Scala Map类代码示例

//设置package包名称以及导入依赖的类
package com.inneractive.cerberus

import java.io.{File, FileInputStream}
import java.util
import javax.xml.transform.stream.StreamSource

import org.dmg.pmml.{FieldName, Model, PMML}
import org.jpmml.evaluator.{EvaluatorUtil, FieldValue, ModelEvaluator, ModelEvaluatorFactory}
import org.jpmml.model.JAXBUtil

import scala.collection.Map
import scala.util.Try



class LRPmmlEvaluator(modelLocation: String, threshold: Option[Double]) {

  val inputStream = new FileInputStream(new File(modelLocation, "/model/PMML/PMML.xml"))
  val pmmModel: PMML = JAXBUtil.unmarshalPMML(new StreamSource(inputStream))

  val evaluatorFactory: ModelEvaluatorFactory = ModelEvaluatorFactory.newInstance()
  val evaluator: ModelEvaluator[_ <: Model] = evaluatorFactory.newModelManager(pmmModel)
  val activeFields: util.List[FieldName] = evaluator.getActiveFields
  val targetFields: util.List[FieldName] = EvaluatorUtil.getTargetFields(evaluator)
  val outputFields: util.List[FieldName] = EvaluatorUtil.getOutputFields(evaluator)

  def arguments(eval: FieldName => (FieldName, FieldValue)) = (activeFields map eval).toMap

  def getResults(result: java.util.Map[FieldName, _]) = {
    val targets = targetFields map (f => EvaluatorUtil.decode(result.get(f)))
    val outputs = outputFields map (f => result.get(f))
    Tuple3(targets.head.asInstanceOf[Double], outputs.head.asInstanceOf[Double], outputs(1).asInstanceOf[Double])
  }

  def callEvaluator(params : Map[FieldName, _]) = getResults(evaluator.evaluate(params))

  def predict(features: Features) = Try {
    val r = callEvaluator(arguments((f: FieldName) => {
      val value = features.vector(f.getValue)
      val activeValue = evaluator.prepare(f, value)
      (f, activeValue)
    }))
    new Prediction("", if (r._1 == 0.0) true else false, if (r._1 == 0) r._2 else r._3)
  }
} 

//设置package包名称以及导入依赖的类
package  com.highperformancespark.examples.goldilocks

import org.apache.spark.HashPartitioner
import org.apache.spark.rdd.RDD

import scala.collection.Map
import scala.reflect.ClassTag

object RDDJoinExamples {

 
 //tag::coreBroadCast[]
 def manualBroadCastHashJoin[K : Ordering : ClassTag, V1 : ClassTag,
 V2 : ClassTag](bigRDD : RDD[(K, V1)],
  smallRDD : RDD[(K, V2)])= {
  val smallRDDLocal: Map[K, V2] = smallRDD.collectAsMap()
  bigRDD.sparkContext.broadcast(smallRDDLocal)
  bigRDD.mapPartitions(iter => {
   iter.flatMap{
    case (k,v1 ) =>
     smallRDDLocal.get(k) match {
      case None => Seq.empty[(K, (V1, V2))]
      case Some(v2) => Seq((k, (v1, v2)))
     }
   }
  }, preservesPartitioning = true)
 }
 //end:coreBroadCast[]
} 

//设置package包名称以及导入依赖的类
package org.apache.spark.lineage.rdd

import org.apache.spark.OneToOneDependency
import org.apache.spark.lineage.LineageContext
import org.apache.spark.rdd.ParallelCollectionRDD

import scala.collection.Map
import scala.reflect._

private[spark] class ParallelCollectionLRDD[T: ClassTag](
    @transient lc: LineageContext,
    @transient data: Seq[T],
    numSlices: Int,
    locationPrefs: Map[Int, Seq[String]])
  extends ParallelCollectionRDD[T](lc.sparkContext, data, numSlices, locationPrefs)
  with Lineage[T] {

  override def lineageContext = lc

  override def ttag: ClassTag[T] = classTag[T]

  override def tapRight(): TapLRDD[T] = {
    val tap = new TapParallelCollectionLRDD[T](lineageContext,  Seq(new OneToOneDependency(this)))
    setTap(tap)
    setCaptureLineage(true)
    tap
  }
} 

