（九）groupByKey,reduceByKey,sortByKey算子-Java&Python版Spark

groupByKey,reduceByKey,sortByKey算子

 

视频教程：

1、优酷

2、 YouTube

 

1、groupByKey

 groupByKey是对每个key进行合并操作，但只生成一个sequence，groupByKey本身不能自定义操作函数。

java：

package com.bean.spark.trans;

import java.util.Arrays;
import java.util.List;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaSparkContext;

import scala.Tuple2;

public class TraGroupByKey {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf();
        conf.setMaster("local");
        conf.setAppName("union");
        System.setProperty("hadoop.home.dir", "D:/tools/spark-2.0.0-bin-hadoop2.6");
        JavaSparkContext sc = new JavaSparkContext(conf);
        List<Tuple2<String, Integer>> list = Arrays.asList(new Tuple2<String, Integer>("cl1", 90),
                new Tuple2<String, Integer>("cl2", 91),new Tuple2<String, Integer>("cl3", 97),
                new Tuple2<String, Integer>("cl1", 96),new Tuple2<String, Integer>("cl1", 89),
                new Tuple2<String, Integer>("cl3", 90),new Tuple2<String, Integer>("cl2", 60));
        JavaPairRDD<String, Integer> listRDD = sc.parallelizePairs(list);
        JavaPairRDD<String, Iterable<Integer>> results  = listRDD.groupByKey();
        System.out.println(results.collect());
        sc.close();
    }
}

python：

# -*- coding:utf-8 -*-

from pyspark import SparkConf
from pyspark import SparkContext
import os

if __name__ == '__main__':
    os.environ["SPARK_HOME"] = "D:/tools/spark-2.0.0-bin-hadoop2.6"
    conf = SparkConf().setMaster('local').setAppName('group')
    sc = SparkContext(conf=conf)
    data = [('tom',90),('jerry',97),('luck',92),('tom',78),('luck',64),('jerry',50)]
    rdd = sc.parallelize(data)
    print rdd.groupByKey().map(lambda x: (x[0],list(x[1]))).collect()

注意：当采用groupByKey时，由于它不接收函数，spark只能先将所有的键值对都移动，这样的后果是集群节点之间的开销很大，导致传输延时。

整个过程如下：

因此，在对大数据进行复杂计算时，reduceByKey优于groupByKey。

另外，如果仅仅是group处理，那么以下函数应该优先于 groupByKey ：

（1）、combineByKey 组合数据，但是组合之后的数据类型与输入时值的类型不一样。

（2）、foldByKey合并每一个 key 的所有值，在级联函数和“零值”中使用。

2、reduceByKey

对数据集key相同的值，都被使用指定的reduce函数聚合到一起。

java：

 

package com.bean.spark.trans;

import java.util.Arrays;
import java.util.List;

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.Function2;

import scala.Tuple2;

public class TraReduceByKey {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf();
        conf.setMaster("local");
        conf.setAppName("reduce");
        System.setProperty("hadoop.home.dir", "D:/tools/spark-2.0.0-bin-hadoop2.6");
        JavaSparkContext sc = new JavaSparkContext(conf);
        List<Tuple2<String, Integer>> list = Arrays.asList(new Tuple2<String, Integer>("cl1", 90),
                new Tuple2<String, Integer>("cl2", 91),new Tuple2<String, Integer>("cl3", 97),
                new Tuple2<String, Integer>("cl1", 96),new Tuple2<String, Integer>("cl1", 89),
                new Tuple2<String, Integer>("cl3", 90),new Tuple2<String, Integer>("cl2", 60));
        JavaPairRDD<String, Integer> listRDD = sc.parallelizePairs(list);
        JavaPairRDD<String, Integer> results = listRDD.reduceByKey(new Function2<Integer, Integer, Integer>() {
            @Override
            public Integer call(Integer s1, Integer s2) throws Exception {
                // TODO Auto-generated method stub
                return s1 + s2;
            }
        });
        System.out.println(results.collect());
sc.close();    
}
}

python：

# -*- coding:utf-8 -*-

from pyspark import SparkConf
from pyspark import SparkContext
import os
from operator import add
if __name__ == '__main__':
    os.environ["SPARK_HOME"] = "D:/tools/spark-2.0.0-bin-hadoop2.6"
    conf = SparkConf().setMaster('local').setAppName('reduce')
    sc = SparkContext(conf=conf)
    data = [('tom',90),('jerry',97),('luck',92),('tom',78),('luck',64),('jerry',50)]
    rdd = sc.parallelize(data)        
print rdd.reduceByKey(add).collect()
sc.close()

当采用reduceByKey时，Spark可以在每个分区移动数据之前将待输出数据与一个共用的key结合。 注意在数据对被搬移前同一机器上同样的key是怎样被组合的。

 

3、sortByKey

通过key进行排序。

java:

package com.bean.spark.trans;

import java.util.Arrays;
import java.util.List;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaSparkContext;

import scala.Tuple2;

public class TraSortByKey {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf();
        conf.setMaster("local");
        conf.setAppName("sort");
        System.setProperty("hadoop.home.dir", "D:/tools/spark-2.0.0-bin-hadoop2.6");
        JavaSparkContext sc = new JavaSparkContext(conf);
        List<Tuple2<Integer, String>> list = Arrays.asList(new Tuple2<Integer,String>(3,"Tom"),
                new Tuple2<Integer,String>(2,"Jerry"),new Tuple2<Integer,String>(5,"Luck")
                ,new Tuple2<Integer,String>(1,"Spark"),new Tuple2<Integer,String>(4,"Storm"));
        JavaPairRDD<Integer,String> rdd = sc.parallelizePairs(list);
        JavaPairRDD<Integer, String> results = rdd.sortByKey(false);
        System.out.println(results.collect());
      sc.close()  
    }
}    

python:

#-*- coding:utf-8 -*-
if __name__ == '__main__':
    os.environ["SPARK_HOME"] = "D:/tools/spark-2.0.0-bin-hadoop2.6"
    conf = SparkConf().setMaster('local').setAppName('reduce')
    sc = SparkContext(conf=conf)
    data = [(5,90),(1,92),(3,50)]
    rdd = sc.parallelize(data) 
print rdd.sortByKey(False).collect()
sc.close()