package com.jiangzeyun.spark.core;
import java.util.Arrays;
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;
/**
*
* @author jiangzeyun
* @brief WordCount 第一个spark程序
*
*/
public class WordCount {
public static void main(String[] args) {
//本地模式
SparkConf conf = new SparkConf().setAppName("WordCount").setMaster("local");
@SuppressWarnings("resource")
JavaSparkContext sc = new JavaSparkContext(conf);
JavaRDD<String> lines = sc.textFile("/usr/local/hadoop/README.txt");
JavaRDD<String> words = lines.flatMap( s -> Arrays.asList(s.split(" ")).iterator());
JavaPairRDD<String, Integer> pairs = words.mapToPair(s -> new Tuple2<String, Integer>(s, 1));
JavaPairRDD<String, Integer> counts = pairs.reduceByKey((a, b) -> a + b);
//如果要实现按单词出现的次数从高低排名,1,首先要tuple的key value值,然后再按key排序,然后再交换过来
JavaPairRDD<Integer, String> tmp = counts.mapToPair(s->new Tuple2<Integer, String>(s._2,s._1)).sortByKey(false);
JavaPairRDD<String, Integer> result = tmp.mapToPair(s->new Tuple2<String, Integer>(s._2,s._1));
result.foreach(a -> System.out.println(a._1+"=>"+a._2()));
sc.stop();
}
}
spark+java1.8+lamda wordCount 实例,并且实现按单词出现的次数的倒序排序
最新推荐文章于 2023-03-28 15:42:02 发布