonRDD = userid2PartAggrInfoRDD.filter( new Function<Tuple2<Long,String>, Boolean>() { private static final long serialVersionUID = 1L; @Override
public Boolean call(Tuple2<Long, String> tuple) throws Exception {
return !tuple._1.equals(skewedUserid);
} }); JavaPairRDD<String, Row> skewedUserid2infoRDD = userid2InfoRDD.filter( new Function<Tuple2<Long,Row>, Boolean>() { private static final long serialVersionUID = 1L; @Override
public Boolean call(Tuple2<Long, Row> tuple) throws Exception {
return tuple._1.equals(skewedUserid);
} }).flatMapToPair(new PairFlatMapFunction<Tuple2<Long,Row>, String, Row>() { private static final long serialVersionUID = 1L; @Override
public Iterable<Tuple2<String, Row>> call(
Tuple2<Long, Row> tuple) throws Exception {
Random random = new Random();
List<Tuple2<String, Row>> list = new ArrayList<Tuple2<String, Row>>(); for(int i = 0; i <; i++) {
int prefix = random.nextInt(100);
list.add(new Tuple2<String, Row>(prefix + "_" + tuple._1, tuple._2));
} return list;
} }); JavaPairRDD<Long, Tuple2<String, Row>> joinedRDD1 = skewedRDD.mapToPair( new PairFunction<Tuple2<Long,String>, String, String>() { private static final long serialVersionUID = 1L; @Override
public Tuple2<String, String> call(Tuple2<Long, String> tuple)
throws Exception {
Random random = new Random();
int prefix = random.nextInt(100);
return new Tuple2<String, String>(prefix + "_" + tuple._1, tuple._2);
} }).join(skewedUserid2infoRDD).mapToPair( new PairFunction<Tuple2<String,Tuple2<String,Row>>, Long, Tuple2<String, Row>>() { private static final long serialVersionUID = 1L; @Override
public Tuple2<Long, Tuple2<String, Row>> call(
Tuple2<String, Tuple2<String, Row>> tuple)
throws Exception {
long userid = Long.valueOf(tuple._1.split("_")[1]);
return new Tuple2<Long, Tuple2<String, Row>>(userid, tuple._2);
} }); JavaPairRDD<Long, Tuple2<String, Row>> joinedRDD2 = commonRDD.join(userid2InfoRDD); JavaPairRDD<Long, Tuple2<String, Row>> joinedRDD = joinedRDD1.union(joinedRDD2); JavaPairRDD<String, String> sessionid2FullAggrInfoRDD = joinedRDD.mapToPair( new PairFunction<Tuple2<Long,Tuple2<String,Row>>, String, String>() { private static final long serialVersionUID = 1L; @Override
public Tuple2<String, String> call(
Tuple2<Long, Tuple2<String, Row>> tuple)
throws Exception {
String partAggrInfo = tuple._2._1;
Row userInfoRow = tuple._2._2; String sessionid = StringUtils.getFieldFromConcatString(
partAggrInfo, "\\|", Constants.FIELD_SESSION_ID); int age = userInfoRow.getInt(3);
String professional = userInfoRow.getString(4);
String city = userInfoRow.getString(5);
String sex = userInfoRow.getString(6); String fullAggrInfo = partAggrInfo + "|"
+ Constants.FIELD_AGE + "=" + age + "|"
+ Constants.FIELD_PROFESSIONAL + "=" + professional + "|"
+ Constants.FIELD_CITY + "=" + city + "|"
+ Constants.FIELD_SEX + "=" + sex; return new Tuple2<String, String>(sessionid, fullAggrInfo);
} });

sample采样倾斜key并单独进行join代码的更多相关文章

  1. MongoDB With Spark遇到的2个错误,不能初始化和sample重复的key

    1.$sample stage could not find a non-duplicate document while using a random cursor 这个问题比较难解决,因为我用mo ...

  2. 图片文档倾斜矫正算法 附完整c代码

    2年前在学习图像算法的时候看到一个文档倾斜矫正的算法. 也就是说能将一些文档图像进行旋转矫正, 当然这个算法一般用于一些文档扫描软件做后处理 或者用于ocr 文字识别做前处理. 相关的关键词: 抗倾斜 ...

