--------------------------------------------------------------------------- Py4JJavaError Traceback (most recent call last) <command-4469290633535374> in <module>() 10 outputMapping={tfx.tensor_name("output_tensor"): 'outputCol'}) 11 ---> 12 odf = transformer.transform(sdf) /databricks/spark/python/pyspark/ml/base.py in transform(self, dataset, params) 171 return self.copy(params)._transform(dataset) 172 else: --> 173 return self._transform(dataset) 174 else: 175 raise ValueError("Params must be a param map but got %s." % type(params)) /local_disk0/spark-7ec0adfe-8e03-4eb0-a54d-95c8e4ab73f3/userFiles-90913bf8-a891-4187-bf0f-37b0dc71bdb6/addedFile4216599572521843780databricks_spark_deep_learning_0_3_0_spark2_2_s_2_11-a9181.jar/sparkdl/transformers/tf_tensor.py in _transform(self, dataset) 133 graph = tf.Graph() 134 with tf.Session(graph=graph): --> 135 analyzed_df = tfs.analyze(dataset) 136 out_tnsr_op_names = [tfx.op_name(tnsr_name) for tnsr_name, _ in output_mapping] 137 # Load graph /local_disk0/spark-7ec0adfe-8e03-4eb0-a54d-95c8e4ab73f3/userFiles-90913bf8-a891-4187-bf0f-37b0dc71bdb6/addedFile3677256273575012649databricks_tensorframes_0_2_9_s_2_11-853eb.jar/tensorframes/core.py in analyze(dframe) 376 :return: a Spark DataFrame with metadata information embedded. 377 """ --> 378 return DataFrame(_java_api().analyze(dframe._jdf), _sql) 379 380 def aggregate(fetches, grouped_data, initial_variables=_initial_variables_default): /databricks/spark/python/lib/py4j-0.10.6-src.zip/py4j/java_gateway.py in __call__(self, *args) 1158 answer = self.gateway_client.send_command(command) 1159 return_value = get_return_value( -> 1160 answer, self.gateway_client, self.target_id, self.name) 1161 1162 for temp_arg in temp_args: /databricks/spark/python/pyspark/sql/utils.py in deco(*a, **kw) 61 def deco(*a, **kw): 62 try: ---> 63 return f(*a, **kw) 64 except py4j.protocol.Py4JJavaError as e: 65 s = e.java_exception.toString() /databricks/spark/python/lib/py4j-0.10.6-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name) 318 raise Py4JJavaError( 319 "An error occurred while calling {0}{1}{2}.\n". --> 320 format(target_id, ".", name), value) 321 else: 322 raise Py4JError( Py4JJavaError: An error occurred while calling o3247.analyze. : org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 194.0 failed 1 times, most recent failure: Lost task 0.0 in stage 194.0 (TID 3608, localhost, executor driver): java.net.SocketException: Socket is closed at java.net.Socket.getInputStream(Socket.java:903) at org.apache.spark.api.python.BasePythonRunner.compute(PythonRunner.scala:114) at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:66) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:332) at org.apache.spark.rdd.RDD.iterator(RDD.scala:296) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:332) at org.apache.spark.rdd.RDD.iterator(RDD.scala:296) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:332) at org.apache.spark.rdd.RDD.iterator(RDD.scala:296) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:332) at org.apache.spark.rdd.RDD.iterator(RDD.scala:296) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:332) at org.apache.spark.rdd.RDD.iterator(RDD.scala:296) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:332) at org.apache.spark.rdd.RDD.iterator(RDD.scala:296) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:332) at org.apache.spark.rdd.RDD.iterator(RDD.scala:296) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:332) at org.apache.spark.rdd.RDD.iterator(RDD.scala:296) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87) at org.apache.spark.scheduler.Task.run(Task.scala:111) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:350) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624) at java.lang.Thread.run(Thread.java:748) Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1718) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1706) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1705) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1705) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:943) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:943) at scala.Option.foreach(Option.scala:257) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:943) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1941) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1889) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1877) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:740) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2109) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2130) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2149) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2174) at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:947) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112) at org.apache.spark.rdd.RDD.withScope(RDD.scala:371) at org.apache.spark.rdd.RDD.collect(RDD.scala:946) at org.tensorframes.ExtraOperations$.deepAnalyzeDataFrame(ExperimentalOperations.scala:92) at org.tensorframes.ExperimentalOperations$class.analyze(ExperimentalOperations.scala:37) at org.tensorframes.impl.DebugRowOps.analyze(DebugRowOps.scala:281) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:498) at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:380) at py4j.Gateway.invoke(Gateway.java:295) at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) at py4j.commands.CallCommand.execute(CallCommand.java:79) at py4j.GatewayConnection.run(GatewayConnection.java:226) at java.lang.Thread.run(Thread.java:748) Caused by: java.net.SocketException: Socket is closed at java.net.Socket.getInputStream(Socket.java:903) at org.apache.spark.api.python.BasePythonRunner.compute(PythonRunner.scala:114) at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:66) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:332) at org.apache.spark.rdd.RDD.iterator(RDD.scala:296) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:332) at org.apache.spark.rdd.RDD.iterator(RDD.scala:296) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:332) at org.apache.spark.rdd.RDD.iterator(RDD.scala:296) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:332) at org.apache.spark.rdd.RDD.iterator(RDD.scala:296) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:332) at org.apache.spark.rdd.RDD.iterator(RDD.scala:296) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:332) at org.apache.spark.rdd.RDD.iterator(RDD.scala:296) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:332) at org.apache.spark.rdd.RDD.iterator(RDD.scala:296) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:332) at org.apache.spark.rdd.RDD.iterator(RDD.scala:296) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87) at org.apache.spark.scheduler.Task.run(Task.scala:111) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:350) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624) ... 1 more