spark helloworld (wordCount实现并按照词频排序)

package main.scala.com.spark.demo.com.com.spark.demo
import org.apache.spark.{SparkContext, SparkConf}
object NewWordCount {
  def main(args: Array[String]) {
    val conf = new SparkConf().setAppName("wordCount").setMaster("local")
    val sc = new SparkContext(conf)
    val rdd = sc.textFile("hdfs://master:9000/data01/words.txt")//your file address
    rdd.cache()
    rdd.flatMap(_.split(" ")).map((_,1)).reduceByKey(_+_).collect().foreach(println)
  }
}

words.txt内容

hello world
hello spark
hello sklearn