1、源数据如下,取出每班成绩的前三名
class1 98
class2 90
class2 92
class1 96
class1 100
class2 89
class2 68
class1 81
class2 90
2.实现代码
package cn.spark.study.core;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Iterator;
import java.util.List;
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.PairFunction;
import org.apache.spark.api.java.function.VoidFunction;
import scala.Tuple2;
/**
* 分组去top3
* @author Administrator
*
*/
public class GroupTop3 {
public static void main(String[] args) {
SparkConf conf = new SparkConf().setAppName("Grouptop3").setMaster("local");
JavaSparkContext sc = new JavaSparkContext(conf);
JavaRDD<String> lines = sc.textFile("E://BigData//sparkdata//score.txt");