//设置package包名称以及导入依赖的类
package mapdomain.street

import base.{ LazyLoggerSupport, MeterSupport }
import mapdomain.graph._
import mapdomain.repository.street.{ StreetRepositorySupport, StreetVertexRepository }
import mapdomain.utils.GraphUtils

import scala.collection.Map
import scala.collection.concurrent.TrieMap

trait StreetGraphContainer extends GeoGraphContainer[StreetEdge, StreetVertex[StreetEdge]] {
  def findNearestStreets(coordinate: Coordinate, radius: Double): List[StreetEdge]
  def vertices: List[StreetVertex[StreetEdge]]
}

case class LazyStreetGraphContainer() extends StreetGraphContainer with StreetRepositorySupport {

  protected val vertexById = new TrieMap[Long, StreetVertex[StreetEdge]]()
  protected val totalVertices: Long = streetVertexRepository.totalVertices

  override def vertices: List[StreetVertex[StreetEdge]] = {
    if (totalVertices != vertexById.size) {
      vertexById.keys
    }
    StreetVertexRepository.findAll
  }

  override def findNearestStreets(coordinate: Coordinate, radius: Double): List[StreetEdge] = streetEdgeRepository.findNearestStreets(coordinate, radius)

  override def findNearest(coordinate: Coordinate): Option[StreetVertex[StreetEdge]] = streetVertexRepository.findNearest(coordinate)

  
  def purgeStreets: UnsavedStreetGraphContainer = withTimeLogging({
    logger.info(s"Purge the unsaved street graph in order to get a connected graph")
    GraphUtils.getConnectedComponent[StreetEdgeUnsaved, UnsavedStreetVertex, UnsavedStreetGraphContainer](this, UnsavedStreetGraphContainer.apply)
  }, (time: Long) ? logger.info(s"Street graph was purged in $time ms."))

} 

//设置package包名称以及导入依赖的类
package dagger.ml

import scala.util.Random
import scala.collection.Map

/**
 * Created by narad on 8/8/14.
 */
case class Prediction[T](label2score: Map[T, Float], entropy: Double = 0.0) {

  def randomMaxLabel(random: Random) = {
    assert(maxLabels.nonEmpty)
    val r = random.nextInt(maxLabels.size)
    maxLabels(r)
  }

  lazy val maxScore: Double = label2score.maxBy(_._2)._2

  lazy val maxLabels: Seq[T] = label2score.toSeq.filter(_._2 == maxScore).map(_._1)

  def maxLabelsWithinThreshold(threshold: Double, optionLimit: Int): Seq[(T, Float)] = {
    val withinThreshold = label2score.toSeq.filter(_._2 >= maxScore - threshold).map {
      x => ((x._1, (x._2 - maxScore).toFloat))
    }
    withinThreshold.sortBy(-_._2).take(optionLimit)
  }
  lazy val maxLabel = maxLabels.head

  override def toString = {
    "Prediction:\n" +
      label2score.keys.map { k =>
        "  %s: %f".format(k, label2score(k))
      }
  }
} 

//设置package包名称以及导入依赖的类
package dagger.ml
import scala.reflect.ClassTag
import scala.collection.Map
import scala.collection.mutable.HashMap

class PassiveAggressiveUpdate[T: ClassTag] extends PerceptronUpdateRule {

  override def update(instance: Instance[T], classifier: AROWClassifier[T], options: AROWOptions): Unit = {
    val prediction = classifier.predict(instance)
    val temp = instance.correctLabels.map(l => (l, prediction.label2score(l))).toArray.sortBy(_._2)
    if (temp.isEmpty) println("No Correct Labels found for: \n" + instance)
    val weightVectors = classifier.weights
    val cachedWeightVectors = classifier.cachedWeights
    val maxLabel = prediction.maxLabel
    val maxScore = prediction.maxScore
    val (minCorrectLabel, minCorrectScore) = temp.head
    val labelList = instance.labels
    val iMaxLabel = labelList.indexOf(maxLabel)
    val icost = instance.costOf(maxLabel)
    val maxWeightLabel = instance.weightLabels(iMaxLabel)
    val iMinCorrectLabel = labelList.indexOf(minCorrectLabel)
    val minCorrectWeightLabel = instance.weightLabels(iMinCorrectLabel)
    val loss = (maxScore - minCorrectScore + math.sqrt(instance.costOf(maxLabel))).toFloat
    val norm = 2 * (AROW.dotMap(instance.feats(iMinCorrectLabel), instance.feats(iMinCorrectLabel)))
    val factor = loss / (norm + (1.0f / (2 * options.SMOOTHING.toFloat)))

