Question

我尝试使用Spark MLlib的推文进行情绪分析。在预处理数据并将其转换为适当的格式之后，我调用NaiveBayes的train方法来获取模型，但它失败并出现异常。这是堆栈跟踪：

java.util.NoSuchElementException: next on empty iterator
    at scala.collection.Iterator$$anon$2.next(Iterator.scala:39)
    at scala.collection.Iterator$$anon$2.next(Iterator.scala:37)
    at scala.collection.IndexedSeqLike$Elements.next(IndexedSeqLike.scala:64)
    at scala.collection.IterableLike$class.head(IterableLike.scala:91)
    at scala.collection.mutable.ArrayOps$ofRef.scala$collection$IndexedSeqOptimized$$super$head(ArrayOps.scala:108)
    at scala.collection.IndexedSeqOptimized$class.head(IndexedSeqOptimized.scala:120)
    at scala.collection.mutable.ArrayOps$ofRef.head(ArrayOps.scala:108)
    at org.apache.spark.mllib.classification.NaiveBayes.run(NaiveBayes.scala:408)
    at org.apache.spark.mllib.classification.NaiveBayes$.train(NaiveBayes.scala:467)
    at org.jc.sparknaivebayes.main.NaiveBayesTrain$delayedInit$body.apply(NaiveBayesTrain.scala:53)
    at scala.Function0$class.apply$mcV$sp(Function0.scala:40)
    at scala.runtime.AbstractFunction0.apply$mcV$sp(AbstractFunction0.scala:12)
    at scala.App$$anonfun$main$1.apply(App.scala:71)
    at scala.App$$anonfun$main$1.apply(App.scala:71)
    at scala.collection.immutable.List.foreach(List.scala:318)
    at scala.collection.generic.TraversableForwarder$class.foreach(TraversableForwarder.scala:32)
    at scala.App$class.main(App.scala:71)
    at org.jc.sparknaivebayes.main.NaiveBayesTrain$.main(NaiveBayesTrain.scala:12)
    at org.jc.sparknaivebayes.main.NaiveBayesTrain.main(NaiveBayesTrain.scala)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:606)
    at org.apache.spark.deploy.yarn.ApplicationMaster$$anon$2.run(ApplicationMaster.scala:542)

这是我的主要方法：

val csvFiles = args(0).split(",")
    val modelStore = args(1)
    val docs = TweetParser.parseAll(csvFiles, sc)
    val termDocs = Tokenizer.tokenizeAll(docs)

    val termDocsRdd = sc.parallelize[TermDoc](termDocs.toSeq)

    val numDocs = termDocsRdd.count()

    //val terms = termDocsRdd.flatMap(_.terms).distinct().collect().sortBy(identity)
    val terms = termDocsRdd.flatMap(_.terms).distinct().sortBy(identity)
    val termDict = new Dictionary(terms)

    //val labels = termDocsRdd.flatMap(_.labels).distinct().collect()
    val labels = termDocsRdd.flatMap(_.labels).distinct()
    val labelDict = new Dictionary(labels)

    val idfs = (termDocsRdd.flatMap(termDoc => termDoc.terms.map((termDoc.doc, _))).distinct().groupBy(_._2) collect {
      case (term, docs) if docs.size > 3 =>
        term -> (numDocs.toDouble / docs.size.toDouble)
    }).collect.toMap

    val tfidfs = termDocsRdd flatMap {
      termDoc =>
        val termPairs: Seq[(Int, Double)] = termDict.tfIdfs(termDoc.terms, idfs)
        termDoc.labels.headOption.map {
          label =>
            val labelId = labelDict.indexOf(label).toDouble
            val vector = Vectors.sparse(termDict.count.toInt, termPairs)
            LabeledPoint(labelId, vector)
        }
    }

    val model = NaiveBayes.train(tfidfs)

字典类在这里：

class Dictionary(dict: RDD[String]) extends Serializable {

  //val builder = ImmutableBiMap.builder[String, Long]()
  //dict.zipWithIndex.foreach(e => builder.put(e._1, e._2))

  //val termToIndex = builder.build()
  val termToIndex = dict.zipWithIndex()

  //@transient
  //lazy val indexToTerm = termToIndex.inverse()
  lazy val indexToTerm = dict.zipWithIndex().map{
    case (k, v) => (v, k)
  } //converts from (a, 0),(b, 1),(c, 2) to (0, a),(1, b),(2, c)

  val count = termToIndex.count().toInt

  def indexOf(term: String): Int = termToIndex.lookup(term).headOption.getOrElse[Long](-1).toInt

  def valueOf(index: Int): String = indexToTerm.lookup(index).headOption.getOrElse("")

  def tfIdfs (terms: Seq[String], idfs: Map[String, Double]): Seq[(Int, Double)] = {
    val filteredTerms = terms.filter(idfs contains)
    (filteredTerms.groupBy(identity).map {
      case (term, instances) => {
        val indexOfTerm: Int = indexOf(term)
        if (indexOfTerm < 0) (-1, 0.0) else (indexOf(term), (instances.size.toDouble / filteredTerms.size.toDouble) * idfs(term))
      }
    }).filter(p => p._1.toInt  >= 0).toSeq.sortBy(_._1)
  }

  def vectorize(tfIdfs: Iterable[(Int, Double)]) = {
    Vectors.sparse(dict.count().toInt, tfIdfs.toSeq)
  }
}

文档类如下所示：

case class Document(docId: String, body: String = "", labels: Set[String] = Set.empty)

TermDoc类：

case class TermDoc(doc: String, labels: Set[String], terms: Seq[String])

我坚持这一步，我真的需要完成这项工作，但我在寻找有用的信息方面遇到了很多麻烦。提前谢谢。

P.S：这是基于chimpler的博客：https://github.com/chimpler/blog-spark-naive-bayes-reuters/blob/master/src/main/scala/com/chimpler/sparknaivebayesreuters/NaiveBayes.scala

更新：CSV解析器和文档构建器的新代码。

import org.apache.spark.SparkContext

import scala.io.Source

/**
  * Created by cespedjo on 14/02/2017.
  */
object TweetParser extends Serializable{

  val headerPart = "polarity"

  val mentionRegex = """@(.)+?\s""".r

  val fullRegex = """(\d+),(.+?),(N|P|NEU|NONE)(,\w+|;\w+)*""".r

  def parseAll(csvFiles: Iterable[String], sc: SparkContext) = csvFiles flatMap(csv => parse(csv, sc))

  def parse(csvFile: String, sc: SparkContext) = {
    val csv = sc.textFile(csvFile)
    val docs = scala.collection.mutable.ArrayBuffer.empty[Document]

    csv.foreach(
      line => if (!line.contains(headerPart)) docs += buildDocument(line)
    )
    docs
    //docs.filter(!_.docId.equals("INVALID"))
  }

  def buildDocument(line: String): Document = {

    val fullRegex(id, txt, snt, opt) = line
    if (id != null && txt != null && snt != null)
      new Document(id, mentionRegex.replaceAllIn(txt, ""), Set(snt))
    else
      new Document("INVALID")
  }
}

case class Document(docId: String, body: String = "", labels: Set[String] = Set.empty)

Spark + Scala：NaiveBayes.train - 异常是java.util.NoSuchElementException：下一个空迭代器

0 个答案: