spark-WordCount案例

最新推荐文章于 2023-03-06 19:46:29 发布

reddy_Hu

最新推荐文章于 2023-03-06 19:46:29 发布

阅读量229

点赞数

文章标签： spark

本文链接：https://blog.youkuaiyun.com/reddy_hu/article/details/107825663

版权

本文详细介绍了如何使用Scala、Java及Java Lambda表达式在Spark中实现WordCount算法，包括创建SparkContext、读取数据、切分单词、组合计数、排序及保存结果等关键步骤。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Scala程序

package com.doit.spark.day01

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

object WordCount {
  def main(args: Array[String]): Unit = {
    //创建SparkContext
    val conf = new SparkConf().setAppName("WordCount")
    SparkContext用来创建最原始的RDD得
    val sc: SparkContext = new SparkContext(conf)
    //创建RDD(lazy)
    val lines: RDD[String] = sc.textFile(args(0))
    //Transformation 开始(lazy)
    //切分压平
    val words: RDD[String] = lines.flatMap(_.split(" "))
    //将单词和1组合成新元组
    val wordAndOne: RDD[(String, Int)] = words.map((_, 1))
    //聚合
    val reduced: RDD[(String, Int)] = wordAndOne.reduceByKey(_ + _)
    //排序
    val sorted: RDD[(String, Int)] = reduced.sortBy(_._2, false)
    //transformation结束
    //Action算子,会触发任务执行
    //将数据保存到HDFS
    sorted.saveAsTextFile(args(1))
    //释放资源
    sc.stop()

  }
}

Java程序

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

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

/**
 * Author:   多易教育-胡磊
 * Date:     2020/8/4
 * Description:
 */
public class JavaWordCount {
    public static void main(String[] args) {
        SparkConf sparkConf = new SparkConf().setAppName("JavaWordCount");
        //创建JavaSparkContext
        JavaSparkContext jsc = new JavaSparkContext(sparkConf);
        //使用JavaSparkContext创建RDD
        JavaRDD<String> lines = jsc.textFile(args[0]);
        //调用Transformation
        //切分压平
        JavaRDD<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public Iterator<String> call(String s) throws Exception {
                return Arrays.asList(s.split(" ")).iterator();
            }
        });
        //将单词和1组合起来
        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,先调换kv的顺序 ->vk
        JavaPairRDD<Integer, String> swapped = reduced.mapToPair(new PairFunction<Tuple2<String, Integer>, Integer, String>() {
            @Override
            public Tuple2<Integer, String> call(Tuple2<String, Integer> tuple2) throws Exception {
                return tuple2.swap();
            }
        });
        //再排序
        JavaPairRDD<Integer, String> sorted = swapped.sortByKey(false);
        //再将 vk -> kv
        JavaPairRDD<String, Integer> result = sorted.mapToPair(new PairFunction<Tuple2<Integer, String>, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(Tuple2<Integer, String> integerStringTuple2) throws Exception {
                return integerStringTuple2.swap();
            }
        });
        //触发Action,将数据保存到hdfs
        result.saveAsTextFile(args[1]);
        jsc.stop();


    }
}

JavaLambda程序

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;

/**
 * Author:   多易教育-胡磊
 * Date:     2020/8/4
 * Description:
 */
public class LambdaWordCount {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf().setAppName("LambdaWordCount");
        JavaSparkContext lsc = new JavaSparkContext(conf);
        //通过JavaSparkContext创建JavaRDD
        JavaRDD<String> lines = lsc.textFile(args[0]);
        //切分压平
        JavaRDD<String> words = lines.flatMap(line -> Arrays.stream(line.split(" ")).iterator());
        //将单词和1组合
        JavaPairRDD<String, Integer> wordAndOne = words.mapToPair(w -> Tuple2.apply(w, 1));
        //聚合
        JavaPairRDD<String, Integer> reduced = wordAndOne.reduceByKey((a, b) -> a + b);
        //排序
        JavaPairRDD<String, Integer> sorted = reduced.mapToPair(tp -> tp.swap()).sortByKey(false).mapToPair(tp -> tp.swap());
        //存到hdfs
        sorted.saveAsTextFile(args[1]);




         lsc.stop();
    }
}