JohnSnowLabs/spark-nlp

org.apache.spark.SparkException: [FAILED_EXECUTE_UDF]

Merlinish opened this issue · 4 comments

Merlinish commented

Hi all, I trained and saved the model according to this spark-nlp training, and then I tested it with some data. But I can't process the outcome of the model, It always shows the error:
when I tried to run the result.select("ner.result").show(truncate=False), it shows

org.apache.spark.SparkException: [FAILED_EXECUTE_UDF] Failed to execute user defined function (HasSimpleAnnotate$$Lambda$3933/0x00007f9ea1245468: (array<array<struct<annotatorType:string,begin:int,end:int,result:string,metadata:map<string,string>,embeddings:array>>>) => array<struct<annotatorType:string,begin:int,end:int,result:string,metadata:map<string,string>,embeddings:array>>).

and

Py4JJavaError: An error occurred while calling o388.showString.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 16.0 failed 1 times, most recent failure: Lost task 0.0 in stage 16.0 (TID 38) (172.19.230.207 executor driver): org.apache.spark.SparkException: [FAILED_EXECUTE_UDF] Failed to execute user defined function (HasSimpleAnnotate$$Lambda$3933/0x00007f9ea1245468: (array<array<struct<annotatorType:string,begin:int,end:int,result:string,metadata:map<string,string>,embeddings:array>>>) => array<struct<annotatorType:string,begin:int,end:int,result:string,metadata:map<string,string>,embeddings:array>>).

you can find my notebook screenshot here. the result format looks fine, but when you want to process it, the error shows.
image
image

Appreciate any help!

maziyarpanahi commented

PS: to also be sure this is not a bug, could you please copy the entire error from top to bottom and paste it here? (it's not possible to traverse inside the screenshot)

Merlinish commented

the entire error is here:

