spark统计spark开头单词个数

object Test3 {
  System.setProperty("hadoop.home.dir","d://software/hadoop-2.9.2")
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setMaster("local[2]").setAppName("sort")
    val sc = new SparkContext(conf)

    sc.textFile("D:\\大数据课件\\在线计算\\spark文档\\spark课件\\core\\data\\words.txt")
      .flatMap(line => line.split(" "))
      .filter(word => word.startsWith("spark"))
      .map(word => (word,1))
      .reduceByKey((x,y) => x+y)
      .foreach(println)
  }
}