Spark Transformation算子-＞groupByKey

作用在 K，V 格式的 RDD 上。根据 Key 进行分组。作用在（K，V），返回（K， Iterable ）。

1. java

package transformations;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaSparkContext;
import scala.Tuple2;

import java.util.Arrays;


public class GroupByKeyTest {
    public static void main(String[] args) {
        JavaSparkContext context = new JavaSparkContext(
                new SparkConf()
                        .setMaster("local")
                        .setAppName("groupbykey")
        );
        context.setLogLevel("Error");
        context.parallelizePairs(Arrays.asList(
                new Tuple2("科比",24),
                new Tuple2("科比",23),
                new Tuple2("威斯布鲁克",0),
                new Tuple2("保罗",3),
                new Tuple2("保罗",12)
        )).groupByKey().foreach(e-> System.out.println(e));
    }
}

2. scala

package transformation

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


object GroupByKeyTest {
  def main(args: Array[String]): Unit = {
    val context = new SparkContext(
      new SparkConf()
        .setAppName("groupbykey")
        .setMaster("local")
    )
    context.setLogLevel("Error")
    context.parallelize(Array[(String,Int)](
      ("科比",24),
      ("科比", 23),
      ("威斯布鲁克", 0),
      ("保罗", 3),
      ("保罗", 12)
    )).groupByKey().foreach(println)
  }
}