24/03/20 14:10:23 ERROR Executor: Exception in task 0.0 in stage 12.0 (TID 34)
org.apache.spark.SparkException: [FAILED_EXECUTE_UDF] Failed to execute user defined function (HasSimpleAnnotate$$Lambda$3430/0x00007ff2bcfe2c28: (array<array<struct<annotatorType:string,begin:int,end:int,result:string,metadata:map<string,string>,embeddings:array>>>) => array<struct<annotatorType:string,begin:int,end:int,result:string,metadata:map<string,string>,embeddings:array>>).
at org.apache.spark.sql.errors.QueryExecutionErrors$.failedExecuteUserDefinedFunctionError(QueryExecutionErrors.scala:217)
at org.apache.spark.sql.errors.QueryExecutionErrors.failedExecuteUserDefinedFunctionError(QueryExecutionErrors.scala)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.project_doConsume_0$(Unknown Source)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:760)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:888)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:888)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:364)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:328)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:92)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:161)
at org.apache.spark.scheduler.Task.run(Task.scala:139)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:554)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1529)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:557)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635)
at java.base/java.lang.Thread.run(Thread.java:840)
Caused by: java.lang.Exception: feature rules is not set
at com.johnsnowlabs.nlp.serialization.Feature.$anonfun$getOrDefault$1(Feature.scala:117)
at scala.Option.getOrElse(Option.scala:189)
at com.johnsnowlabs.nlp.serialization.Feature.getOrDefault(Feature.scala:117)
at com.johnsnowlabs.nlp.HasFeatures.$$(HasFeatures.scala:73)
at com.johnsnowlabs.nlp.HasFeatures.$$$(HasFeatures.scala:73)
at com.johnsnowlabs.nlp.AnnotatorModel.$$(AnnotatorModel.scala:29)
at com.johnsnowlabs.nlp.annotators.TokenizerModel.$anonfun$tag$5(TokenizerModel.scala:342)
at scala.collection.Iterator$$anon$11.nextCur(Iterator.scala:486)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:492)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:513)
at scala.collection.Iterator.foreach(Iterator.scala:943)
at scala.collection.Iterator.foreach$(Iterator.scala:943)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1431)
at scala.collection.generic.Growable.$plus$plus$eq(Growable.scala:62)
at scala.collection.generic.Growable.$plus$plus$eq$(Growable.scala:53)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:105)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:49)
at scala.collection.TraversableOnce.to(TraversableOnce.scala:366)
at scala.collection.TraversableOnce.to$(TraversableOnce.scala:364)
at scala.collection.AbstractIterator.to(Iterator.scala:1431)
at scala.collection.TraversableOnce.toBuffer(TraversableOnce.scala:358)
at scala.collection.TraversableOnce.toBuffer$(TraversableOnce.scala:358)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1431)
at scala.collection.TraversableOnce.toArray(TraversableOnce.scala:345)
at scala.collection.TraversableOnce.toArray$(TraversableOnce.scala:339)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1431)
at com.johnsnowlabs.nlp.annotators.TokenizerModel.$anonfun$tag$2(TokenizerModel.scala:400)
at scala.collection.TraversableLike.$anonfun$map$1(TraversableLike.scala:286)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at scala.collection.TraversableLike.map(TraversableLike.scala:286)
at scala.collection.TraversableLike.map$(TraversableLike.scala:279)
at scala.collection.AbstractTraversable.map(Traversable.scala:108)
at com.johnsnowlabs.nlp.annotators.TokenizerModel.tag(TokenizerModel.scala:290)
at com.johnsnowlabs.nlp.annotators.TokenizerModel.annotate(TokenizerModel.scala:408)
at com.johnsnowlabs.nlp.HasSimpleAnnotate.$anonfun$dfAnnotate$1(HasSimpleAnnotate.scala:46)
... 19 more
24/03/20 14:10:23 WARN TaskSetManager: Lost task 0.0 in stage 12.0 (TID 34) (172.19.230.207 executor driver): org.apache.spark.SparkException: [FAILED_EXECUTE_UDF] Failed to execute user defined function (HasSimpleAnnotate$$Lambda$3430/0x00007ff2bcfe2c28: (array<array<struct<annotatorType:string,begin:int,end:int,result:string,metadata:map<string,string>,embeddings:array>>>) => array<struct<annotatorType:string,begin:int,end:int,result:string,metadata:map<string,string>,embeddings:array>>).
at org.apache.spark.sql.errors.QueryExecutionErrors$.failedExecuteUserDefinedFunctionError(QueryExecutionErrors.scala:217)
at org.apache.spark.sql.errors.QueryExecutionErrors.failedExecuteUserDefinedFunctionError(QueryExecutionErrors.scala)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.project_doConsume_0$(Unknown Source)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:760)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:888)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:888)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:364)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:328)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:92)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:161)
at org.apache.spark.scheduler.Task.run(Task.scala:139)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:554)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1529)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:557)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635)
at java.base/java.lang.Thread.run(Thread.java:840)
Caused by: java.lang.Exception: feature rules is not set
at com.johnsnowlabs.nlp.serialization.Feature.$anonfun$getOrDefault$1(Feature.scala:117)
at scala.Option.getOrElse(Option.scala:189)
at com.johnsnowlabs.nlp.serialization.Feature.getOrDefault(Feature.scala:117)
at com.johnsnowlabs.nlp.HasFeatures.$$(HasFeatures.scala:73)
at com.johnsnowlabs.nlp.HasFeatures.$$$(HasFeatures.scala:73)
at com.johnsnowlabs.nlp.AnnotatorModel.$$(AnnotatorModel.scala:29)
at com.johnsnowlabs.nlp.annotators.TokenizerModel.$anonfun$tag$5(TokenizerModel.scala:342)
at scala.collection.Iterator$$anon$11.nextCur(Iterator.scala:486)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:492)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:513)
at scala.collection.Iterator.foreach(Iterator.scala:943)
at scala.collection.Iterator.foreach$(Iterator.scala:943)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1431)
at scala.collection.generic.Growable.$plus$plus$eq(Growable.scala:62)
at scala.collection.generic.Growable.$plus$plus$eq$(Growable.scala:53)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:105)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:49)
at scala.collection.TraversableOnce.to(TraversableOnce.scala:366)
at scala.collection.TraversableOnce.to$(TraversableOnce.scala:364)
at scala.collection.AbstractIterator.to(Iterator.scala:1431)
at scala.collection.TraversableOnce.toBuffer(TraversableOnce.scala:358)
at scala.collection.TraversableOnce.toBuffer$(TraversableOnce.scala:358)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1431)
at scala.collection.TraversableOnce.toArray(TraversableOnce.scala:345)
at scala.collection.TraversableOnce.toArray$(TraversableOnce.scala:339)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1431)
at com.johnsnowlabs.nlp.annotators.TokenizerModel.$anonfun$tag$2(TokenizerModel.scala:400)
at scala.collection.TraversableLike.$anonfun$map$1(TraversableLike.scala:286)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at scala.collection.TraversableLike.map(TraversableLike.scala:286)
at scala.collection.TraversableLike.map$(TraversableLike.scala:279)
at scala.collection.AbstractTraversable.map(Traversable.scala:108)
at com.johnsnowlabs.nlp.annotators.TokenizerModel.tag(TokenizerModel.scala:290)
at com.johnsnowlabs.nlp.annotators.TokenizerModel.annotate(TokenizerModel.scala:408)
at com.johnsnowlabs.nlp.HasSimpleAnnotate.$anonfun$dfAnnotate$1(HasSimpleAnnotate.scala:46)
... 19 more

