Gaëtan Lehmann created SPARK-13082:
--------------------------------------
Summary: sqlCtx.real.json() doesn't work with PythonRDD
Key: SPARK-13082
URL: https://issues.apache.org/jira/browse/SPARK-13082
Project: Spark
Issue Type: Bug
Components: PySpark
Affects Versions: 1.6.0
Environment: Tested on macosx 10.10 using Spark 1.6
Reporter: Gaëtan Lehmann
This code works without problem:
sqlCtx.read.json(sqlCtx.range(10).toJSON())
but these ones fail with the traceback below:
sqlCtx.read.json(sc.parallelize(['{"id":1}']*10))
sqlCtx.read.json(sqlCtx.range(10).toJSON().pipe("cat"))
sqlCtx.read.json(sqlCtx.range(10).toJSON().map(lambda x: x))
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-93-91a986fee7f9> in <module>()
----> 1 sqlCtx.read.json(sqlCtx.range(10).toJSON().map(lambda x: x))
/usr/local/Cellar/apache-spark/1.6.0/libexec/python/pyspark/sql/readwriter.pyc
in json(self, path, schema)
178 return
self._df(self._jreader.json(self._sqlContext._sc._jvm.PythonUtils.toSeq(path)))
179 elif isinstance(path, RDD):
--> 180 return self._df(self._jreader.json(path._jrdd))
181 else:
182 raise TypeError("path can be only string or RDD")
/usr/local/Cellar/apache-spark/1.6.0/libexec/python/lib/py4j-0.9-src.zip/py4j/java_gateway.py
in __call__(self, *args)
811 answer = self.gateway_client.send_command(command)
812 return_value = get_return_value(
--> 813 answer, self.gateway_client, self.target_id, self.name)
814
815 for temp_arg in temp_args:
/usr/local/Cellar/apache-spark/1.6.0/libexec/python/pyspark/sql/utils.pyc in
deco(*a, **kw)
43 def deco(*a, **kw):
44 try:
---> 45 return f(*a, **kw)
46 except py4j.protocol.Py4JJavaError as e:
47 s = e.java_exception.toString()
/usr/local/Cellar/apache-spark/1.6.0/libexec/python/lib/py4j-0.9-src.zip/py4j/protocol.py
in get_return_value(answer, gateway_client, target_id, name)
306 raise Py4JJavaError(
307 "An error occurred while calling {0}{1}{2}.\n".
--> 308 format(target_id, ".", name), value)
309 else:
310 raise Py4JError(
Py4JJavaError: An error occurred while calling o961.json.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in
stage 55.0 failed 1 times, most recent failure: Lost task 0.0 in stage 55.0
(TID 149, localhost): java.lang.ClassCastException: [B cannot be cast to
java.lang.String
at
org.apache.spark.sql.execution.datasources.json.InferSchema$$anonfun$1$$anonfun$apply$1.apply(InferSchema.scala:53)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.foldLeft(TraversableOnce.scala:144)
at scala.collection.AbstractIterator.foldLeft(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.aggregate(TraversableOnce.scala:201)
at scala.collection.AbstractIterator.aggregate(Iterator.scala:1157)
at
org.apache.spark.rdd.RDD$$anonfun$treeAggregate$1$$anonfun$23.apply(RDD.scala:1121)
at
org.apache.spark.rdd.RDD$$anonfun$treeAggregate$1$$anonfun$23.apply(RDD.scala:1121)
at
org.apache.spark.rdd.RDD$$anonfun$treeAggregate$1$$anonfun$24.apply(RDD.scala:1122)
at
org.apache.spark.rdd.RDD$$anonfun$treeAggregate$1$$anonfun$24.apply(RDD.scala:1122)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at scala.Option.foreach(Option.scala:236)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at
org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1952)
at org.apache.spark.rdd.RDD$$anonfun$reduce$1.apply(RDD.scala:1025)
at
org.apache.spark.rdd.RDDOperationScope$.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.RDD.reduce(RDD.scala:1007)
at
org.apache.spark.rdd.RDD$$anonfun$treeAggregate$1.apply(RDD.scala:1136)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.RDD.treeAggregate(RDD.scala:1113)
at
org.apache.spark.sql.execution.datasources.json.InferSchema$.infer(InferSchema.scala:65)
at
org.apache.spark.sql.execution.datasources.json.JSONRelation$$anonfun$4.apply(JSONRelation.scala:114)
at
org.apache.spark.sql.execution.datasources.json.JSONRelation$$anonfun$4.apply(JSONRelation.scala:109)
at scala.Option.getOrElse(Option.scala:120)
at
org.apache.spark.sql.execution.datasources.json.JSONRelation.dataSchema$lzycompute(JSONRelation.scala:109)
at
org.apache.spark.sql.execution.datasources.json.JSONRelation.dataSchema(JSONRelation.scala:108)
at
org.apache.spark.sql.sources.HadoopFsRelation.schema$lzycompute(interfaces.scala:636)
at
org.apache.spark.sql.sources.HadoopFsRelation.schema(interfaces.scala:635)
at
org.apache.spark.sql.execution.datasources.LogicalRelation.<init>(LogicalRelation.scala:37)
at
org.apache.spark.sql.SQLContext.baseRelationToDataFrame(SQLContext.scala:442)
at org.apache.spark.sql.DataFrameReader.json(DataFrameReader.scala:288)
at org.apache.spark.sql.DataFrameReader.json(DataFrameReader.scala:275)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381)
at py4j.Gateway.invoke(Gateway.java:259)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:209)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.ClassCastException: [B cannot be cast to java.lang.String
at
org.apache.spark.sql.execution.datasources.json.InferSchema$$anonfun$1$$anonfun$apply$1.apply(InferSchema.scala:53)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.foldLeft(TraversableOnce.scala:144)
at scala.collection.AbstractIterator.foldLeft(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.aggregate(TraversableOnce.scala:201)
at scala.collection.AbstractIterator.aggregate(Iterator.scala:1157)
at
org.apache.spark.rdd.RDD$$anonfun$treeAggregate$1$$anonfun$23.apply(RDD.scala:1121)
at
org.apache.spark.rdd.RDD$$anonfun$treeAggregate$1$$anonfun$23.apply(RDD.scala:1121)
at
org.apache.spark.rdd.RDD$$anonfun$treeAggregate$1$$anonfun$24.apply(RDD.scala:1122)
at
org.apache.spark.rdd.RDD$$anonfun$treeAggregate$1$$anonfun$24.apply(RDD.scala:1122)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
... 1 more
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