    AROW.add(weightVectors(maxWeightLabel), instance.feats(iMaxLabel), -1.0f * factor)
    AROW.add(weightVectors(minCorrectWeightLabel), instance.feats(iMinCorrectLabel), factor)
    if (options.AVERAGING) {
      AROW.add(cachedWeightVectors(maxWeightLabel), instance.feats(iMaxLabel), -1.0f * factor * classifier.averagingCounter)
      AROW.add(cachedWeightVectors(minCorrectWeightLabel), instance.feats(iMinCorrectLabel), factor * classifier.averagingCounter)
    }
  }
} 

//设置package包名称以及导入依赖的类
package org.sparksamples.decisiontree

import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.mllib.tree.DecisionTree
import org.apache.spark.rdd.RDD
import org.sparksamples.Util

import scala.collection.Map
import scala.collection.mutable.ListBuffer


object DecisionTreeUtil {

  def getTrainTestData(): (RDD[LabeledPoint], RDD[LabeledPoint]) = {
    val recordsArray = Util.getRecords()
    val records = recordsArray._1
    val first = records.first()
    val numData = recordsArray._2

    println(numData.toString())
    records.cache()
    print("Mapping of first categorical feature column: " +  Util.get_mapping(records, 2))
    var list = new ListBuffer[Map[String, Long]]()
    for( i <- 2 to 9){
      val m = Util.get_mapping(records, i)
      list += m
    }
    val mappings = list.toList
    var catLen = 0
    mappings.foreach( m => (catLen +=m.size))

    val numLen = records.first().slice(11, 15).size
    val totalLen = catLen + numLen

    val data = {
      records.map(r => LabeledPoint(Util.extractLabel(r), Util.extractFeatures(r, catLen, mappings)))
    }
    val data_dt = {
      records.map(r => LabeledPoint(Util.extractLabel(r), Util.extract_features_dt(r)))
    }

    val splits = data_dt.randomSplit(Array(0.8, 0.2), seed = 11L)
    val training = splits(0).cache()
    val test = splits(1)
    return (training, test)
  }

  def evaluate(train: RDD[LabeledPoint],test: RDD[LabeledPoint],
               categoricalFeaturesInfo: scala.Predef.Map[Int, Int],
                maxDepth :Int, maxBins: Int): Double = {
    val impurity = "variance"
    val decisionTreeModel = DecisionTree.trainRegressor(train, categoricalFeaturesInfo,
      impurity,maxDepth, maxBins )

    val true_vs_predicted = test.map(p => (p.label, decisionTreeModel.predict(p.features)))
    val rmsle = Math.sqrt(true_vs_predicted.map{ case(t, p) => Util.squaredLogError(t, p)}.mean())
    return rmsle
  }

} 

//设置package包名称以及导入依赖的类
package com.ox.bigdata.util.kafka

import kafka.common.KafkaException
import kafka.utils.Logging

import scala.collection.{Iterable, Map}
import scala.util.parsing.json.JSON


  def encode(obj: Any): String = {
    obj match {
      case null => "null"
      case b: Boolean => b.toString
      case s: String => "\"" + s + "\""
      case n: Number => n.toString
      case m: Map[_, _] =>
        "{" +
          m.map(elem =>
            elem match {
              case t: Tuple2[_, _] => encode(t._1) + ":" + encode(t._2)
              case _ => throw new IllegalArgumentException("Invalid map element (" + elem + ") in " + obj)
            }).mkString(",") +
          "}"
      case a: Array[_] => encode(a.toSeq)
      case i: Iterable[_] => "[" + i.map(encode).mkString(",") + "]"
      case other: AnyRef => throw new IllegalArgumentException("Unknown arguement of type " + other.getClass + ": " + other)
    }
  }
} 

