import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}
object WordCount {
def main(args: Array[String]): Unit = {
val config: SparkConf = new SparkConf().setMaster("local[*]").setAppName("WordCount")
val sc = new SparkContext(config)
// println(sc)
val lines: RDD[String] = sc.textFile("in/word.txt")
val words: RDD[String] = lines.flatMap(x=>x.split(" "))
val wordToOne: RDD[(String, Int)] = words.map(x=>(x,1))
val wordToSum: RDD[(String, Int)] = wordToOne.reduceByKey((x,y)=>(x+y))
val result: Array[(String, Int)] = wordToSum.collect()
for(word <- result) println(word)
// lines.flatMap(_.split(" ")).map((_, 1)).reduceByKey(_+_).collect().foreach(println)
}
}
Scala实现wordcount
最新推荐文章于 2023-11-20 15:31:37 发布