java實現spark常用算子之filter

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 org.apache.spark.api.java.function.VoidFunction;

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

/**
 * filter 算子使用
 * 通過函數篩選出需要的數據元素，返回true表示保留，返回false表示拋棄
 */
public class FilterOperator {
    public static void main(String[] args){
        SparkConf conf = new SparkConf().setMaster("local").setAppName("filter");
        JavaSparkContext sc = new JavaSparkContext(conf);
        List<Integer> names = Arrays.asList(12,56,5,14,44);
        JavaRDD<Integer> nameRdd = sc.parallelize(names);
        JavaRDD<Integer> result = nameRdd.filter(new Function<Integer, Boolean>() {
            @Override
            public Boolean call(Integer integer) throws Exception {
                if(integer<10) {
                    return false;
                }
                return true;
            }
        });

        result.foreach(new VoidFunction<Integer>() {
            @Override
            public void call(Integer integer) throws Exception {
                System.err.println("filter算子:"+integer);
            }
        });

    }
}

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！