//设置package包名称以及导入依赖的类
package org.kneelawk.imagegenerator2.comparecolors

import java.awt.image.BufferedImage

import scala.collection.Map

import org.kneelawk.imagegenerator2.ImageGenerator
import org.kneelawk.imagegenerator2.util.MathUtil
import javax.imageio.ImageIO
import java.io.File

object CompareColors extends ImageGenerator {
  def name: String = "CompareColors"

  def options: Seq[(String, String)] = Array(
    ("path", "Path to starting image"))

  def apply(i: BufferedImage, options: Map[String, String], width: Int, height: Int): Unit = {
    import MathUtil._
    val input = ImageIO.read(new File(options("path")))

    if (input.getWidth != width || input.getHeight != height) throw new IllegalArgumentException("Input and Output image sizes must mach")
    
    for (y <- 0 until height; x <- 0 until width) {
      val r = input.getRGB(mod2(x + 1, 0, width), y)
      val l = input.getRGB(mod2(x - 1, 0, width), y)
      val d = input.getRGB(x, mod2(y + 1, 0, height))
      val u = input.getRGB(x, mod2(y - 1, 0, height))
      val c = input.getRGB(x, y)
      
      if (r != c || l != c || d != c || u != c) {
        i.setRGB(x, y, 0xFFFFFFFF)
      } else {
        i.setRGB(x, y, 0x00000000)
      }
    }
  }
} 

//设置package包名称以及导入依赖的类
package com.github.tarao.namedcap

import scala.collection.immutable.{Map => ImmutableMap}
import scala.collection.Map

object MultiMap {
  def apply(): MultiMap = new MultiMap(Map.empty)
  def apply[S <: Seq[String]](m: Map[String, S]): MultiMap = new MultiMap(m)
  val empty = MultiMap()
}


class MultiMap(m: Map[String, Seq[String]])
    extends ImmutableMap[String, String] {
  def get(key: String): Option[String] = m.get(key).flatMap(_.headOption)
  def getAll(key: String): Seq[String] = m.getOrElse(key, Seq.empty)
  def +[V >: String](kv: (String, V)): MultiMap = {
    val (key, value) = kv
    val list = m.getOrElse(key, Vector.empty) :+ value.asInstanceOf[String]
    new MultiMap(m + (key -> list))
  }
  def -(key: String): MultiMap = new MultiMap(m - key)
  def iterator: Iterator[(String, String)] =
    m.iterator.flatMap(kv => kv._2.headOption.map(kv._1 -> _))
  override def default(key: String): String =
    m.default(key).headOption.getOrElse {
      throw new NoSuchElementException("key not found: " + key)
    }
} 

//设置package包名称以及导入依赖的类
package org.danielnixon.extrawarts

import org.scalatest.FunSuite
import org.wartremover.test.WartTestTraverser

import scala.collection.{ GenMapLike, Map }

class GenMapLikePartialTest extends FunSuite {
  val map: GenMapLike[String, Int, Map[String, Int]] = Map[String, Int]()

  test("can't use GenMapLike#apply") {
    val result = WartTestTraverser(GenMapLikePartial) {
      val foo = map("foo")
    }
    assertResult(List("[wartremover:GenMapLikePartial] GenMapLike#apply is disabled - use GenMapLike#get instead"), "result.errors")(result.errors)
    assertResult(List.empty, "result.warnings")(result.warnings)
  }

  test("doesn't detect other `apply` methods") {
    val result = WartTestTraverser(GenMapLikePartial) {
      case class A(apply: Int)
      println(A(1).apply)
    }
    assertResult(List.empty, "result.errors")(result.errors)
    assertResult(List.empty, "result.warnings")(result.warnings)
  }

  test("GenMapLikePartial wart obeys SuppressWarnings") {
    val result = WartTestTraverser(GenMapLikePartial) {
      @SuppressWarnings(Array("org.danielnixon.extrawarts.GenMapLikePartial"))
      val foo = map("foo")
    }
    assertResult(List.empty, "result.errors")(result.errors)
    assertResult(List.empty, "result.warnings")(result.warnings)
  }
} 

