0

使用 Scalding 我试图找到相似字符串对之间的编辑距离。总而言之,我在 CSV 文件中有 10 000 000 个字符串。为了减少计算,我使用以下算法:

  1. 使用前三个字符作为键将所有字符串分组
  2. 在每组中生成两个字符串的组合
  3. 查找每个组中每对字符串的编辑距离(参见下面的代码)

当我在 HDFS 上运行此算法时,它适用于 1 000 000 个字符串。使用 10 000 000 个字符串,节点管理器抱怨我的“映射”作业尝试分配比节点更多的物理内存。.groupBy('key) { _.mapList ...}我知道当在代码中创建大量组合时会发生这种情况。当然,这个算法并不能真正扩展。

请建议其他方法来减少此任务的计算。

import cascading.tuple.Fields
import com.twitter.scalding._

class Proto1(args: Args) extends Job(args) {
  val outputStr = "tmp/out.txt"
  val output = TextLine(outputStr)

  val wordsList = List(
    ("aaaa"),
    ("aaaa"),
    ("aaaad"),
    ("aaaab"),
    ("aaabb"),
    ("aabbcc"),
    ("aaabccdd"),
    ("aaabbccdde"),
    ("aaabbddd"),
    ("bbbb"),
    ("bbbb"),
    ("bbbaaa"),
    ("bbaaabb"),
    ("bbbcccc"),
    ("bbbddde"),
    ("bbbdddd"),
    ("bbbdddf"),
    ("bbbdddd"),
    ("ccccc"),
    ("cccaaa"),
    ("ccccaabbb"),
    ("ccbbbddd"),
    ("cdddeee"),
    ("ddd"),
    ("ddd")
    )

  val orderedPipe =
    IterableSource[(String)](wordsList, ('word))
      .map('word -> 'key) { word: String => word.take(3) }
      .debug
      //.groupBy('key) { _.toList[String]('word -> 'list) }
      //.debug
      .groupBy('key) { _.mapList[String, List[(String, String, Int)]]('word -> 'list)(editDistances) }
      .filterNot('key, 'list) { fields: (String, List[(String, String, Int)]) =>
        val (key, list) = fields
        list.isEmpty
      }
      .flatMapTo('list -> ('str1, 'str2, 'dist)) {list:List[(String, String, Int)] => list  }
      .debug
      //.write(output)
      .write(Csv(outputStr))

  def editDistances(list: List[String]): List[(String, String, Int)] = {

    val resultList = list.combinations(2).toList.map(x => (x(0), x(1), editDistance(x(0), x(1))))
        //println(resultList+"\n")
    val result = resultList.filter(x => x._3 <= 1)
    result
  }

  def editDistance(a: String, b: String): Int = {

    import scala.math.min

    def min3(x: Int, y: Int, z: Int) = min(min(x, y), z)

    val (m, n) = (a.length, b.length)

    val matrix = Array.fill(m + 1, n + 1)(0)

    for (i <- 0 to m; j <- 0 to n) {

      matrix(i)(j) = if (i == 0) j
      else if (j == 0) i
      else if (a(i - 1) == b(j - 1)) matrix(i - 1)(j - 1)
      else min3(
        matrix(i - 1)(j) + 1,
        matrix(i)(j - 1) + 1,
        matrix(i - 1)(j - 1) + 1)
    }

    matrix(m)(n)
  }

}

有任何想法吗?

4

0 回答 0