Spark UnsupportedOperationException：空集合

Question

在嘗試使用由Databricks提供的動手執行spark mllib ALS時，是否有人知道此錯誤的可能原因？

14/11/20 23:33:38 WARN Utils: Set SPARK_LOCAL_IP if you need to bind to another address
14/11/20 23:33:39 WARN SizeEstimator: Failed to check whether UseCompressedOops is set; assuming yes
Got 27980 ratings from 24071 users on 4211 movies.
Training: 27989, validation: 0, test: 0
Exception in thread "main" java.lang.UnsupportedOperationException: empty collection
    at org.apache.spark.rdd.RDD$$anonfun$reduce$1.apply(RDD.scala:806)
    at org.apache.spark.rdd.RDD$$anonfun$reduce$1.apply(RDD.scala:806)
    at scala.Option.getOrElse(Option.scala:120)
    at org.apache.spark.rdd.RDD.reduce(RDD.scala:806)
    at MovieLensALS$.computeRmse(MovieLensALS.scala:149)
    at MovieLensALS$$anonfun$main$1$$anonfun$apply$mcVI$sp$1$$anonfun$apply$mcVD$sp$1.apply$mcVI$sp(MovieLensALS.scala:95)
    at MovieLensALS$$anonfun$main$1$$anonfun$apply$mcVI$sp$1$$anonfun$apply$mcVD$sp$1.apply(MovieLensALS.scala:93)
    at MovieLensALS$$anonfun$main$1$$anonfun$apply$mcVI$sp$1$$anonfun$apply$mcVD$sp$1.apply(MovieLensALS.scala:93)
    at scala.collection.immutable.List.foreach(List.scala:318)
    at MovieLensALS$$anonfun$main$1$$anonfun$apply$mcVI$sp$1.apply$mcVD$sp(MovieLensALS.scala:93)
    at MovieLensALS$$anonfun$main$1$$anonfun$apply$mcVI$sp$1.apply(MovieLensALS.scala:93)
    at MovieLensALS$$anonfun$main$1$$anonfun$apply$mcVI$sp$1.apply(MovieLensALS.scala:93)
    at scala.collection.immutable.List.foreach(List.scala:318)
    at MovieLensALS$$anonfun$main$1.apply$mcVI$sp(MovieLensALS.scala:93)
    at MovieLensALS$$anonfun$main$1.apply(MovieLensALS.scala:93)
    at MovieLensALS$$anonfun$main$1.apply(MovieLensALS.scala:93)
    at scala.collection.immutable.List.foreach(List.scala:318)
    at MovieLensALS$.main(MovieLensALS.scala:93)
    at MovieLensALS.main(MovieLensALS.scala)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:606)
    at org.apache.spark.deploy.SparkSubmit$.launch(SparkSubmit.scala:292)
    at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:55)
    at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)

更新：當然可以！ 我正在上這堂課。 可在https://databricks-training.s3.amazonaws.com/movie-recommendation-with-mllib.html和https://databricks-training.s3.amazonaws.com/getting-started.html#additional-必需下載 。 讓我知道是否還有其他可以幫助您的問題

import java.io.File

import scala.io.Source

import org.apache.log4j.Logger
import org.apache.log4j.Level

import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.apache.spark.rdd._`enter code here`
import org.apache.spark.mllib.recommendation.{ALS, Rating, MatrixFactorizationModel}

object MovieLensALS {

  def main(args: Array[String]) {

    Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
    Logger.getLogger("org.eclipse.jetty.server").setLevel(Level.OFF)

    if (args.length != 2) {
      println("Usage: /path/to/spark/bin/spark-submit --driver-memory 2g --class MovieLensALS " +
        "target/scala-*/movielens-als-ssembly-*.jar movieLensHomeDir personalRatingsFile")
      sys.exit(1)
    }

    // set up environment

    val conf = new SparkConf()
      .setAppName("MovieLensALS")
      .set("spark.executor.memory", "2g")
    val sc = new SparkContext(conf)

    // load personal ratings

    val myRatings = loadRatings(args(1))
    val myRatingsRDD = sc.parallelize(myRatings, 1)

    // load ratings and movie titles

    val movieLensHomeDir = args(0)

    val ratings = sc.textFile(new File(movieLensHomeDir, "ratings.dat").toString).map { line =>
      val fields = line.split("::")
      // format: (timestamp % 10, Rating(userId, movieId, rating))
      (fields(3).toLong % 10, Rating(fields(0).toInt, fields(1).toInt, fields(2).toDouble))
    }

    val movies = sc.textFile(new File(movieLensHomeDir, "movies.dat").toString).map { line =>
      val fields = line.split("::")
      // format: (movieId, movieName)
      (fields(0).toInt, fields(1))
    }.collect().toMap

    val numRatings = ratings.count()
    val numUsers = ratings.map(_._2.user).distinct().count()
    val numMovies = ratings.map(_._2.product).distinct().count()

    println("Got " + numRatings + " ratings from "
      + numUsers + " users on " + numMovies + " movies.")

