[
https://issues.apache.org/jira/browse/SPARK-20086?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
mandar uapdhye updated SPARK-20086:
-----------------------------------
Description:
original post at
[stackoverflow |
http://stackoverflow.com/questions/43007433/pyspark-2-1-0-error-when-working-with-window-function]
I get error when working with pyspark window function. here is some example
code:
{code:title=test.py|borderStyle=solid}
import pyspark
import pyspark.sql.functions as sf
import pyspark.sql.types as sparktypes
from pyspark.sql import window
sc = pyspark.SparkContext()
sqlc = pyspark.SQLContext(sc)
rdd = sc.parallelize([(1, 2.0), (1, 3.0), (1, 1.), (1, -2.), (1, -1.)])
df = sqlc.createDataFrame(rdd, ["x", "AmtPaid"])
df.show()
{code}
gives:
+---+-------+
| x|AmtPaid|
+---+-------+
| 1| 2.0|
| 1| 3.0|
| 1| 1.0|
| 1| -2.0|
| 1| -1.0|
+---+-------+
next, compute cumulative sum
win_spec_max = (window.Window
.partitionBy(['x'])
.rowsBetween(window.Window.unboundedPreceding, 0)))
df = df.withColumn('AmtPaidCumSum',
sf.sum(sf.col('AmtPaid')).over(win_spec_max))
df.show()
gives,
+---+-------+-------------+
| x|AmtPaid|AmtPaidCumSum|
+---+-------+-------------+
| 1| 2.0| 2.0|
| 1| 3.0| 5.0|
| 1| 1.0| 6.0|
| 1| -2.0| 4.0|
| 1| -1.0| 3.0|
+---+-------+-------------+
next, compute cumulative max,
df = df.withColumn('AmtPaidCumSumMax',
sf.max(sf.col('AmtPaidCumSum')).over(win_spec_max))
df.show()
gives error log
Py4JJavaError: An error occurred while calling o2609.showString.
with traceback:
Py4JJavaErrorTraceback (most recent call last)
<ipython-input-215-3106d06b6e49> in <module>()
----> 1 df.show()
/Users/<>/spark-2.1.0-bin-hadoop2.7/python/pyspark/sql/dataframe.pyc in
show(self, n, truncate)
316 """
317 if isinstance(truncate, bool) and truncate:
--> 318 print(self._jdf.showString(n, 20))
319 else:
320 print(self._jdf.showString(n, int(truncate)))
/Users/<>/.virtualenvs/<>/lib/python2.7/site-packages/py4j/java_gateway.pyc
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:
/Users/<>/spark-2.1.0-bin-hadoop2.7/python/pyspark/sql/utils.pyc 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()
/Users/<>/.virtualenvs/<>/lib/python2.7/site-packages/py4j/protocol.pyc 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(
but interestingly enough, if i introduce another change before sencond window
operation, say inserting a column then it does not give that error:
df = df.withColumn('MaxBound', sf.lit(6.))
df.show()
+---+-------+-------------+--------+
| x|AmtPaid|AmtPaidCumSum|MaxBound|
+---+-------+-------------+--------+
| 1| 2.0| 2.0| 6.0|
| 1| 3.0| 5.0| 6.0|
| 1| 1.0| 6.0| 6.0|
| 1| -2.0| 4.0| 6.0|
| 1| -1.0| 3.0| 6.0|
+---+-------+-------------+--------+
#then apply the second window operations
df = df.withColumn('AmtPaidCumSumMax',
sf.max(sf.col('AmtPaidCumSum')).over(win_spec_max))
df.show()
+---+-------+-------------+--------+----------------+
| x|AmtPaid|AmtPaidCumSum|MaxBound|AmtPaidCumSumMax|
+---+-------+-------------+--------+----------------+
| 1| 2.0| 2.0| 6.0| 2.0|
| 1| 3.0| 5.0| 6.0| 5.0|
| 1| 1.0| 6.0| 6.0| 6.0|
| 1| -2.0| 4.0| 6.0| 6.0|
| 1| -1.0| 3.0| 6.0| 6.0|
+---+-------+-------------+--------+----------------+
I do not understand this behaviour
well, so far so good, but then I try another operation then again get similar
error:
def _udf_compare_cumsum_sll(x):
if x['AmtPaidCumSumMax'] >= x['MaxBound']:
output = 0
else:
output = x['AmtPaid']
udf_compare_cumsum_sll = sf.udf(_udf_compare_cumsum_sll,
sparktypes.FloatType())
df = df.withColumn('AmtPaidAdjusted',
udf_compare_cumsum_sll(sf.struct([df[x] for x in df.columns])))
df.show()
gives,
Py4JJavaErrorTraceback (most recent call last)
<ipython-input-18-3106d06b6e49> in <module>()
----> 1 df.show()
/Users/<>/spark-2.1.0-bin-hadoop2.7/python/pyspark/sql/dataframe.pyc in
show(self, n, truncate)
316 """
317 if isinstance(truncate, bool) and truncate:
--> 318 print(self._jdf.showString(n, 20))
319 else:
320 print(self._jdf.showString(n, int(truncate)))
/Users/<>/.virtualenvs/<>/lib/python2.7/site-packages/py4j/java_gateway.pyc
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:
/Users/<>/spark-2.1.0-bin-hadoop2.7/python/pyspark/sql/utils.pyc 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()
/Users/<>/.virtualenvs/<>/lib/python2.7/site-packages/py4j/protocol.pyc 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 o91.showString.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0
in stage 36.0 failed 1 times, most recent failure: Lost task 0.0 in stage 36.0
(TID 645, localhost, executor driver):
org.apache.spark.sql.catalyst.errors.package$TreeNodeException: Binding
attribute, tree: AmtPaidCumSum#10
I wonder if someone could reproduce this behaviour ...
here is complete log ..
Py4JJavaErrorTraceback (most recent call last)
<ipython-input-69-3106d06b6e49> in <module>()
----> 1 df.show()
