java实现spark常用算子之distinct

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;

/**
 * distinct 算子：
 * 简单去重
 *
 */
public class DistinctOperator {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf().setMaster("local").setAppName("distinct");
        JavaSparkContext sc  = new JavaSparkContext(conf);
        List<String> list1 = Arrays.asList("w1","w2","w3","w4","w2");

        JavaRDD<String> list1Rdd = sc.parallelize(list1);

        //此时result有3个分区
        JavaRDD<String> result = list1Rdd.distinct(2);

        result.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！