spark版wordcount实现

💐💐扫码关注公众号，回复 spark 关键字下载geekbang 原价 90 元 零基础入门 Spark 学习资料💐💐

spark-shell

val wordCounts = textFile.flatMap(line => line.split(" ")).groupByKey(identity).count()
wordCounts.collect()

java/scala

1. 引入依赖包

plugins {
    id 'java'
    id 'scala'
}

repositories {
    maven{ url 'http://maven.aliyun.com/nexus/content/groups/public/'}
}

ext {
    hadoopVersion = "2.7.0" //hadoop版本号
    sparkVersion = "3.0.0" //spark版本号
    scalaVersion = "2.12" //scala版本号
}

dependencies {
    implementation "org.apache.hadoop:hadoop-client:$hadoopVersion"
    implementation "org.apache.spark:spark-core_$scalaVersion:$sparkVersion"
}

代码(java)：

        SparkConf conf = new SparkConf();
        conf.setAppName("WordCountJava2");
        conf.setMaster("local");

        //创建java sc
        JavaSparkContext sc = new JavaSparkContext(conf);
        //加载文本文件
        JavaRDD<String> rdd1 = sc.textFile("README.md");

        //压扁
        JavaRDD<String> rdd2 = rdd1.flatMap(new FlatMapFunction<String, String>() {
            public Iterator<String> call(String s) throws Exception {
                List<String> list = new ArrayList<String>();
                String[] arr = s.split(" ");
                for(String ss :arr){
                    list.add(ss);
                }
                return list.iterator();
            }
        });

        //映射,word -> (word,1)
        JavaPairRDD<String,Integer> rdd3 = rdd2.mapToPair(new PairFunction<String, String, Integer>() {
            public Tuple2<String, Integer> call(String s) throws Exception {
                return new Tuple2<String, Integer>(s,1);
            }
        });

        //reduce化简
        JavaPairRDD<String,Integer> rdd4 = rdd3.reduceByKey(new Function2<Integer, Integer, Integer>() {
            public Integer call(Integer v1, Integer v2) throws Exception {
                return v1 + v2;
            }
        });

        //
        List<Tuple2<String,Integer>> list = rdd4.collect();
        for(Tuple2<String, Integer> t : list){
            System.out.println(t._1() + " : " + t._2());
        }

代码（scala）

object WordCountScala {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setMaster("local").setAppName("WordCountJava2")
    val sc = new SparkContext(conf)
    val rdd: RDD[(String, Int)] = sc.textFile("word.txt", 1)
      .flatMap(_.split(  " "))
      .map((_, 1))
      .reduceByKey(_+_)
    rdd.foreach(println)
  }
}

打成jar包，在yarn上运行

bin/spark-submit \
--master yarn \
--deploy-mode cluster \
--class com.ruby.scaladata.WordCountScala \
/home/mustafa/Documents/IdeaProjects/spark/build/libs/spark-1.0-SNAPSHOT.jar