//设置package包名称以及导入依赖的类
package com.datawizards.sparklocal.rdd

import org.apache.spark.Partitioner
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.SparkSession

import scala.collection.{GenIterable, GenMap, Map}
import scala.reflect.ClassTag

trait PairRDDFunctionsAPI[K, V] {
  protected lazy val spark: SparkSession = SparkSession.builder().getOrCreate()
  protected def parallelize[That: ClassTag](d: Seq[That]): RDD[That] = spark.sparkContext.parallelize(d)
  protected def parallelize[That: ClassTag](d: GenIterable[That]): RDD[That] = parallelize(d.toList)

  def mapValues[U: ClassTag](f: (V) => U): RDDAPI[(K, U)]
  def keys: RDDAPI[K]
  def values: RDDAPI[V]
  def flatMapValues[U: ClassTag](f: (V) => TraversableOnce[U]): RDDAPI[(K, U)]
  def countByKey(): GenMap[K, Long]
  def reduceByKey(func: (V, V) => V): RDDAPI[(K, V)]
  def reduceByKey(func: (V, V) => V, numPartitions: Int): RDDAPI[(K, V)]
  def reduceByKey(partitioner: Partitioner, func: (V, V) => V): RDDAPI[(K, V)]
  def reduceByKeyLocally(func: (V, V) => V): Map[K, V]
  def groupByKey(): RDDAPI[(K, GenIterable[V])]
  def groupByKey(numPartitions: Int): RDDAPI[(K, GenIterable[V])]
  def groupByKey(partitioner: Partitioner): RDDAPI[(K, GenIterable[V])]
  def foldByKey(zeroValue: V)(func: (V, V) => V): RDDAPI[(K, V)]
  def foldByKey(zeroValue: V, numPartitions: Int)(func: (V, V) => V): RDDAPI[(K, V)]
  def foldByKey(zeroValue: V, partitioner: Partitioner)(func: (V, V) => V): RDDAPI[(K, V)]
  def join[W: ClassTag](other: RDDAPI[(K, W)]): RDDAPI[(K, (V, W))]
  def join[W: ClassTag](other: RDDAPI[(K, W)], numPartitions: Int): RDDAPI[(K, (V, W))]
  def join[W: ClassTag](other: RDDAPI[(K, W)], partitioner: Partitioner): RDDAPI[(K, (V, W))]
  def leftOuterJoin[W: ClassTag](other: RDDAPI[(K, W)]): RDDAPI[(K, (V, Option[W]))]
  def leftOuterJoin[W: ClassTag](other: RDDAPI[(K, W)], numPartitions: Int): RDDAPI[(K, (V, Option[W]))]
  def leftOuterJoin[W: ClassTag](other: RDDAPI[(K, W)], partitioner: Partitioner): RDDAPI[(K, (V, Option[W]))]
  def rightOuterJoin[W: ClassTag](other: RDDAPI[(K, W)]): RDDAPI[(K, (Option[V], W))]
  def rightOuterJoin[W: ClassTag](other: RDDAPI[(K, W)], numPartitions: Int): RDDAPI[(K, (Option[V], W))]
  def rightOuterJoin[W: ClassTag](other: RDDAPI[(K, W)], partitioner: Partitioner): RDDAPI[(K, (Option[V], W))]
  def fullOuterJoin[W: ClassTag](other: RDDAPI[(K, W)]): RDDAPI[(K, (Option[V], Option[W]))]
  def fullOuterJoin[W: ClassTag](other: RDDAPI[(K, W)], numPartitions: Int): RDDAPI[(K, (Option[V], Option[W]))]
  def fullOuterJoin[W: ClassTag](other: RDDAPI[(K, W)], partitioner: Partitioner): RDDAPI[(K, (Option[V], Option[W]))]
  def cogroup[W1: ClassTag, W2: ClassTag, W3: ClassTag](other1: RDDAPI[(K, W1)], other2: RDDAPI[(K, W2)], other3: RDDAPI[(K, W3)], partitioner: Partitioner): RDDAPI[(K, (GenIterable[V], GenIterable[W1], GenIterable[W2], GenIterable[W3]))]
  def cogroup[W: ClassTag](other: RDDAPI[(K, W)], partitioner: Partitioner): RDDAPI[(K, (GenIterable[V], GenIterable[W]))]
  def cogroup[W1: ClassTag, W2: ClassTag](other1: RDDAPI[(K, W1)], other2: RDDAPI[(K, W2)], partitioner: Partitioner): RDDAPI[(K, (GenIterable[V], GenIterable[W1], GenIterable[W2]))]
  def cogroup[W1: ClassTag, W2: ClassTag, W3: ClassTag](other1: RDDAPI[(K, W1)], other2: RDDAPI[(K, W2)], other3: RDDAPI[(K, W3)]): RDDAPI[(K, (GenIterable[V], GenIterable[W1], GenIterable[W2], GenIterable[W3]))]
  def cogroup[W: ClassTag](other: RDDAPI[(K, W)]): RDDAPI[(K, (GenIterable[V], GenIterable[W]))]
  def cogroup[W1: ClassTag, W2: ClassTag](other1: RDDAPI[(K, W1)], other2: RDDAPI[(K, W2)]): RDDAPI[(K, (GenIterable[V], GenIterable[W1], GenIterable[W2]))]
  def cogroup[W: ClassTag](other: RDDAPI[(K, W)], numPartitions: Int): RDDAPI[(K, (GenIterable[V], GenIterable[W]))]
  def cogroup[W1: ClassTag, W2: ClassTag](other1: RDDAPI[(K, W1)], other2: RDDAPI[(K, W2)], numPartitions: Int): RDDAPI[(K, (GenIterable[V], GenIterable[W1], GenIterable[W2]))]
  def cogroup[W1: ClassTag, W2: ClassTag, W3: ClassTag](other1: RDDAPI[(K, W1)], other2: RDDAPI[(K, W2)], other3: RDDAPI[(K, W3)], numPartitions: Int): RDDAPI[(K, (GenIterable[V], GenIterable[W1], GenIterable[W2], GenIterable[W3]))]
  def collectAsMap(): GenMap[K, V]
  def subtractByKey[W: ClassTag](other: RDDAPI[(K, W)]): RDDAPI[(K, V)]
  def subtractByKey[W: ClassTag](other: RDDAPI[(K, W)], numPartitions: Int): RDDAPI[(K, V)]
  def subtractByKey[W: ClassTag](other: RDDAPI[(K, W)], p: Partitioner): RDDAPI[(K, V)]
  def aggregateByKey[U: ClassTag](zeroValue: U)(seqOp: (U, V) => U, combOp: (U, U) => U): RDDAPI[(K, U)]
  def aggregateByKey[U: ClassTag](zeroValue: U, partitioner: Partitioner)(seqOp: (U, V) => U, combOp: (U, U) => U): RDDAPI[(K, U)]
  def aggregateByKey[U: ClassTag](zeroValue: U, numPartitions: Int)(seqOp: (U, V) => U, combOp: (U, U) => U): RDDAPI[(K, U)]
  def partitionBy(partitioner: Partitioner): RDDAPI[(K, V)]

