Spark ML TF-IDF Scala失败

Question

我密切关注了Spark ML网站上的example，看不到哪里出了问题。尝试对新闻文章语料库进行TF-IDF。这是我的代码，在最后一行中断：

import org.apache.spark.ml.clustering.KMeans
import org.apache.spark.ml.evaluation.ClusteringEvaluator
import org.apache.spark.ml.feature.{HashingTF, IDF, Tokenizer}

// load in the data
val data = spark.read.
    option("header", "true").
    format("csv").
    load("data/articles.csv")

// select article content column
val content = data.select("content")

//tokenize content
val tokenizer = new Tokenizer().
    setInputCol("content").
    setOutputCol("words")

val wordsDF = tokenizer.transform(content)

// calculate TF
val hashingTF = new HashingTF().
    setInputCol("words").
    setOutputCol("rawFeatures").
    setNumFeatures(20)

val featurizedData = hashingTF.transform(wordsDF)

// calculate IDF
val idf = new IDF().
    setInputCol("rawFeatures").
    setOutputCol("features")

val idfModel = idf.fit(featurizedData)

这是我的堆栈跟踪的顶部：

2019-02-25 13:24:58 ERROR Executor:91 - Exception in task 0.0 in stage 3.0 (TID 5)
org.apache.spark.SparkException: Failed to execute user defined function($anonfun$createTransformFunc$1: (string) => array<string>)
    at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
    at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
    at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$10$$anon$1.hasNext(WholeStageCodegenExec.scala:614)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
    at scala.collection.Iterator$class.foreach(Iterator.scala:893)
    at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
    at scala.collection.TraversableOnce$class.foldLeft(TraversableOnce.scala:157)
    at scala.collection.AbstractIterator.foldLeft(Iterator.scala:1336)
    at scala.collection.TraversableOnce$class.aggregate(TraversableOnce.scala:214)
    at scala.collection.AbstractIterator.aggregate(Iterator.scala:1336)
    at org.apache.spark.rdd.RDD$$anonfun$treeAggregate$1$$anonfun$23.apply(RDD.scala:1145)
    at org.apache.spark.rdd.RDD$$anonfun$treeAggregate$1$$anonfun$23.apply(RDD.scala:1145)
    at org.apache.spark.rdd.RDD$$anonfun$treeAggregate$1$$anonfun$24.apply(RDD.scala:1146)
    at org.apache.spark.rdd.RDD$$anonfun$treeAggregate$1$$anonfun$24.apply(RDD.scala:1146)
    at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:801)