一个 Spark DataFrame 包含一个类型为 Array[Double] 的列。当我试图在 map() 函数中获取它时,它会抛出 ClassCastException 异常。以下 Scala 代码会生成一个异常。
case class Dummy( x:Array[Double] )
val df = sqlContext.createDataFrame(Seq(Dummy(Array(1,2,3))))
val s = df.map( r => {
val arr:Array[Double] = r.getAs[Array[Double]]("x")
arr.sum
})
s.foreach(println)
例外情况是
java.lang.ClassCastException: scala.collection.mutable.WrappedArray$ofRef cannot be cast to [D
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(<console>:24)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(<console>:23)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at org.apache.spark.rdd.RDD$$anonfun$foreach$1$$anonfun$apply$28.apply(RDD.scala:890)
at org.apache.spark.rdd.RDD$$anonfun$foreach$1$$anonfun$apply$28.apply(RDD.scala:890)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1848)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1848)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
谁能给我解释一下为什么它不起作用?我该怎么做呢? 我正在使用Spark 1.5.1和scala 2.10.6
谢谢