Spark Scala、Java、Java_Lambda写WordCount案例

目录

Spark Scala

Java

java_Lambda

提交

---

Spark Scala

package com.doit.Spark.day01

import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}

object SparkRDD {
  def main(args: Array[String]): Unit = {
    //神奇的大集合
    val conf: SparkConf = new SparkConf().setAppName("WordCount")
    //创建SparkContext
    val sc: SparkContext = new SparkContext(conf)
    //创建RDD
    val lines: RDD[String] = sc.textFile(args(0))
    //调用RDD的Transformation（）方法
    //调用Transformation转换算子后悔生成一个新的RDD
    //切分压平  Transformation开始
    val words: RDD[String] = lines.flatMap(_.split(" "))
    //将单词和1 组合
    val wordAndOne: RDD[(String, Int)] = words.map((_, 1))
    //按照key进行聚合，分组聚合，reduceByKey 可以先局部聚合，然后再全局聚合
    val reduces: RDD[(String, Int)] = wordAndOne.reduceByKey(_ + _) //key相同的value相加，key不变
    //按照出现次数进行排序
    val sorted: RDD[(String, Int)] = reduces.sortBy(_._2, false)
    //Transformation结束，Transformation的代码都是在Action开始执行
    //写出到hdfs
    //调用Action行动算子
    sorted.saveAsTextFile(args(1))
    //释放资源
    sc.stop();
  }
}

------------------------------------------------------------------------------------------
import org.apache.spark.{SparkConf, SparkContext}

object OneLineWordCount {
  def main(args: Array[String]): Unit = {
    val sc: SparkContext = new SparkContext(new SparkConf().setAppName("WordCount"))
    sc
      .textFile(args(0))
      .flatMap(_.split(" "))
      .map((_, 1))
      .reduceByKey(_ + _)
      .sortBy(_._2, false)
      .saveAsTextFile(args(1))
    //释放资源
    sc.stop();
  }
}

Java

package com.doit.Spark.day01;

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 org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFunction;
import scala.Tuple2;

import java.util.Arrays;
import java.util.Iterator;

/**
 * @Classname SparkRdd
 * @Date 2020/11/22 17:42
 * @Created by BaiYE
 * @Description
 */
public class SparkRdd {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf().setAppName("WordCount");
        /**
         *创建JavaSparkContext
         */
        JavaSparkContext jsc = new JavaSparkContext(conf);

        //创建JavaRDD
        JavaRDD<String> lines = jsc.textFile(args[0]);
        //调用Transformation
        //切割字符串
        JavaRDD<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public Iterator<String> call(String line) throws Exception {
                return Arrays.asList(line.split(" ")).iterator();   //将一行切分成多行，然后放进list中，再转成iterator，数组无法转iterator
            }
        });

        //单词和一拼接,调用mapToPair
        JavaPairRDD<String, Integer> wordAndOne = words.mapToPair(new PairFunction<String, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(String s) throws Exception {
                return Tuple2.apply(s, 1);
            }
        });

        //分组聚合
        JavaPairRDD<String, Integer> reduced = wordAndOne.reduceByKey(new Function2<Integer, Integer, Integer>() {
            @Override
            public Integer call(Integer v1, Integer v2) throws Exception {
                return v1 + v2;
            }
        });

        //排序
            //java只能对key进行排序，所以需要将key和value换位置
        JavaPairRDD<Integer, String> swapped = reduced.mapToPair(new PairFunction<Tuple2<String, Integer>, Integer, String>() {
            @Override
            public Tuple2<Integer, String> call(Tuple2<String, Integer> tp) throws Exception {
                // return Tuple2.apply(tp._2,tp._1);
                return tp.swap();
            }
        });
        /**
         * 按照key进行降序排序
         */
        JavaPairRDD<Integer, String> sorted = swapped.sortByKey(false);
        
        
        //再将key和value的位置换回来
        JavaPairRDD<String, Integer> resault = sorted.mapToPair(new PairFunction<Tuple2<Integer, String>, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(Tuple2<Integer, String> tp) throws Exception {
                return tp.swap();
            }
        });

        //写出，位置由main方法传入
        resault.saveAsTextFile(args[1]);

        //释放资源
        jsc.stop();
    }
}

Java_Lambda

package com.doit.Spark.day01;

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;

/**
 * @Classname lambda
 * @Date 2020/11/22 22:09
 * @Created by BaiYE
 * @Description
 */
public class lambdaRdd {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf().setAppName("WordCount");
        //创建JavaContext
        JavaSparkContext jsc = new JavaSparkContext(conf);
        //创建JavaRDD，指定文件读取位置，由main方法传入
        JavaRDD<String> lines = jsc.textFile(args[0]);
        //切割字符串，放入list中，并转成iterator
        JavaRDD<String> word = lines.flatMap(line -> Arrays.asList(line.split(" ")).iterator());
        //将单词和一组合
        JavaPairRDD<String, Integer> wordAndOne = word.mapToPair(w -> Tuple2.apply(w, 1));
        //分组聚合
        JavaPairRDD<String, Integer> reduced = wordAndOne.reduceByKey((a, b) -> a + b);
        //排序，Java只能对key进行排序，需要调换key和value的位置
        JavaPairRDD<Integer, String> swapped = reduced.mapToPair(tp -> tp.swap());
        //按照单词出现次数降序排序
        JavaPairRDD<Integer, String> sorted = swapped.sortByKey(false);
        //排完序后将key和value位置再换回来
        JavaPairRDD<String, Integer> result = sorted.mapToPair(tp -> tp.swap());
        //写出，位置由main方法传入
        result.saveAsTextFile(args[1]);
        //释放资源
        jsc.stop();
    }
}

提交

将代码打成.jar包，提交到任意一台有Spark的机器，运行即可

[root@linux01 ~]# /opt/apps/spark-3.0.1-bin-hadoop3.2/bin/spark-submit --master spark://linux01:7077 --executor-memory 1g --total-executor-cores 4 -class com.doit.Spark.day01.lambdaRdd /root/SparkTest-1.0-SNAPSHOT.jar hdfs://linux01:8020/word.txt hdfs:/linux01:8020/output/