/Users/<>/spark-2.1.0-bin-hadoop2.7/python/pyspark/sql/dataframe.pyc in
show(self, n, truncate)
316 """
317 if isinstance(truncate, bool) and truncate:
--> 318 print(self._jdf.showString(n, 20))
319 else:
320 print(self._jdf.showString(n, int(truncate)))
/Users/<>/.virtualenvs/<>/lib/python2.7/site-packages/py4j/java_gateway.pyc
in __call__(self, *args)
1131 answer = self.gateway_client.send_command(command)
1132 return_value = get_return_value(
-> 1133 answer, self.gateway_client, self.target_id, self.name)
1134
1135 for temp_arg in temp_args:
/Users/<>/spark-2.1.0-bin-hadoop2.7/python/pyspark/sql/utils.pyc in
deco(*a, **kw)
61 def deco(*a, **kw):
62 try:
---> 63 return f(*a, **kw)
64 except py4j.protocol.Py4JJavaError as e:
65 s = e.java_exception.toString()
/Users/<>/.virtualenvs/<>/lib/python2.7/site-packages/py4j/protocol.pyc in
get_return_value(answer, gateway_client, target_id, name)
317 raise Py4JJavaError(
318 "An error occurred while calling {0}{1}{2}.\n".
--> 319 format(target_id, ".", name), value)
320 else:
321 raise Py4JError(
Py4JJavaError: An error occurred while calling o703.showString.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0
in stage 119.0 failed 1 times, most recent failure: Lost task 0.0 in stage
119.0 (TID 1817, localhost, executor driver):
org.apache.spark.sql.catalyst.errors.package$TreeNodeException: Binding
attribute, tree: AmtPaidCumSum#2076
at
org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:56)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:88)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:87)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:288)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:288)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:287)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:293)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:293)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5$$anonfun$apply$11.apply(TreeNode.scala:360)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.immutable.List.foreach(List.scala:381)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.immutable.List.map(List.scala:285)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:358)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:188)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:329)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:293)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:277)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$.bindReference(BoundAttribute.scala:87)
at
org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$$anonfun$bind$1.apply(GenerateMutableProjection.scala:38)
at
org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$$anonfun$bind$1.apply(GenerateMutableProjection.scala:38)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at
org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.bind(GenerateMutableProjection.scala:38)
at
org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.generate(GenerateMutableProjection.scala:44)
at
org.apache.spark.sql.execution.SparkPlan.newMutableProjection(SparkPlan.scala:353)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$org$apache$spark$sql$execution$window$WindowExec$$anonfun$$processor$1$1.apply(WindowExec.scala:203)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$org$apache$spark$sql$execution$window$WindowExec$$anonfun$$processor$1$1.apply(WindowExec.scala:202)
at
org.apache.spark.sql.execution.window.AggregateProcessor$.apply(AggregateProcessor.scala:98)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2.org$apache$spark$sql$execution$window$WindowExec$$anonfun$$processor$1(WindowExec.scala:198)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$6.apply(WindowExec.scala:225)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$6.apply(WindowExec.scala:222)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$14$$anon$1$$anonfun$16.apply(WindowExec.scala:318)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$14$$anon$1$$anonfun$16.apply(WindowExec.scala:318)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:186)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$14$$anon$1.<init>(WindowExec.scala:318)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$14.apply(WindowExec.scala:290)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$14.apply(WindowExec.scala:289)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:796)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:796)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:99)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.RuntimeException: Couldn't find AmtPaidCumSum#2076 in
[sum#2299,max#2300,x#2066L,AmtPaid#2067]
at scala.sys.package$.error(package.scala:27)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:94)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:88)
at