    // split ratings into train (60%), validation (20%), and test (20%) based on the 
    // last digit of the timestamp, add myRatings to train, and cache them

    val numPartitions = 4
    val training = ratings.filter(x => x._1 < 6)
      .values
      .union(myRatingsRDD)
      .repartition(numPartitions)
      .cache()
    val validation = ratings.filter(x => x._1 >= 6 && x._1 < 8)
      .values
      .repartition(numPartitions)
      .cache()
    val test = ratings.filter(x => x._1 >= 8).values.cache()

    val numTraining = training.count()
    val numValidation = validation.count()
    val numTest = test.count()

    println("Training: " + numTraining + ", validation: " + numValidation + ", test: " + numTest)

    // train models and evaluate them on the validation set

    val ranks = List(8, 12)
    val lambdas = List(0.1, 10.0)
    val numIters = List(10, 20)
    var bestModel: Option[MatrixFactorizationModel] = None
    var bestValidationRmse = Double.MaxValue
    var bestRank = 0
    var bestLambda = -1.0
    var bestNumIter = -1
    for (rank <- ranks; lambda <- lambdas; numIter <- numIters) {
      val model = ALS.train(training, rank, numIter, lambda)
      val validationRmse = computeRmse(model, validation, numValidation)
      println("RMSE (validation) = " + validationRmse + " for the model trained with rank = " 
        + rank + ", lambda = " + lambda + ", and numIter = " + numIter + ".")
      if (validationRmse < bestValidationRmse) {
        bestModel = Some(model)
        bestValidationRmse = validationRmse
        bestRank = rank
        bestLambda = lambda
        bestNumIter = numIter
      }
    }

    // evaluate the best model on the test set

    val testRmse = computeRmse(bestModel.get, test, numTest)

    println("The best model was trained with rank = " + bestRank + " and lambda = " + bestLambda
      + ", and numIter = " + bestNumIter + ", and its RMSE on the test set is " + testRmse + ".")

    // create a naive baseline and compare it with the best model

    val meanRating = training.union(validation).map(_.rating).mean
    val baselineRmse = 
      math.sqrt(test.map(x => (meanRating - x.rating) * (meanRating - x.rating)).mean)
    val improvement = (baselineRmse - testRmse) / baselineRmse * 100
    println("The best model improves the baseline by " + "%1.2f".format(improvement) + "%.")

    // make personalized recommendations

    val myRatedMovieIds = myRatings.map(_.product).toSet
    val candidates = sc.parallelize(movies.keys.filter(!myRatedMovieIds.contains(_)).toSeq)
    val recommendations = bestModel.get
      .predict(candidates.map((0, _)))
      .collect()
      .sortBy(- _.rating)
      .take(50)

    var i = 1
    println("Movies recommended for you:")
    recommendations.foreach { r =>
      println("%2d".format(i) + ": " + movies(r.product))
      i += 1
    }

    // clean up
    sc.stop()
  }

  /** Compute RMSE (Root Mean Squared Error). */
  def computeRmse(model: MatrixFactorizationModel, data: RDD[Rating], n: Long): Double = {
    val predictions: RDD[Rating] = model.predict(data.map(x => (x.user, x.product)))
    val predictionsAndRatings = predictions.map(x => ((x.user, x.product), x.rating))
      .join(data.map(x => ((x.user, x.product), x.rating)))
      .values
    math.sqrt(predictionsAndRatings.map(x => (x._1 - x._2) * (x._1 - x._2)).reduce(_ + _) / n)
  }

  /** Load ratings from file. */
  def loadRatings(path: String): Seq[Rating] = {
    val lines = Source.fromFile(path).getLines()
    val ratings = lines.map { line =>
      val fields = line.split("::")
      Rating(fields(0).toInt, fields(1).toInt, fields(2).toDouble)
    }.filter(_.rating > 0.0)
    if (ratings.isEmpty) {
      sys.error("No ratings provided.")
    } else {
      ratings.toSeq
    }
  }
}

Answer 1

可能是由於您（或computeRmse方法）正在使用某些過濾器，所以reduce方法在空集合/ RDD上被調用，因此引發了“空集合”。 嘗試仔細檢查過濾器或computeRmse（）函數。

Answer 2

我在使用相同的示例時遇到了相同的問題。 問題是我使用的訓練數據不夠大，並且沒有足夠的重復值。 ALS模型只能預測訓練數據中存在的用戶，產品ID對。 （這與其他機器學習算法有所不同），因此，如果驗證集中的每一對都包含一個不在訓練集中的ID，則預測RDD將為null（因為它無法預測這些值中的任何一個），並且rmse方法中的reduce轉換將引發此異常。 為避免這種情況，您應該：

A）沒有足夠的訓練數據，請勿使用此算法，並且

B）在進入“尋找最佳模型”循環之前進行檢查，以確認您的驗證集將在此訓練集的訓練中起作用。

最后，如果要使用此算法，請確保不要使用此方法返回的最佳模型，因為它可能沒有所有用戶和產品ID。 如果真是這樣，那么您將限制可以預測的新用戶和產品。 我建議使用此邏輯來識別正確的訓練參數，然后使用這些參數在所有數據上訓練模型並使用該模型。

Answer 3

我遇到了完全相同的例外。 就我而言，這是代碼中的錯誤，導致實際評級RDD的大小為零:)通過將空評級RDD傳遞給ALS.train，我絕對應該得到UnsupportedOperationException：空集合