java實現spark常用算子之collect

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.Function;

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

/**
 * collect 算子：
 * 將集群中其他節點的數據拉去到driver所在的機器上
 * 如果數據量比較大時，容易造成內存溢出
 * foreach遍歷數據是在從節點上執行，collect是在driver機器上執行
 */
public class CollectOpeartor {

    public static void main(String[] args){
        SparkConf conf = new SparkConf().setMaster("local").setAppName("collect");
        JavaSparkContext sc = new JavaSparkContext(conf);
        List<String> names = Arrays.asList("w1","w2","w3","w4","w5");

        JavaRDD<String> nameRdd = sc.parallelize(names);

        JavaRDD<String> tempRdd =nameRdd.map(new Function<String, String>() {
            @Override
            public String call(String s) throws Exception {
                return "001"+s;
            }
        });

        List<String> result = tempRdd.collect();

        for(int i = 0; i < result.size(); i++){
            System.err.println(result.get(i));
        }
    }

}

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！