java实现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
 *对RDD中的数据进行随机采样
 * 第一个参数：boolean类型，表示产生的样本是否可以重复
 * 第二个参数：代表取样的比例
 * 第三个参数：代表一个随机数种子，就是抽样算法的初始值
 *
 */
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);
            }
        });

    }
}

微信扫描下图二维码加入博主知识星球,获取更多大数据、人工智能、算法等免费学习资料哦！