scala - 在scala中没有列表的替代方法

我有一个这样的scala代码

 def avgCalc(buffer: Iterable[Array[String]], list: Array[String]) = {
    val currentTimeStamp = list(1).toLong // loads the timestamp column
    var sum = 0.0
    var count = 0
    var check = false
    import scala.util.control.Breaks._
    breakable {
      for (array <- buffer) {
        val toCheckTimeStamp = array(1).toLong // timestamp column
        if (((currentTimeStamp - 10L) <= toCheckTimeStamp) && (currentTimeStamp >= toCheckTimeStamp)) { // to check the timestamp for 10 seconds difference
          sum += array(5).toDouble // RSSI weightage values
          count += 1
        }

        if ((currentTimeStamp - 10L) > toCheckTimeStamp) {

          check = true
          break

        }
      }
    }
     list :+ sum

  }

我将像这样调用上面的函数

 import spark.implicits._
  val averageDF =
    filterop.rdd.map(_.mkString(",")).map(line => line.split(",").map(_.trim))
      .sortBy(array => array(1), false) // Sort by timestamp
      .groupBy(array => (array(0), array(2))) // group by tag and listner
      .mapValues(buffer => {
        buffer.map(list => {
         avgCalc(buffer, list) // calling the average function
        })
      })
      .flatMap(x => x._2)
      .map(x => findingavg(x(0).toString, x(1).toString.toLong, x(2).toString, x(3).toString, x(4).toString, x(5).toString.toDouble, x(6).toString.toDouble)) // defining the schema through case class
      .toDF // converting to data frame

上面的代码工作正常。但是我需要删除列表。我的上级要求我删除列表，因为列表会降低执行速度。有没有列表的建议吗？
任何帮助将不胜感激。

最佳答案

我想以下解决方案应该可以工作，我试图避免同时传递可迭代和一个数组。

def avgCalc(buffer: Iterable[Array[String]]) = {
  var finalArray = Array.empty[Array[String]]
  import scala.util.control.Breaks._
  breakable {
    for (outerArray <- buffer) {
      val currentTimeStamp = outerArray(1).toLong
      var sum = 0.0
      var count = 0
      var check = false
      var list = outerArray
      for (array <- buffer) {
        val toCheckTimeStamp = array(1).toLong
        if (((currentTimeStamp - 10L) <= toCheckTimeStamp) && (currentTimeStamp >= toCheckTimeStamp)) {
          sum += array(5).toDouble
          count += 1
        }
        if ((currentTimeStamp - 10L) > toCheckTimeStamp) {
          check = true
          break
        }
      }
      if (sum != 0.0 && check) list = list :+ (sum / count).toString
      else list = list :+ list(5).toDouble.toString

      finalArray ++= Array(list)
    }
  }
  finalArray
}

你可以这样称呼它

import sqlContext.implicits._
val averageDF =
  filter_op.rdd.map(_.mkString(",")).map(line => line.split(",").map(_.trim))
    .sortBy(array => array(1), false)
    .groupBy(array => (array(0), array(2)))
    .mapValues(buffer => {
        avgCalc(buffer)
    })
    .flatMap(x => x._2)
    .map(x => findingavg(x(0).toString, x(1).toString.toLong, x(2).toString, x(3).toString, x(4).toString, x(5).toString.toDouble, x(6).toString.toDouble))
    .toDF

我希望这是理想的答案

关于scala - 在scala中没有列表的替代方法，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/45341832/