java實現spark常用算子之Sample

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.VoidFunction;

import java.util.Arrays;
import java.util.List;

/**
 *sampleoperator(withReplacement,fraction,seed) 算子
 *對RDD中的數據進行隨機采樣
 * 第一個參數：boolean類型，表示產生的樣本是否可以重復
 * 第二個參數：代表取樣的比例
 * 第三個參數：代表一個隨機數種子，就是抽樣算法的初始值
 *
 */
public class SampleOperator {
 public static void main(String[] args){
 SparkConf conf = new SparkConf().setMaster("local").setAppName("sample");
 JavaSparkContext sc = new JavaSparkContext(conf);
 List<String> list = Arrays.asList("w1","w2","w3","w4","w5","w6","w7","w8","w9","w10");

 JavaRDD<String> listRdd = sc.parallelize(list);

 JavaRDD<String> sampleRdd = listRdd.sample(false,0.5);

 sampleRdd.foreach(new VoidFunction<String>() {
 @Override
 public void call(String s) throws Exception {
 System.err.println(s);
 }
 });



 }
}

微信掃描下圖二維碼加入博主知識星球,獲取更多大數據、人工智能、算法等免費學習資料哦！