24/03/20 14:10:24 ERROR TaskSetManager: Task 0 in stage 12.0 failed 1 times; aborting job

and

Py4JJavaError: An error occurred while calling o321.showString.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 12.0 failed 1 times, most recent failure: Lost task 0.0 in stage 12.0 (TID 34) (172.19.230.207 executor driver): org.apache.spark.SparkException: [FAILED_EXECUTE_UDF] Failed to execute user defined function (HasSimpleAnnotate$$Lambda$3430/0x00007ff2bcfe2c28: (array<array<struct<annotatorType:string,begin:int,end:int,result:string,metadata:map<string,string>,embeddings:array>>>) => array<struct<annotatorType:string,begin:int,end:int,result:string,metadata:map<string,string>,embeddings:array>>).
at org.apache.spark.sql.errors.QueryExecutionErrors$.failedExecuteUserDefinedFunctionError(QueryExecutionErrors.scala:217)
at org.apache.spark.sql.errors.QueryExecutionErrors.failedExecuteUserDefinedFunctionError(QueryExecutionErrors.scala)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.project_doConsume_0$(Unknown Source)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:760)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:888)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:888)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:364)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:328)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:92)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:161)
at org.apache.spark.scheduler.Task.run(Task.scala:139)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:554)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1529)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:557)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635)
at java.base/java.lang.Thread.run(Thread.java:840)
Caused by: java.lang.Exception: feature rules is not set
at com.johnsnowlabs.nlp.serialization.Feature.$anonfun$getOrDefault$1(Feature.scala:117)
at scala.Option.getOrElse(Option.scala:189)
at com.johnsnowlabs.nlp.serialization.Feature.getOrDefault(Feature.scala:117)
at com.johnsnowlabs.nlp.HasFeatures.$$(HasFeatures.scala:73)
at com.johnsnowlabs.nlp.HasFeatures.$$$(HasFeatures.scala:73)
at com.johnsnowlabs.nlp.AnnotatorModel.$$(AnnotatorModel.scala:29)
at com.johnsnowlabs.nlp.annotators.TokenizerModel.$anonfun$tag$5(TokenizerModel.scala:342)
at scala.collection.Iterator$$anon$11.nextCur(Iterator.scala:486)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:492)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:513)
at scala.collection.Iterator.foreach(Iterator.scala:943)
at scala.collection.Iterator.foreach$(Iterator.scala:943)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1431)
at scala.collection.generic.Growable.$plus$plus$eq(Growable.scala:62)
at scala.collection.generic.Growable.$plus$plus$eq$(Growable.scala:53)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:105)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:49)
at scala.collection.TraversableOnce.to(TraversableOnce.scala:366)
at scala.collection.TraversableOnce.to$(TraversableOnce.scala:364)
at scala.collection.AbstractIterator.to(Iterator.scala:1431)
at scala.collection.TraversableOnce.toBuffer(TraversableOnce.scala:358)
at scala.collection.TraversableOnce.toBuffer$(TraversableOnce.scala:358)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1431)
at scala.collection.TraversableOnce.toArray(TraversableOnce.scala:345)
at scala.collection.TraversableOnce.toArray$(TraversableOnce.scala:339)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1431)
at com.johnsnowlabs.nlp.annotators.TokenizerModel.$anonfun$tag$2(TokenizerModel.scala:400)
at scala.collection.TraversableLike.$anonfun$map$1(TraversableLike.scala:286)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at scala.collection.TraversableLike.map(TraversableLike.scala:286)
at scala.collection.TraversableLike.map$(TraversableLike.scala:279)
at scala.collection.AbstractTraversable.map(Traversable.scala:108)
at com.johnsnowlabs.nlp.annotators.TokenizerModel.tag(TokenizerModel.scala:290)
at com.johnsnowlabs.nlp.annotators.TokenizerModel.annotate(TokenizerModel.scala:408)
at com.johnsnowlabs.nlp.HasSimpleAnnotate.$anonfun$dfAnnotate$1(HasSimpleAnnotate.scala:46)
... 19 more

Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2785)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2721)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2720)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2720)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1206)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1206)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1206)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2984)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2923)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2912)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:971)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2263)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2284)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2303)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:61)
at org.apache.spark.sql.Dataset.collectFromPlan(Dataset.scala:4177)
at org.apache.spark.sql.Dataset.$anonfun$head$1(Dataset.scala:3161)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4167)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:526)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4165)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:118)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:195)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:103)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:827)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:65)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4165)
at org.apache.spark.sql.Dataset.head(Dataset.scala:3161)
at org.apache.spark.sql.Dataset.take(Dataset.scala:3382)
at org.apache.spark.sql.Dataset.getRows(Dataset.scala:284)
at org.apache.spark.sql.Dataset.showString(Dataset.scala:323)
at java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)
at java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.base/java.lang.reflect.Method.invoke(Method.java:568)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)
at py4j.ClientServerConnection.run(ClientServerConnection.java:106)
at java.base/java.lang.Thread.run(Thread.java:840)
Caused by: org.apache.spark.SparkException: [FAILED_EXECUTE_UDF] Failed to execute user defined function (HasSimpleAnnotate$$Lambda$3430/0x00007ff2bcfe2c28: (array<array<struct<annotatorType:string,begin:int,end:int,result:string,metadata:map<string,string>,embeddings:array>>>) => array<struct<annotatorType:string,begin:int,end:int,result:string,metadata:map<string,string>,embeddings:array>>).
at org.apache.spark.sql.errors.QueryExecutionErrors$.failedExecuteUserDefinedFunctionError(QueryExecutionErrors.scala:217)
at org.apache.spark.sql.errors.QueryExecutionErrors.failedExecuteUserDefinedFunctionError(QueryExecutionErrors.scala)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.project_doConsume_0$(Unknown Source)
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$$anon$1.hasNext(WholeStageCodegenExec.scala:760)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:888)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:888)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:364)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:328)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:92)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:161)
at org.apache.spark.scheduler.Task.run(Task.scala:139)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:554)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1529)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:557)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635)
... 1 more
Caused by: java.lang.Exception: feature rules is not set
at com.johnsnowlabs.nlp.serialization.Feature.$anonfun$getOrDefault$1(Feature.scala:117)
at scala.Option.getOrElse(Option.scala:189)
at com.johnsnowlabs.nlp.serialization.Feature.getOrDefault(Feature.scala:117)
at com.johnsnowlabs.nlp.HasFeatures.$$(HasFeatures.scala:73)
at com.johnsnowlabs.nlp.HasFeatures.$$$(HasFeatures.scala:73)
at com.johnsnowlabs.nlp.AnnotatorModel.$$(AnnotatorModel.scala:29)
at com.johnsnowlabs.nlp.annotators.TokenizerModel.$anonfun$tag$5(TokenizerModel.scala:342)
at scala.collection.Iterator$$anon$11.nextCur(Iterator.scala:486)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:492)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:513)
at scala.collection.Iterator.foreach(Iterator.scala:943)
at scala.collection.Iterator.foreach$(Iterator.scala:943)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1431)
at scala.collection.generic.Growable.$plus$plus$eq(Growable.scala:62)
at scala.collection.generic.Growable.$plus$plus$eq$(Growable.scala:53)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:105)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:49)
at scala.collection.TraversableOnce.to(TraversableOnce.scala:366)
at scala.collection.TraversableOnce.to$(TraversableOnce.scala:364)
at scala.collection.AbstractIterator.to(Iterator.scala:1431)
at scala.collection.TraversableOnce.toBuffer(TraversableOnce.scala:358)
at scala.collection.TraversableOnce.toBuffer$(TraversableOnce.scala:358)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1431)
at scala.collection.TraversableOnce.toArray(TraversableOnce.scala:345)
at scala.collection.TraversableOnce.toArray$(TraversableOnce.scala:339)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1431)
at com.johnsnowlabs.nlp.annotators.TokenizerModel.$anonfun$tag$2(TokenizerModel.scala:400)
at scala.collection.TraversableLike.$anonfun$map$1(TraversableLike.scala:286)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at scala.collection.TraversableLike.map(TraversableLike.scala:286)
at scala.collection.TraversableLike.map$(TraversableLike.scala:279)
at scala.collection.AbstractTraversable.map(Traversable.scala:108)
at com.johnsnowlabs.nlp.annotators.TokenizerModel.tag(TokenizerModel.scala:290)
at com.johnsnowlabs.nlp.annotators.TokenizerModel.annotate(TokenizerModel.scala:408)
at com.johnsnowlabs.nlp.HasSimpleAnnotate.$anonfun$dfAnnotate$1(HasSimpleAnnotate.scala:46)
... 19 more

  • 👍1