org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:52)
... 62 more
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.sql.execution.SparkPlan.executeTake(SparkPlan.scala:333)
at
org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38)
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$$anonfun$head$1.apply(Dataset.scala:2113)
at
org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2112)
at org.apache.spark.sql.Dataset.withTypedCallback(Dataset.scala:2795)
at org.apache.spark.sql.Dataset.head(Dataset.scala:2112)
at org.apache.spark.sql.Dataset.take(Dataset.scala:2327)
at org.apache.spark.sql.Dataset.showString(Dataset.scala:248)
at sun.reflect.GeneratedMethodAccessor83.invoke(Unknown Source)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.spark.sql.catalyst.errors.package$TreeNodeException:
Binding attribute, tree: null
at
org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:56)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:88)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:87)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:288)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:288)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:287)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:293)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:293)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5$$anonfun$apply$11.apply(TreeNode.scala:360)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.immutable.List.foreach(List.scala:381)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.immutable.List.map(List.scala:285)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:358)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:188)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:329)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:293)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:277)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$.bindReference(BoundAttribute.scala:87)
at
org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$$anonfun$bind$1.apply(GenerateMutableProjection.scala:38)
at
org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$$anonfun$bind$1.apply(GenerateMutableProjection.scala:38)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at
org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.bind(GenerateMutableProjection.scala:38)
at
org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.generate(GenerateMutableProjection.scala:44)
at
org.apache.spark.sql.execution.SparkPlan.newMutableProjection(SparkPlan.scala:353)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$org$apache$spark$sql$execution$window$WindowExec$$anonfun$$processor$1$1.apply(WindowExec.scala:203)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$org$apache$spark$sql$execution$window$WindowExec$$anonfun$$processor$1$1.apply(WindowExec.scala:202)
at
org.apache.spark.sql.execution.window.AggregateProcessor$.apply(AggregateProcessor.scala:98)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2.org$apache$spark$sql$execution$window$WindowExec$$anonfun$$processor$1(WindowExec.scala:198)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$6.apply(WindowExec.scala:225)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$6.apply(WindowExec.scala:222)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$14$$anon$1$$anonfun$16.apply(WindowExec.scala:318)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$14$$anon$1$$anonfun$16.apply(WindowExec.scala:318)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:186)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$14$$anon$1.<init>(WindowExec.scala:318)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$14.apply(WindowExec.scala:290)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$14.apply(WindowExec.scala:289)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:796)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:796)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:99)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
... 1 more
Caused by: java.lang.RuntimeException: Couldn't find AmtPaidCumSum#2076 in
[sum#2299,max#2300,x#2066L,AmtPaid#2067]
at scala.sys.package$.error(package.scala:27)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:94)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:88)
at
org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:52)
... 62 more
was:
original post at
[stackoverflow |
http://stackoverflow.com/questions/43007433/pyspark-2-1-0-error-when-working-with-window-function]
I get error when working with pyspark window function. here is some example
code:
import pyspark
import pyspark.sql.functions as sf
import pyspark.sql.types as sparktypes
from pyspark.sql import window
sc = pyspark.SparkContext()
sqlc = pyspark.SQLContext(sc)
rdd = sc.parallelize([(1, 2.0), (1, 3.0), (1, 1.), (1, -2.), (1, -1.)])
