John Berryman created SPARK-20527:
-------------------------------------
Summary: Schema issues when fields are queries in different order
Key: SPARK-20527
URL: https://issues.apache.org/jira/browse/SPARK-20527
Project: Spark
Issue Type: Bug
Components: SQL
Affects Versions: 2.1.0
Reporter: John Berryman
In the code below I
* create a dataframe
* shove it into hive
* use spark.sql to query it with different field orderings, and retrieve the
schema
* try to to apply the same data to the schema
Observation: the order of the fields in the spark.sql query matters, in one
order the schema is successfully applied, in the other order we get an error
Expectation: since the ``rows`` all have named field, I would suspect that the
ordering should not matter and the error appears to be a bug
{code}
#######
# setup
from datetime import datetime
spark.sql('CREATE DATABASE test_trash')
rows = [
dict(number=1, letters='real1', some_date=datetime(2017,12,1,3,15)),
dict(number=2, letters='real2', some_date=datetime(2017,12,2,3,15)),
dict(number=3, letters='real3', some_date=datetime(2017,12,3,3,15)),
]
rows_rdd = spark.sparkContext.parallelize(rows).map(lambda r: Row(**r))
df = spark.createDataFrame(rows_rdd)
df.write.mode(saveMode='overwrite').saveAsTable('test_trash.thingy')
##############################
# this works as I would expect
schema = spark.sql('SELECT number, some_date FROM test_trash.thingy').schema
rows_rdd = spark.sparkContext.parallelize(rows).map(lambda r: Row(**r))
df = spark.createDataFrame(rows_rdd, schema)
assert df.count() == 1 # force evaluation so that the schema is evaluated
print "Made it here! "
########################################################################
# this fails and the only difference is in the order of the query fields
schema = spark.sql('SELECT some_date, number FROM test_trash.thingy').schema
rows_rdd = spark.sparkContext.parallelize(rows).map(lambda r: Row(**r))
df = spark.createDataFrame(rows_rdd, schema)
try:
df.count() # force evaluation so that the schema is evaluated
except:
print "Oh no! Why?!"
raise
else:
print "Everything worked just fine."
{code}
results in
{code}
Made it here!
Oh no! Why?!
Py4JJavaErrorTraceback (most recent call last)
<ipython-input-90-353e9a10b2b7> in <module>()
35 df = spark.createDataFrame(rows_rdd, schema)
36 try:
---> 37 df.count() # force evaluation so that the schema is evaluated
38 except:
39 print "Oh no! Why?!"
/usr/local/spark/python/pyspark/sql/dataframe.py in count(self)
378 2
379 """
--> 380 return int(self._jdf.count())
381
382 @ignore_unicode_prefix
/usr/local/spark/python/lib/py4j-0.10.4-src.zip/py4j/java_gateway.py in
__call__(self, *args)
1131 answer = self.gateway_client.send_command(command)
1132 return_value = get_return_value(
-> 1133 answer, self.gateway_client, self.target_id, self.name)
1134
1135 for temp_arg in temp_args:
/usr/local/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()
/usr/local/spark/python/lib/py4j-0.10.4-src.zip/py4j/protocol.py in
get_return_value(answer, gateway_client, target_id, name)
317 raise Py4JJavaError(
318 "An error occurred while calling {0}{1}{2}.\n".
--> 319 format(target_id, ".", name), value)
320 else:
321 raise Py4JError(
Py4JJavaError: An error occurred while calling o2469.count.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in
stage 127.0 failed 1 times, most recent failure: Lost task 0.0 in stage 127.0
(TID 100, localhost, executor driver):
org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/usr/local/spark/python/lib/pyspark.zip/pyspark/worker.py", line 174,
in main
process()
File "/usr/local/spark/python/lib/pyspark.zip/pyspark/worker.py", line 169,
in process
serializer.dump_stream(func(split_index, iterator), outfile)
File "/usr/local/spark/python/lib/pyspark.zip/pyspark/serializers.py", line
268, in dump_stream
vs = list(itertools.islice(iterator, batch))
File "/usr/local/spark/python/pyspark/sql/types.py", line 576, in toInternal
return tuple(f.toInternal(v) for f, v in zip(self.fields, obj))
File "/usr/local/spark/python/pyspark/sql/types.py", line 576, in <genexpr>
return tuple(f.toInternal(v) for f, v in zip(self.fields, obj))
File "/usr/local/spark/python/lib/pyspark.zip/pyspark/sql/types.py", line
436, in toInternal
return self.dataType.toInternal(obj)
File "/usr/local/spark/python/lib/pyspark.zip/pyspark/sql/types.py", line
190, in toInternal
seconds = (calendar.timegm(dt.utctimetuple()) if dt.tzinfo
AttributeError: 'int' object has no attribute 'tzinfo'
at
org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:193)
at
org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:234)
at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:152)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
at org.apache.spark.scheduler.Task.run(Task.scala:99)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
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$$failJobAndIndependentStages(DAGScheduler.scala:1435)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1423)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1422)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1422)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
at scala.Option.foreach(Option.scala:257)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:802)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1650)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1605)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1594)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at
org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:628)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1918)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1931)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1944)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1958)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:935)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
at org.apache.spark.rdd.RDD.collect(RDD.scala:934)
at
org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:275)
at
org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1.apply(Dataset.scala:2371)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
at org.apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2765)
at
org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$execute$1(Dataset.scala:2370)
at
org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collect(Dataset.scala:2377)
at
org.apache.spark.sql.Dataset$$anonfun$count$1.apply(Dataset.scala:2405)
at
org.apache.spark.sql.Dataset$$anonfun$count$1.apply(Dataset.scala:2404)
at org.apache.spark.sql.Dataset.withCallback(Dataset.scala:2778)
at org.apache.spark.sql.Dataset.count(Dataset.scala:2404)
at sun.reflect.GeneratedMethodAccessor40.invoke(Unknown Source)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.spark.api.python.PythonException: Traceback (most recent
call last):
File "/usr/local/spark/python/lib/pyspark.zip/pyspark/worker.py", line 174,
in main
process()
File "/usr/local/spark/python/lib/pyspark.zip/pyspark/worker.py", line 169,
in process
serializer.dump_stream(func(split_index, iterator), outfile)
File "/usr/local/spark/python/lib/pyspark.zip/pyspark/serializers.py", line
268, in dump_stream
vs = list(itertools.islice(iterator, batch))
File "/usr/local/spark/python/pyspark/sql/types.py", line 576, in toInternal
return tuple(f.toInternal(v) for f, v in zip(self.fields, obj))
File "/usr/local/spark/python/pyspark/sql/types.py", line 576, in <genexpr>
return tuple(f.toInternal(v) for f, v in zip(self.fields, obj))
File "/usr/local/spark/python/lib/pyspark.zip/pyspark/sql/types.py", line
436, in toInternal
return self.dataType.toInternal(obj)
File "/usr/local/spark/python/lib/pyspark.zip/pyspark/sql/types.py", line
190, in toInternal
seconds = (calendar.timegm(dt.utctimetuple()) if dt.tzinfo
AttributeError: 'int' object has no attribute 'tzinfo'
at
org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:193)
at
org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:234)
at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:152)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
at org.apache.spark.scheduler.Task.run(Task.scala:99)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
... 1 more
{code}
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