} 

//设置package包名称以及导入依赖的类
package com.danielwestheide.kontextfrei

import scala.collection.Map
import scala.reflect.ClassTag

private[kontextfrei] trait DCollectionPairFunctions[DCollection[_]] {

  def values[A: ClassTag, B: ClassTag](x: DCollection[(A, B)]): DCollection[B]

  def keys[A: ClassTag, B: ClassTag](x: DCollection[(A, B)]): DCollection[A]

  def cogroup[A: ClassTag, B: ClassTag, C: ClassTag](x: DCollection[(A, B)])(
      y: DCollection[(A, C)]): DCollection[(A, (Iterable[B], Iterable[C]))]

  def leftOuterJoin[A: ClassTag, B: ClassTag, C: ClassTag](
      x: DCollection[(A, B)])(
      y: DCollection[(A, C)]): DCollection[(A, (B, Option[C]))]

  def rightOuterJoin[A: ClassTag, B: ClassTag, C: ClassTag](
      x: DCollection[(A, B)])(
      y: DCollection[(A, C)]): DCollection[(A, (Option[B], C))]

  def fullOuterJoin[A: ClassTag, B: ClassTag, C: ClassTag](
      x: DCollection[(A, B)])(
      y: DCollection[(A, C)]): DCollection[(A, (Option[B], Option[C]))]

  def mapValues[A: ClassTag, B: ClassTag, C: ClassTag](x: DCollection[(A, B)])(
      f: B => C): DCollection[(A, C)]