df = sqlc.createDataFrame(rdd, ["x", "AmtPaid"])
df.show()
gives:
+---+-------+
| x|AmtPaid|
+---+-------+
| 1| 2.0|
| 1| 3.0|
| 1| 1.0|
| 1| -2.0|
| 1| -1.0|
+---+-------+
next, compute cumulative sum
win_spec_max = (window.Window
.partitionBy(['x'])
.rowsBetween(window.Window.unboundedPreceding, 0)))
df = df.withColumn('AmtPaidCumSum',
sf.sum(sf.col('AmtPaid')).over(win_spec_max))
df.show()
gives,
+---+-------+-------------+
| x|AmtPaid|AmtPaidCumSum|
+---+-------+-------------+
| 1| 2.0| 2.0|
| 1| 3.0| 5.0|
| 1| 1.0| 6.0|
| 1| -2.0| 4.0|
| 1| -1.0| 3.0|
+---+-------+-------------+
next, compute cumulative max,
df = df.withColumn('AmtPaidCumSumMax',
sf.max(sf.col('AmtPaidCumSum')).over(win_spec_max))
df.show()
gives error log
Py4JJavaError: An error occurred while calling o2609.showString.
with traceback:
Py4JJavaErrorTraceback (most recent call last)
<ipython-input-215-3106d06b6e49> in <module>()
----> 1 df.show()
/Users/<>/spark-2.1.0-bin-hadoop2.7/python/pyspark/sql/dataframe.pyc in
show(self, n, truncate)
316 """
317 if isinstance(truncate, bool) and truncate:
--> 318 print(self._jdf.showString(n, 20))
319 else:
320 print(self._jdf.showString(n, int(truncate)))
/Users/<>/.virtualenvs/<>/lib/python2.7/site-packages/py4j/java_gateway.pyc
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:
/Users/<>/spark-2.1.0-bin-hadoop2.7/python/pyspark/sql/utils.pyc 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()
/Users/<>/.virtualenvs/<>/lib/python2.7/site-packages/py4j/protocol.pyc 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(
but interestingly enough, if i introduce another change before sencond window
operation, say inserting a column then it does not give that error:
df = df.withColumn('MaxBound', sf.lit(6.))
df.show()
+---+-------+-------------+--------+
| x|AmtPaid|AmtPaidCumSum|MaxBound|
+---+-------+-------------+--------+
| 1| 2.0| 2.0| 6.0|
| 1| 3.0| 5.0| 6.0|
| 1| 1.0| 6.0| 6.0|
| 1| -2.0| 4.0| 6.0|
| 1| -1.0| 3.0| 6.0|
+---+-------+-------------+--------+
#then apply the second window operations
df = df.withColumn('AmtPaidCumSumMax',
sf.max(sf.col('AmtPaidCumSum')).over(win_spec_max))
df.show()
+---+-------+-------------+--------+----------------+
| x|AmtPaid|AmtPaidCumSum|MaxBound|AmtPaidCumSumMax|
+---+-------+-------------+--------+----------------+
| 1| 2.0| 2.0| 6.0| 2.0|
| 1| 3.0| 5.0| 6.0| 5.0|
| 1| 1.0| 6.0| 6.0| 6.0|
| 1| -2.0| 4.0| 6.0| 6.0|
| 1| -1.0| 3.0| 6.0| 6.0|
+---+-------+-------------+--------+----------------+
I do not understand this behaviour
well, so far so good, but then I try another operation then again get similar
error:
def _udf_compare_cumsum_sll(x):
if x['AmtPaidCumSumMax'] >= x['MaxBound']:
output = 0
else:
output = x['AmtPaid']
udf_compare_cumsum_sll = sf.udf(_udf_compare_cumsum_sll,
sparktypes.FloatType())
df = df.withColumn('AmtPaidAdjusted',
udf_compare_cumsum_sll(sf.struct([df[x] for x in df.columns])))
df.show()
gives,
Py4JJavaErrorTraceback (most recent call last)
<ipython-input-18-3106d06b6e49> in <module>()
----> 1 df.show()
/Users/<>/spark-2.1.0-bin-hadoop2.7/python/pyspark/sql/dataframe.pyc in
show(self, n, truncate)
316 """
317 if isinstance(truncate, bool) and truncate:
--> 318 print(self._jdf.showString(n, 20))
319 else:
320 print(self._jdf.showString(n, int(truncate)))
/Users/<>/.virtualenvs/<>/lib/python2.7/site-packages/py4j/java_gateway.pyc
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:
/Users/<>/spark-2.1.0-bin-hadoop2.7/python/pyspark/sql/utils.pyc 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()
/Users/<>/.virtualenvs/<>/lib/python2.7/site-packages/py4j/protocol.pyc 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 o91.showString.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0
in stage 36.0 failed 1 times, most recent failure: Lost task 0.0 in stage 36.0
(TID 645, localhost, executor driver):
org.apache.spark.sql.catalyst.errors.package$TreeNodeException: Binding
attribute, tree: AmtPaidCumSum#10
I wonder if someone could reproduce this behaviour ...
here is complete log ..
