spark学习记录（一、scala与java编写wordCount比较）

 添加依赖：

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.12</artifactId>
            <version>2.4.0</version>
        </dependency>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>2.12.8</version>
        </dependency>
        <dependency>
            <groupId>com.thoughtworks.paranamer</groupId>
            <artifactId>paranamer</artifactId>
            <version>2.8</version>
        </dependency>
​

public class JavaWordCount {
    public static void main(String[] args) {
        /**
         * conf:
         * 1.设置spark的运行模式
         * 2.设置spark在webui中显示的application的名称
         * 3.设置当前spark application运行所需要的资源
         *
         * Spark运行模式：
         * 1.local：开发过程中使用本地模式，多用于测试
         * 2.stanalone:Spark自带的资源调度框架，支持分布式搭建
         * 3.yarn：hadoop生态圈的资源调度框架
         */
        SparkConf conf = new SparkConf();
        conf.setMaster("local");
        conf.setAppName("JavaWordCount");
        /**
         * SparkContext是通往集群的唯一通道
         */
        JavaSparkContext sc = new JavaSparkContext(conf);
        JavaRDD<String> lines = sc.textFile("C:/words.txt");
        /**
         * flatMap：进一条数据出多条数据
         */
        JavaRDD<String> words = lines.flatMap(new FlatMapFunction<String, String>() {

            public Iterator<String> call(String line) throws Exception {
                return Arrays.asList(line.split(" ")).iterator();
            }
        });
        /**
         * 将RDD转换成k,v格式
         */
        JavaPairRDD<String, Integer> pairWords = words.mapToPair(new PairFunction<String, String, Integer>() {
            public Tuple2<String, Integer> call(String s) throws Exception {
                return new Tuple2<String, Integer>(s, 1);
            }
        });
        /**
         * reduceByKey
         * 1.先将相同的key分组
         * 2.对每组key对应的value按照逻辑去处理
         */
        JavaPairRDD<String, Integer> reduce = pairWords.reduceByKey(new Function2<Integer, Integer, Integer>() {
            public Integer call(Integer integer, Integer integer2) throws Exception {
                return integer + integer2;
            }
        });
        /**
         * 排序
         * 1.先调换k,v再排序，在调换回来
         * */
        JavaPairRDD<Integer, String> mapToPair = reduce.mapToPair(new PairFunction<Tuple2<String, Integer>, Integer, String>() {
            public Tuple2<Integer, String> call(Tuple2<String, Integer> tuple) throws Exception {
                return tuple.swap();
            }
        });
        JavaPairRDD<Integer, String> sortByKey = mapToPair.sortByKey();

        JavaPairRDD<String, Integer> result = sortByKey.mapToPair(new PairFunction<Tuple2<Integer, String>, String, Integer>() {
            public Tuple2<String, Integer> call(Tuple2<Integer, String> tuple) throws Exception {
                return tuple.swap();
            }
        });
        result.foreach(new VoidFunction<Tuple2<String, Integer>>() {
            public void call(Tuple2<String, Integer> stringIntegerTuple2) throws Exception {
                System.out.println(stringIntegerTuple2);
            }
        });

        sc.stop();
    }
}

object ScalaWordCount {
  def main(args: Array[String]): Unit = {
    //    代码简化
    //    val conf = new SparkConf()
    //    conf.setMaster("local").setAppName("ScalaWordCount")
    //    val sc = new SparkContext(conf)
    //    sc.textFile("C:/words.txt").flatMap(_.split(" ")).map((_,1)).reduceByKey(_+_).foreach(println)
    //    sc.stop()

    //    spark配置
    val conf = new SparkConf()
    conf.setMaster("local").setAppName("ScalaWordCount")
    val sc = new SparkContext(conf)
    //    读数据
    val lines = sc.textFile("C:/words.txt")
    //    分割数据
    val words = lines.flatMap(line => {line.split(" ")})
    //    计数
    val pairWords = words.map(word => {new Tuple2(word, 1)})

    val result = pairWords.reduceByKey((v1: Int, v2: Int) => {v1 + v2})
    //排序,按照tuple中的第1位升序排序
    result.sortBy(tuple=>{tuple._2}).foreach(println)
    sc.stop()


  }
}