java实现spark常用算子之count

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

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

/**
 * count 算子：
 * 统计一下RDD中有多少数据量
 */
public class CountOperator {
    public static void main(String[] args) {
        SparkConf conf =new SparkConf().setMaster("local").setAppName("count");
        JavaSparkContext sc = new JavaSparkContext(conf);
        List<String> names= Arrays.asList("w1","w2","w3","w4");
        JavaRDD<String> nameRdd = sc.parallelize(names);
        long dataNum = nameRdd.count();
        System.err.println(dataNum);

    }
}

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！