Spark-Spark setMaster & WordCount Demo

 Spark setMaster源码

/**
   * The master URL to connect to, such as "local" to run locally with one thread, "local[4]" to
   * run locally with 4 cores, or "spark://master:7077" to run on a Spark standalone cluster.
   */
  def setMaster(master: String): SparkConf = {
    set("spark.master", master)
  }

要连接到的主URL，例如“local”用一个线程在本地运行，“local [ 4 ]”用4个内核在本地运行，或者“Spark : / / master : 7077”用Spark独立集群运行。

 

package cn.rzlee.spark.scala

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

// object相当于静态的
object ScalaWordCount {
  def main(args: Array[String]): Unit = {

    //创建spark配置,设置应用程序名字
    val conf = new SparkConf().setAppName("wordCountApp")

    // 创建spark执行入口
    val sc = new SparkContext()

    // 指定以后从哪里读取数据创建RDD（弹性分布式数据集）
    val lines: RDD[String] = sc.textFile("")
    // 切分压平
    val words: RDD[String] = lines.flatMap(_.split(" "))
    // 将单词和一组合
    val wordAndOne: RDD[(String, Int)] = words.map((_, 1))
    // 按key进行聚合  相同key不变，将value相加
    val reduced: RDD[(String, Int)] = wordAndOne.reduceByKey(_+_)
    // 排序
    val sorted = reduced.sortBy(_._2,false)
    // 将结果保存到HDFS中
    sorted.saveAsTextFile("")
    //释放资源
    sc.stop()
  }
}

 

 

基于排序机制的wordCount

java 版本:

package cn.rzlee.spark.core;

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 org.apache.spark.api.java.function.VoidFunction;
import scala.Tuple2;
import scala.actors.threadpool.Arrays;

/**
 * @Author ^_^
 * @Create 2018/11/3
 */
public class SortWordCount {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf().setAppName("SortWordCount").setMaster("local");
        JavaSparkContext sc = new JavaSparkContext(conf);

        // 创建line RDD
        JavaRDD lines = sc.textFile("C:\\Users\\txdyl\\Desktop\\log\\in\\data.txt", 1);

        // 执行单词计数
        JavaRDD words = lines.flatMap(new FlatMapFunction() {
            @Override
            public Iterable call(String s) throws Exception {
                return Arrays.asList(s.split("\t"));
            }
        });


        JavaPairRDD pair = words.mapToPair(new PairFunction() {
            @Override
            public Tuple2 call(String s) throws Exception {
                return new Tuple2<>(s, 1);
            }
        });

        JavaPairRDD wordCounts = pair.reduceByKey(new Function2() {
            @Override
            public Integer call(Integer v1, Integer v2) throws Exception {
                return v1 + v2;
            }
        });

        // 进行key-value的反转映射
        JavaPairRDD countWords = wordCounts.mapToPair(new PairFunction, Integer, String>() {
            @Override
            public Tuple2 call(Tuple2 t) throws Exception {
                return new Tuple2<>(t._2, t._1);
            }
        });

        // 按照key进行排序
        JavaPairRDD sortedCountWords = countWords.sortByKey(false);

        // 再次进行key-value的反转映射
        JavaPairRDD sortedWordCounts = sortedCountWords.mapToPair(new PairFunction, String, Integer>() {
            @Override
            public Tuple2 call(Tuple2 t) throws Exception {
                return new Tuple2<>(t._2, t._1);
            }
        });


        // 打印结果
        sortedWordCounts.foreach(new VoidFunction>() {
            @Override
            public void call(Tuple2 t) throws Exception {
                System.out.println(t._1 + " appears " + t._2+ " times.");
            }
        });
        // 关闭JavaSparkContext
        sc.close();
    }
}

scala版本:

package cn.rzlee.spark.scala

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

object SortWordCount {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName(this.getClass.getSimpleName).setMaster("local")
    val sc = new SparkContext(conf)
    
    
    val lines = sc.textFile("C:\\Users\\txdyl\\Desktop\\log\\in\\data.txt",1)
    val words: RDD[String] = lines.flatMap(line=>line.split("\t"))
    val pairs: RDD[(String, Int)] = words.map(word=>(word,1))
    val wordCounts: RDD[(String, Int)] = pairs.reduceByKey(_+_)
    val countWords: RDD[(Int, String)] = wordCounts.map(wordCount=>(wordCount._2, wordCount._1))
    val sortedCountWords = countWords.sortByKey(false)
    val sortedWordCounts: RDD[(String, Int)] = sortedCountWords.map(sortedCountWord=>(sortedCountWord._2, sortedCountWord._1))
    sortedWordCounts.foreach(sortedWordCount=>{
      println(sortedWordCount._1+" appear "+ sortedWordCount._2 + " times.")
    })

    sc.stop()
  }

}

 

转载于:https://www.cnblogs.com/RzCong/p/9563509.html