Py4JJavaErrorTraceback (most recent call last)
<ipython-input-69-3106d06b6e49> in <module>()
----> 1 df.show()
/Users/<>/spark-2.1.0-bin-hadoop2.7/python/pyspark/sql/dataframe.pyc in
show(self, n, truncate)
316 """
317 if isinstance(truncate, bool) and truncate:
--> 318 print(self._jdf.showString(n, 20))
319 else:
320 print(self._jdf.showString(n, int(truncate)))
/Users/<>/.virtualenvs/<>/lib/python2.7/site-packages/py4j/java_gateway.pyc
in __call__(self, *args)
1131 answer = self.gateway_client.send_command(command)
1132 return_value = get_return_value(
-> 1133 answer, self.gateway_client, self.target_id, self.name)
1134
1135 for temp_arg in temp_args:
/Users/<>/spark-2.1.0-bin-hadoop2.7/python/pyspark/sql/utils.pyc in
deco(*a, **kw)
61 def deco(*a, **kw):
62 try:
---> 63 return f(*a, **kw)
64 except py4j.protocol.Py4JJavaError as e:
65 s = e.java_exception.toString()
/Users/<>/.virtualenvs/<>/lib/python2.7/site-packages/py4j/protocol.pyc in
get_return_value(answer, gateway_client, target_id, name)
317 raise Py4JJavaError(
318 "An error occurred while calling {0}{1}{2}.\n".
--> 319 format(target_id, ".", name), value)
320 else:
321 raise Py4JError(
Py4JJavaError: An error occurred while calling o703.showString.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0
in stage 119.0 failed 1 times, most recent failure: Lost task 0.0 in stage
119.0 (TID 1817, localhost, executor driver):
org.apache.spark.sql.catalyst.errors.package$TreeNodeException: Binding
attribute, tree: AmtPaidCumSum#2076
at
org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:56)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:88)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:87)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:288)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:288)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:287)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:293)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:293)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5$$anonfun$apply$11.apply(TreeNode.scala:360)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.immutable.List.foreach(List.scala:381)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.immutable.List.map(List.scala:285)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:358)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:188)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:329)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:293)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:277)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$.bindReference(BoundAttribute.scala:87)
at
org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$$anonfun$bind$1.apply(GenerateMutableProjection.scala:38)
at
org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$$anonfun$bind$1.apply(GenerateMutableProjection.scala:38)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at
org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.bind(GenerateMutableProjection.scala:38)
at
org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.generate(GenerateMutableProjection.scala:44)
at
org.apache.spark.sql.execution.SparkPlan.newMutableProjection(SparkPlan.scala:353)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$org$apache$spark$sql$execution$window$WindowExec$$anonfun$$processor$1$1.apply(WindowExec.scala:203)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$org$apache$spark$sql$execution$window$WindowExec$$anonfun$$processor$1$1.apply(WindowExec.scala:202)
at
org.apache.spark.sql.execution.window.AggregateProcessor$.apply(AggregateProcessor.scala:98)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2.org$apache$spark$sql$execution$window$WindowExec$$anonfun$$processor$1(WindowExec.scala:198)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$6.apply(WindowExec.scala:225)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$6.apply(WindowExec.scala:222)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$14$$anon$1$$anonfun$16.apply(WindowExec.scala:318)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$14$$anon$1$$anonfun$16.apply(WindowExec.scala:318)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:186)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$14$$anon$1.<init>(WindowExec.scala:318)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$14.apply(WindowExec.scala:290)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$14.apply(WindowExec.scala:289)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:796)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:796)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:99)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.RuntimeException: Couldn't find AmtPaidCumSum#2076 in
[sum#2299,max#2300,x#2066L,AmtPaid#2067]
at scala.sys.package$.error(package.scala:27)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:94)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:88)
at
org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:52)
... 62 more
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.sql.execution.SparkPlan.executeTake(SparkPlan.scala:333)
at
org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38)
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$$anonfun$head$1.apply(Dataset.scala:2113)
at
org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2112)
at org.apache.spark.sql.Dataset.withTypedCallback(Dataset.scala:2795)