  3. 使用随机数以及扩容表进行join代码

    /** * 使用随机数和扩容表进行join */ JavaPairRDD<String, Row> expandedRDD = userid2InfoRDD.flatMapToPair( ...

  4. split().reverse().join()代码解析

    split() 方法用于把一个字符串分割成字符串数组. reverse() 方法用于颠倒数组中元素的顺序. join() 方法用于把数组中的所有元素放入一个字符串.

  5. git 设置 key 到服务器,同步代码不需要输入用户名和密码

    1  ssh-keygen -t rsa 2  vim ~/.ssh/id_rsa.pub 3. 添加到git 服务器,这样同步代码就不需要输入密码

  6. Spark实践 -- 性能优化基础

    性能调优相关的原理讲解.经验总结: 掌握一整套Spark企业级性能调优解决方案:而不只是简单的一些性能调优技巧. 针对写好的spark作业,实施一整套数据倾斜解决方案:实际经验中积累的数据倾斜现象的表 ...

  7. 最完整的数据倾斜解决方案(spark)

    一.了解数据倾斜 数据倾斜的原理: 在执行shuffle操作的时候,按照key,来进行values的数据的输出,拉取和聚合.同一个key的values,一定是分配到一个Reduce task进行处理. ...

  8. spark性能调优06-数据倾斜处理

    1.数据倾斜 1.1 数据倾斜的现象 现象一:大部分的task都能快速执行完,剩下几个task执行非常慢 现象二:大部分的task都能快速执行完,但总是执行到某个task时就会报OOM,JVM out ...

  9. Spark性能调优之解决数据倾斜

    Spark性能调优之解决数据倾斜 数据倾斜七种解决方案 shuffle的过程最容易引起数据倾斜 1.使用Hive ETL预处理数据    • 方案适用场景:如果导致数据倾斜的是Hive表.如果该Hiv ...

随机推荐

  1. Netty入门3之----Decoder和Encoder

    ​ Netty强大的地方,是他能方便的实现自定义协议的网络传输.在上一篇文章中,通过使用Netty封装好的工具类,实现了简单的http服务器.在接下来的文章中,我们看看怎么使用他来搭建自定义协议的服务 ...

  2. Angular4 微信的坑

    1.不要重置对象的引用!(重置只应该在组件或服务的初始化时) why:会使页面产生闪烁 2.不要给图片绑定一个空的值或空的图片引用(如果值从服务器异步过来,那应该在初始化时给它一个默认值) why:会 ...

  3. 最短路径-Dijkstra算法与Floyd算法

    一.最短路径 ①在非网图中,最短路径是指两顶点之间经历的边数最少的路径. AE:1    ADE:2   ADCE:3   ABCE:3 ②在网图中,最短路径是指两顶点之间经历的边上权值之和最短的路径 ...

  4. ZT 类与类之间的四种关系

    csdn上一个好贴子:http://bbs.csdn.net/topics/390646332 类与类之间的四种关系1.依赖(Dependency)   类A在类B中作为一个成员函数的参数或者是返回值 ...

  5. 关于函数指针与c++多态

    原文  https://www.cnblogs.com/zhchngzng/p/4013031.html 虚函数是实现多态的重要元素,请看: class A { public: void a0(){c ...

  6. css3实现 两个点之间有一条线,循环运动

    <!DOCTYPE html> <html> <head lang="en"> <meta charset="UTF-8&quo ...

  7. UVa 1608 - Non-boring sequences

    链接: https://uva.onlinejudge.org/index.php?option=com_onlinejudge&Itemid=8&page=show_problem& ...

  8. CTSC2018 && APIO2018 && SDOI2018R2游记

    Day -? 占个坑先.希望CTSC,APIO别打铁,R2别滚粗QAQ CTSC Day 0 早起坐车睡觉颓废报道颓废 反正游记就是咕懒得写了 Day 1 早上四点被xp的闹钟吵醒(???还两次) 幸 ...

  9. PHP------数组的遍历

    echo current($attr); //取当前元素的value值 echo key($attr); //取当前元素的key next($attr); //将数组里面的指针指向下一个(向下移)pr ...

  10. window.jQuery || document.write("<script src='__PUBLIC__/assets/js/jquery.js'>"+"<"+"/script>")

    今天无意中看到这样一段代码 <script type="text/javascript"> window.jQuery || document.write(" ...