filter(func)

作用：过滤。返回一个新的RDD，该RDD由经过func函数计算后返回值为true的输入元素组成。

package com.atguigu

import org.apache.spark.rdd.RDD
import org.apache.spark.{HashPartitioner, Partitioner, SparkConf, SparkContext}

object Trans {
  def main(args: Array[String]): Unit = {

    val conf: SparkConf = new SparkConf().setMaster("local[*]").setAppName("Spark01_Partition")
    //构建spark上下文对象
    val sc = new SparkContext(conf)

    val numRDD: RDD[Int] = sc.makeRDD(List(1,4,3,2))
   //val rdd1: RDD[Int] = numRDD.filter(x => (x%2==0))
   val rdd1: RDD[Int] = numRDD.filter(_%2==0)
    rdd1.collect().foreach(println)

    sc.stop()
  }
}

4
2

package com.atguigu

import org.apache.spark.rdd.RDD
import org.apache.spark.{HashPartitioner, Partitioner, SparkConf, SparkContext}

object Trans {
  def main(args: Array[String]): Unit = {

    val conf: SparkConf = new SparkConf().setMaster("local[*]").setAppName("Spark01_Partition")
    //构建spark上下文对象
    val sc = new SparkContext(conf)

    val numRDD: RDD[String] = sc.makeRDD(List("xiaomi","xiaohong","dazhi"))
   val rdd1: RDD[String] = numRDD.filter(_.contains("xiao"))
    rdd1.collect().foreach(println)

    sc.stop()
  }
}

xiaomi
xiaohong