環境:spark 1.60。私はスカラを使用します。 私はsbtでプログラムをコンパイルできますが、プログラムをコミットするとエラーが発生します。以下のように 私の完全なエラーは次のとおりです。タスクはaggegateByKeyについてシリアル化できません
238 17/01/21 18:32:24 INFO net.NetworkTopology: Adding a new node: /YH11070029/10.39.0.213:50010
17/01/21 18:32:24 INFO storage.BlockManagerMasterEndpoint: Registering block manager 10.39.0.44:41961 with 2.7 GB RAM, BlockManagerId(349, 10.39.0.44, 41961)
17/01/21 18:32:24 INFO storage.BlockManagerMasterEndpoint: Registering block manager 10.39.2.178:48591 with 2.7 GB RAM, BlockManagerId(518, 10.39.2.178, 48591)
Exception in thread "main" org.apache.spark.SparkException: Task not serializable
at org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:304)
at org.apache.spark.util.ClosureCleaner$.org$apache$spark$util$ClosureCleaner$$clean(ClosureCleaner.scala:294)
at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:122)
at org.apache.spark.SparkContext.clean(SparkContext.scala:2055)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$combineByKeyWithClassTag$1.apply(PairRDDFunctions.scala:93)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$combineByKeyWithClassTag$1.apply(PairRDDFunctions.scala:82)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.PairRDDFunctions.combineByKeyWithClassTag(PairRDDFunctions.scala:82)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$aggregateByKey$1.apply(PairRDDFunctions.scala:177)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$aggregateByKey$1.apply(PairRDDFunctions.scala:166)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.PairRDDFunctions.aggregateByKey(PairRDDFunctions.scala:166)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$aggregateByKey$3.apply(PairRDDFunctions.scala:206)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$aggregateByKey$3.apply(PairRDDFunctions.scala:206)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.PairRDDFunctions.aggregateByKey(PairRDDFunctions.scala:205)
at com.sina.adalgo.feature.ETL$$anonfun$13.apply(ETL.scala:190)
at com.sina.adalgo.feature.ETL$$anonfun$13.apply(ETL.scala:102)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
コードの目的は、カテゴリ機能frequentenciesを統計することです。メインコードは以下のとおりです。
object ETL extends Serializable {
... ...
val cateList = featureData.map{v =>
case (psid: String, label: String, cate_features: ParArray[String], media_features: String) =>
val pair_feature = cate_features.zipWithIndex.map(x => (x._2, x._1))
pair_feature
}.flatMap(_.toList)
def seqop(m: HashMap[String, Int] , s: String) : HashMap[String, Int]={
var x = m.getOrElse(s, 0)
x += 1
m += s -> x
m
}
def combop(m: HashMap[String, Int], n: HashMap[String, Int]) : HashMap[String, Int]={
for (k <- n) {
var x = m.getOrElse(k._1, 0)
x += k._2
m += k._1 -> x
}
m
}
val hash = HashMap[String, Int]()
val feaFreq = cateList.aggregateByKey(hash)(seqop, combop)// (i, HashMap[String, Int]) i corresponded with categorical feature
オブジェクトはSerializableを継承しています。 なぜですか?私を助けることができますか?
コードを追加できますか?例外だけで問題の原因を見ることはできません。 – maasg
"タスクはシリアル化できません"。独自のコードにシリアル化可能でないオブジェクトがあるかどうかを検出します。 –
コードが表示されます。私はオブジェクトがシリアライズ可能であることを確認しました。 –