09高级编程之基于排序机制的wordcount程序
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了09高级编程之基于排序机制的wordcount程序相关的知识，希望对你有一定的参考价值。
package sparkcore.java;
import java.util.Arrays;
import java.util.Iterator;
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 org.apache.spark.api.java.function.VoidFunction;
import scala.Tuple2;
/**
* 排序的wordcount程序：根据单词出现的次数进行排序
*/
public class SortWordCount {
public static void main(String[] args) {
// 创建SparkConf和JavaSparkContext
SparkConf conf = new SparkConf().setAppName("SortWordCount").setMaster("local");
JavaSparkContext sc = new JavaSparkContext(conf);
// 创建lines RDD
JavaRDD<String> lines = sc.textFile("test.txt");
// 执行我们之前做过的单词计数
JavaRDD<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
private static final long serialVersionUID = 1L;
@Override
public Iterator<String> call(String t) throws Exception {
return Arrays.asList(t.split(" ")).iterator();
}
});
JavaPairRDD<String, Integer> pairs = words.mapToPair(
new PairFunction<String, String, Integer>() {
private static final long serialVersionUID = 1L;
@Override
public Tuple2<String, Integer> call(String t) throws Exception {
return new Tuple2<String, Integer>(t, 1);
}
});
JavaPairRDD<String, Integer> wordCounts = pairs.reduceByKey(
new Function2<Integer, Integer, Integer>() {
private static final long serialVersionUID = 1L;
@Override
public Integer call(Integer v1, Integer v2) throws Exception {
return v1 + v2;
}
});
// 到这里为止，就得到了每个单词出现的次数
// 但是，问题是，我们的新需求，是要按照每个单词出现次数的顺序，降序排序
// wordCounts RDD内的元素是什么？应该是这种格式的吧：(hello, 3) (you, 2)
// 我们需要将RDD转换成(3, hello) (2, you)的这种格式，才能根据单词出现次数进行排序把！
// 进行key-value的反转映射
JavaPairRDD<Integer, String> countWords = wordCounts.mapToPair(
new PairFunction<Tuple2<String, Integer>, Integer, String>() {
private static final long serialVersionUID = 1L;
@Override
public Tuple2<Integer, String> call(Tuple2<String, Integer> t) throws Exception {
return new Tuple2<Integer, String>(t._2, t._1);
}
});
// 按照key进行排序。注：其实可以使用sortBy()函数来根据自定义排序规则来进行排序，而不用像这里在排序前后进行Key与Value对调
JavaPairRDD<Integer, String> sortedCountWords = countWords.sortByKey(false);
// 再次将value-key进行反转映射
JavaPairRDD<String, Integer> sortedWordCounts = sortedCountWords.mapToPair(
new PairFunction<Tuple2<Integer, String>, String, Integer>() {
private static final long serialVersionUID = 1L;
@Override
public Tuple2<String, Integer> call(Tuple2<Integer, String> t) throws Exception {
return new Tuple2<String, Integer>(t._2, t._1);
}
});
// 到此为止，我们获得了按照单词出现次数排序后的单词计数
// 打印出来
sortedWordCounts.foreach(new VoidFunction<Tuple2<String, Integer>>() {
private static final long serialVersionUID = 1L;
@Override
public void call(Tuple2<String, Integer> t) throws Exception {
System.out.println(t._1 + " : " + t._2);
}
});
// 关闭JavaSparkContext
sc.close();
}
}
package sparkcore.scala
import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
object SortWordCount {
def main(args: Array[String]) {
val conf = new SparkConf()
.setAppName("SortWordCount")
.setMaster("local")
val sc = new SparkContext(conf)
val lines = sc.textFile("test.txt", 1)
val words = lines.flatMap { line => line.split(" ") }
val pairs = words.map { word => (word, 1) }
val wordCounts = pairs.reduceByKey(_ + _)
val countWords = wordCounts.map(wordCount => (wordCount._2, wordCount._1))
val sortedCountWords = countWords.sortByKey(false)
val sortedWordCounts = sortedCountWords.map(sortedCountWord => (sortedCountWord._2, sortedCountWord._1))
sortedWordCounts.foreach(sortedWordCount => println(sortedWordCount._1 + " : " + sortedWordCount._2))
}
}以上是关于09高级编程之基于排序机制的wordcount程序的主要内容，如果未能解决你的问题，请参考以下文章