Spark学习之路 （三）Spark之RDD

scala> val file = sc.textFile("/spark/hello.txt")

scala> val array = Array(1,2,3,4,5)
array: Array[Int] = Array(1, 2, 3, 4, 5)

scala> val rdd = sc.parallelize(array)
rdd: org.apache.spark.rdd.RDD[Int] = ParallelCollectionRDD[27] at parallelize at <console>:26

scala> 

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

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

    val conf = new SparkConf()
    /**
      * 如果这个参数不设置，默认认为你运行的是集群模式
      * 如果设置成local代表运行的是local模式
      */
    conf.setMaster("local")
    //设置任务名
    conf.setAppName("WordCount")
    //创建SparkCore的程序入口
    val sc = new SparkContext(conf)
    //读取文件 生成RDD
    val file: RDD[String] = sc.textFile("E:\hello.txt")
    //把每一行数据按照，分割
    val word: RDD[String] = file.flatMap(_.split(","))
    //让每一个单词都出现一次
    val wordOne: RDD[(String, Int)] = word.map((_,1))
    //单词计数
    val wordCount: RDD[(String, Int)] = wordOne.reduceByKey(_+_)
    //按照单词出现的次数 降序排序
    val sortRdd: RDD[(String, Int)] = wordCount.sortBy(tuple => tuple._2,false)
    //将最终的结果进行保存
    sortRdd.saveAsTextFile("E:\result")

    sc.stop()
  }

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;

public class SparkWordCountWithJava7 {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf();
        conf.setMaster("local");
        conf.setAppName("WordCount");
        JavaSparkContext sc = new JavaSparkContext(conf);
        JavaRDD<String> fileRdd = sc.textFile("E:\hello.txt");

        JavaRDD<String> wordRDD = fileRdd.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public Iterator<String> call(String line) throws Exception {
                return Arrays.asList(line.split(",")).iterator();
            }
        });

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

        JavaPairRDD<String, Integer> wordCountRDD = wordOneRDD.reduceByKey(new Function2<Integer, Integer, Integer>() {
            @Override
            public Integer call(Integer i1, Integer i2) throws Exception {
                return i1 + i2;
            }
        });

        JavaPairRDD<Integer, String> count2WordRDD = wordCountRDD.mapToPair(new PairFunction<Tuple2<String, Integer>, Integer, String>() {
            @Override
            public Tuple2<Integer, String> call(Tuple2<String, Integer> tuple) throws Exception {
                return new Tuple2<>(tuple._2, tuple._1);
            }
        });

        JavaPairRDD<Integer, String> sortRDD = count2WordRDD.sortByKey(false);

        JavaPairRDD<String, Integer> resultRDD = sortRDD.mapToPair(new PairFunction<Tuple2<Integer, String>, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(Tuple2<Integer, String> tuple) throws Exception {
                return new Tuple2<>(tuple._2, tuple._1);
            }
        });

        resultRDD.saveAsTextFile("E:\result7");

    }
}

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;

public class SparkWordCountWithJava8 {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf();
        conf.setAppName("WortCount");
        conf.setMaster("local");
        JavaSparkContext sc = new JavaSparkContext(conf);

        JavaRDD<String> fileRDD = sc.textFile("E:\hello.txt");
        JavaRDD<String> wordRdd = fileRDD.flatMap(line -> Arrays.asList(line.split(",")).iterator());
        JavaPairRDD<String, Integer> wordOneRDD = wordRdd.mapToPair(word -> new Tuple2<>(word, 1));
        JavaPairRDD<String, Integer> wordCountRDD = wordOneRDD.reduceByKey((x, y) -> x + y);
        JavaPairRDD<Integer, String> count2WordRDD = wordCountRDD.mapToPair(tuple -> new Tuple2<>(tuple._2, tuple._1));
        JavaPairRDD<Integer, String> sortRDD = count2WordRDD.sortByKey(false);
        JavaPairRDD<String, Integer> resultRDD = sortRDD.mapToPair(tuple -> new Tuple2<>(tuple._2, tuple._1));
        resultRDD.saveAsTextFile("E:\result8");

    }