9 Spark Sample, collect partial results sample, takeordered

Spark provides a random sampling of the result set RDD, which is the ability to get a small subset of the data. There are sample, Takesample, takeordered and other methods.

Import Org.apache.spark.api.java.JavaRDD;
Import Org.apache.spark.api.java.JavaSparkContext;

Import org.apache.spark.sql.SparkSession;

Import java.util.List;
 /** * sampling * @author Wuweifeng wrote on 2018/4/24. */public class Testsample {public static void main (string[] args) {sparksession sparksession = sparksession

        . Builder (). AppName ("Javawordcount"). Master ("local"). Getorcreate ();
        Javasparkcontext javasparkcontext = new Javasparkcontext (Sparksession.sparkcontext ());
        javardd<string> Javardd = Javasparkcontext.textfile ("/users/wuwf/age");
        Take 10% of the data, the random number of seeds themselves set, you can also do not set javardd<string> sample = Javardd.sample (False, 0.1, 1234);
        Long sampledatasize = Sample.count ();
        Long rawdatasize = Javardd.count ();

        System.out.println (Rawdatasize + "and after the sampling:" + sampledatasize);
        Take a specified number of random data list<string> List = Javardd.takesample (false, 10);

        SYSTEM.OUT.PRINTLN (list); //Take the specified number of sorted data list<string> orderlist = javardd.takeordered (10);
    System.out.println (orderlist);
 }
}