scala一行代码实现经典实例wordcount

 原始代码

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

object WorldCount {
  def main(args: Array[String]): Unit = {
     val conf =new SparkConf()
    //设置本地运行
    conf.setMaster("local")
    conf.setAppName("WC")
    设置上下文对象
    val sc = new SparkContext(conf)

    val lines=sc.textFile("./data/words")
    //切好的单词 hello
    //           scala
    val pairlines = lines.flatMap(line=>{line.split(" ")})
    //(hello,1  )
    val ww=pairlines.map(pairline=>(new Tuple2(pairline,1)))
    //(hello,33)
    val result = ww.reduceByKey((v1:Int,V2:Int) =>(v1+V2))
    result.foreach(tp=>{println(tp)})
    }
}

 进化

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

object WorldCount {
  def main(args: Array[String]): Unit = {
    new SparkContext(new SparkConf().setAppName("WC").setMaster("local")).textFile("./data/words").flatMap(line=>{line.split(" ")}).map(c=>(new Tuple2(c,1))).reduceByKey((v1:Int,V2:Int) =>(v1+V2)).foreach(tp=>(println(tp)))




    }
}

 超级进化

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

object WorldCount {
  def main(args: Array[String]): Unit = {

    
 new SparkContext(new SparkConf().setAppName("WC").setMaster("local")).textFile("./data/words").flatMap(_.split(" ")).map((_,1)).reduceByKey(_+_).foreach(println)



    }
]

 java代码实现

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.*;
import scala.Tuple2;

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

/**
 * Hello world!
 *
 */
public class App {
    public static void main(String[] args) {
//        SparkConf conf = new SparkConf();
//        conf.setMaster("local");
//        conf.setAppName("XXX");
//        JavaSparkContext sc =new JavaSparkContext(conf);
//        JavaRDD<String> lines = sc.textFile("./data/words");
//        JavaRDD<String > words = lines.flatMap(line -> Arrays.asList(line.split(" ")).iterator());
//        JavaPairRDD<String, Integer> pairWords = words.mapToPair(word -> new Tuple2<>(word, 1));
//        JavaPairRDD<String, Integer> result = pairWords.reduceByKey((v1, v2) -> v1 + v2);
//        result.foreach(tp -> System.out.println(tp));

        SparkConf conf = new SparkConf();
        conf.setMaster("local");
        conf.setAppName("xxx");
        JavaSparkContext sc = new JavaSparkContext(conf);
        JavaRDD<String> lines = sc.textFile("./data/words");
        JavaRDD<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public Iterator<String> call(String line) throws Exception {
                return Arrays.asList(line.split(" ")).iterator();
            }
        });


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

        JavaPairRDD<String, Integer> reduce = pairWords.reduceByKey(new Function2<Integer, Integer, Integer>() {
            @Override
            public Integer call(Integer v1, Integer v2) throws Exception {
                return v1 + v2;
            }
        });
        JavaPairRDD<Integer, String> transRDD = reduce.mapToPair(new PairFunction<Tuple2<String, Integer>, Integer, String>() {
            @Override
            public Tuple2<Integer, String> call(Tuple2<String, Integer> tp) throws Exception {
                return new Tuple2<Integer, String>(tp._2, tp._1);
            }
        });
        JavaPairRDD<Integer, String> sortByRDD = transRDD.sortByKey(false);
        JavaPairRDD<String, Integer> result = sortByRDD.mapToPair(new PairFunction<Tuple2<Integer, String>, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(Tuple2<Integer, String> tp) throws Exception {
                return tp.swap();
            }
        });

        result.foreach(new VoidFunction<Tuple2<String, Integer>>() {
            @Override
            public void call(Tuple2<String, Integer> tuple2) throws Exception {
                System.out.println(tuple2);
            }
        });



    }
}