package sparkcore

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

object Demo05Sample {
  def main(args: Array[String]): Unit = {
    val conf: SparkConf = new SparkConf().setAppName("Sample").setMaster("local")

    val sc = new SparkContext(conf)

    val students: RDD[String] = sc.textFile("data/students.txt")

    /**
      * sample:抽样算子
      */
    val sampleRDD: RDD[String] = students.sample(false,0.1)

    sampleRDD.foreach(println)
  }

}

sample