  def flatMapValues[A: ClassTag, B: ClassTag, C: ClassTag](
      xs: DCollection[(A, B)])(f: B => TraversableOnce[C]): DCollection[(A, C)]

  def foldByKey[A: ClassTag, B: ClassTag](xs: DCollection[(A, B)])(
      zeroValue: B,
      func: (B, B) => B): DCollection[(A, B)]

  def reduceByKey[A: ClassTag, B: ClassTag](xs: DCollection[(A, B)])(
      f: (B, B) => B): DCollection[(A, B)]

  def aggregateByKey[A: ClassTag, B: ClassTag, C: ClassTag](
      xs: DCollection[(A, B)])(zeroValue: C)(
      seqOp: (C, B) => C,
      combOp: (C, C) => C): DCollection[(A, C)]

  def combineByKey[A: ClassTag, B: ClassTag, C: ClassTag](
      xs: DCollection[(A, B)])(createCombiner: B => C)(
      mergeValue: (C, B) => C,
      mergeCombiners: (C, C) => C): DCollection[(A, C)]

  def countByKey[A: ClassTag, B: ClassTag](
      xs: DCollection[(A, B)]): Map[A, Long]

  def collectAsMap[A: ClassTag, B: ClassTag](
      xs: DCollection[(A, B)]): Map[A, B]
} 

//设置package包名称以及导入依赖的类
package com.spark.scala.core

import org.apache.spark.SparkContext
import org.apache.spark.SparkConf
import org.apache.spark.rdd.RDD
import scala.collection.Map
import org.apache.commons.io.FileUtils
import java.io.File
import java.util.Properties

class SparkWordCountJob (sc: SparkContext) {
  //reads data  and computes the results
  def run(t: String , outputFile: String)  = {
  val readsdata = sc.textFile(t)
  // Transform into word and count.
  val words = readsdata.flatMap(word => word.split(" "))
  val counts = words.map(word => (word, 1)).reduceByKey(_ + _)
  // Save the word count back out to a text file
  counts.saveAsTextFile(outputFile)
                
	}
	
  //Delete results folder if exists
  def deleteFile(proprietes: Properties) = {
   if (new File((proprietes.getProperty("Output").toString())).exists ()) {
   FileUtils.deleteDirectory (new File((proprietes.getProperty("Output").toString())));
   } 
    }
} 

//设置package包名称以及导入依赖的类
package com.harry0000.kancolle

import scala.collection.{Map, Seq, mutable}
import scala.collection.immutable.TreeMap

package object ac {
  type ShipName = String
  type ShipMap = TreeMap[ShipCategory, Seq[ShipName]]
  object ShipMap {
    def empty: ShipMap = TreeMap.empty[ShipCategory, Seq[ShipName]]
    def apply(value: (ShipCategory, Seq[ShipName]) *): ShipMap = TreeMap(value: _*)
  }

  sealed abstract class ShipCategory(val name: String)
  object ShipCategory {
    case object Destroyer       extends ShipCategory("???")
    case object LightCruiser    extends ShipCategory("??")
    case object HeavyCruiser    extends ShipCategory("??")
    case object SeaplaneTender  extends ShipCategory("?????")
    case object AircraftCarrier extends ShipCategory("??")
    case object Submarine       extends ShipCategory("???")
    case object Battleship      extends ShipCategory("??")

    private val order: Map[ShipCategory, Int] = mutable.LinkedHashMap.empty ++ Seq(
      Destroyer,
      LightCruiser,
      HeavyCruiser,
      SeaplaneTender,
      AircraftCarrier,
      Submarine,
      Battleship
    ).zipWithIndex

    implicit val ordering: Ordering[ShipCategory] = Ordering.by(order.getOrElse(_, Int.MaxValue))

    def apply(shipType: String): ShipCategory = shipType match {
      case "??" => Destroyer
      case "??" => LightCruiser
      case "??" => HeavyCruiser
      case "??" => SeaplaneTender
      case "??" => AircraftCarrier
      case "??" => AircraftCarrier
      case "??" => Submarine
      case "??" => Battleship
    }

    def get(index: Int): Option[ShipCategory] = order.find(_._2 == index).map(_._1)

    def values: Seq[ShipCategory] = order.keys.toSeq
  }
}