09、高级编程之基于排序机制的wordcount程序

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[] )
    val ) }
    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))
  }

}

上一篇:hdu 2476(第一道区间dp)


下一篇:基于ICSharpCode.SharpZipLib.Zip的压缩解压缩