java实现spark常用算子之Union

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;

/**
 * union 算子：
 * 取两个RDD的并集,不去重,会增加partition的数量,同时并行度也会增加
 *
 */
public class UnionOperator {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf().setMaster("local").setAppName("sampleTake");
        JavaSparkContext sc  = new JavaSparkContext(conf);
        List<String> list1 = Arrays.asList("w1","w2","w3","w4","w5");
        List<String> list2 = Arrays.asList("q1","q2","q3","q4","q5");

        JavaRDD<String> list1Rdd = sc.parallelize(list1,2);
        JavaRDD<String> list2Rdd = sc.parallelize(list2);

        //此时result有3个分区
        JavaRDD<String> result = list1Rdd.union(list2Rdd);

        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！