Spark算子（八）

package com.spark.operator;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import scala.Tuple2;

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

/**
* Created by Administrator on 2017/07/20.
*/
public class CartesianOperator {
public static void main(String[] args) {
SparkConf conf = new SparkConf().setAppName("CartesianOperator").setMaster("local");
JavaSparkContext sc = new JavaSparkContext(conf);
List<String> clothes = Arrays.asList("T恤衫","夹克","皮大衣","衬衫","毛衣");
List<String> trousers = Arrays.asList("西裤","内裤","铅笔裤","皮裤","牛仔裤");
JavaRDD<String> clothesRDD = sc.parallelize(clothes);
JavaRDD<String> trousersRDD = sc.parallelize(trousers);
JavaPairRDD<String,String> pairs = clothesRDD.cartesian(trousersRDD);
for (Tuple2<String,String> result :pairs.collect()){
System.out.println(result);
}
}
}

package com.spark.operator;

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.Function;

public class CollectOperator {

public static void main(String[] args) {
SparkConf conf = new SparkConf().setAppName("ReduceOperator")
.setMaster("local");
JavaSparkContext sc = new JavaSparkContext(conf);

// 有一个集合，里面有1到10，10个数字，现在我们通过reduce来进行累加
List<Integer> numberList = Arrays.asList(1, 2, 3, 4, 5);
JavaRDD<Integer> numbers = sc.parallelize(numberList);

JavaRDD<Integer> doubleNumbers = numbers.map(new Function<Integer, Integer>() {

private static final long serialVersionUID = 1L;

@Override
public Integer call(Integer v) throws Exception {
return v * 2;
}
});

// 用foreach action操作，collect在远程集群上遍历RDD的元素
// 用collect操作，将分布式 的在远程集群里面的数据拉取到本地！！！
// 这种方式不建议使用，如果数据量大，走大量的网络传输
// 甚至有可能OOM内存溢出，通常情况下你会看到用foreach操作
List<Integer> doubleNumberList = doubleNumbers.collect();
for(Integer num : doubleNumberList){
System.out.println(num);
}

sc.close();
}
}

package com.spark.operator;

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;

/**
* Created by Administrator on 2017/07/20.
*/
public class CogroupOperator {
public static void main(String[] args) {
SparkConf conf = new SparkConf().setAppName("CogroupOperator").setMaster("local");
JavaSparkContext sc = new JavaSparkContext(conf);
List<Tuple2<String,String>> studentsList = Arrays.asList(
new Tuple2<String,String>("1","xuruyun"),
new Tuple2<String,String>("2","wangfei"),
new Tuple2<String,String>("3","lixin"));
List<Tuple2<String,String>> scoreList = Arrays.asList(
new Tuple2<String,String>("1","100"),
new Tuple2<String,String>("2","90"),
new Tuple2<String,String>("3","80"),
new Tuple2<String,String>("1","70"),
new Tuple2<String,String>("2","60"),
new Tuple2<String,String>("3","50"));
JavaPairRDD<String,String> students = sc.parallelizePairs(studentsList);
JavaPairRDD<String,String> scores = sc.parallelizePairs(scoreList);
JavaPairRDD<String, Tuple2<Iterable<String>, Iterable<String>>> result = students.cogroup(scores);
result.foreach(new VoidFunction<Tuple2<String, Tuple2<Iterable<String>, Iterable<String>>>>() {
@Override
//cogroup的用法是，根据key进行聚合，如果没有的话，返回null
public void call(Tuple2<String, Tuple2<Iterable<String>, Iterable<String>>> tuple) throws Exception {
System.out.println("id:"+tuple._1);
System.out.println("name:"+tuple._2._1);
System.out.println("score:"+tuple._2._2);
}
});

}
}