Why functional programming matters (aka MapReduce for humans)

mapreduce.scala

import com.cloudera.crunch._
import com.cloudera.scrunch._

class ScrunchWordCount {
  def wordCount(inputFile: String, outputFile: String) = {
    val pipeline = new Pipeline[ScrunchWordCount]
    pipeline.read(from.textFile(inputFile))
      .flatMap(_.toLowerCase.split("\\W+"))
      .filter(!_.isEmpty())
      .count
      .write(to.textFile(outputFile)) // Word counts
      .map((word, count) => (word.slice(0, 1), count))
      .groupByKey.combine(v => v.sum).materialize
    pipeline.done
  }
}

object ScrunchWordCount {
  def main(args: Array[String]) = {
     new ScrunchWordCount.wordCount(args(0), args(1))
  }
}