at org.apache.spark.sql.Dataset.head(Dataset.scala:2112)
at org.apache.spark.sql.Dataset.take(Dataset.scala:2327)
at org.apache.spark.sql.Dataset.showString(Dataset.scala:248)
at sun.reflect.GeneratedMethodAccessor83.invoke(Unknown Source)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.spark.sql.catalyst.errors.package$TreeNodeException:
Binding attribute, tree: null
at
org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:56)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:88)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:87)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:288)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:288)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:287)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:293)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:293)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5$$anonfun$apply$11.apply(TreeNode.scala:360)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.immutable.List.foreach(List.scala:381)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.immutable.List.map(List.scala:285)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:358)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:188)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:329)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:293)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:277)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$.bindReference(BoundAttribute.scala:87)
at
org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$$anonfun$bind$1.apply(GenerateMutableProjection.scala:38)
at
org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$$anonfun$bind$1.apply(GenerateMutableProjection.scala:38)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at
org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.bind(GenerateMutableProjection.scala:38)
at
org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.generate(GenerateMutableProjection.scala:44)
at
org.apache.spark.sql.execution.SparkPlan.newMutableProjection(SparkPlan.scala:353)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$org$apache$spark$sql$execution$window$WindowExec$$anonfun$$processor$1$1.apply(WindowExec.scala:203)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$org$apache$spark$sql$execution$window$WindowExec$$anonfun$$processor$1$1.apply(WindowExec.scala:202)
at
org.apache.spark.sql.execution.window.AggregateProcessor$.apply(AggregateProcessor.scala:98)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2.org$apache$spark$sql$execution$window$WindowExec$$anonfun$$processor$1(WindowExec.scala:198)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$6.apply(WindowExec.scala:225)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$6.apply(WindowExec.scala:222)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$14$$anon$1$$anonfun$16.apply(WindowExec.scala:318)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$14$$anon$1$$anonfun$16.apply(WindowExec.scala:318)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:186)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$14$$anon$1.<init>(WindowExec.scala:318)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$14.apply(WindowExec.scala:290)
at
org.apache.spark.sql.execution.window.WindowExec$$anonfun$14.apply(WindowExec.scala:289)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:796)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:796)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:99)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
... 1 more
Caused by: java.lang.RuntimeException: Couldn't find AmtPaidCumSum#2076 in
[sum#2299,max#2300,x#2066L,AmtPaid#2067]
at scala.sys.package$.error(package.scala:27)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:94)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:88)
at
org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:52)
... 62 more
> issue with pyspark 2.1.0 window function
> ----------------------------------------
>
> Key: SPARK-20086
> URL: https://issues.apache.org/jira/browse/SPARK-20086
> Project: Spark
> Issue Type: Bug
> Components: PySpark
> Affects Versions: 2.1.0
> Reporter: mandar uapdhye
>
> original post at
> [stackoverflow |
> http://stackoverflow.com/questions/43007433/pyspark-2-1-0-error-when-working-with-window-function]
> I get error when working with pyspark window function. here is some example
> code:
> {code:title=test.py|borderStyle=solid}
> import pyspark
> import pyspark.sql.functions as sf
> import pyspark.sql.types as sparktypes
> from pyspark.sql import window
>
> sc = pyspark.SparkContext()
> sqlc = pyspark.SQLContext(sc)
> rdd = sc.parallelize([(1, 2.0), (1, 3.0), (1, 1.), (1, -2.), (1, -1.)])
> df = sqlc.createDataFrame(rdd, ["x", "AmtPaid"])
> df.show()
> {code}
> gives:
> +---+-------+
> | x|AmtPaid|
> +---+-------+
> | 1| 2.0|
> | 1| 3.0|
> | 1| 1.0|
> | 1| -2.0|
> | 1| -1.0|
> +---+-------+
> next, compute cumulative sum
> win_spec_max = (window.Window
> .partitionBy(['x'])
> .rowsBetween(window.Window.unboundedPreceding, 0)))
> df = df.withColumn('AmtPaidCumSum',
> sf.sum(sf.col('AmtPaid')).over(win_spec_max))
> df.show()
> gives,
> +---+-------+-------------+
> | x|AmtPaid|AmtPaidCumSum|
> +---+-------+-------------+
> | 1| 2.0| 2.0|
> | 1| 3.0| 5.0|
> | 1| 1.0| 6.0|
> | 1| -2.0| 4.0|
> | 1| -1.0| 3.0|
> +---+-------+-------------+
> next, compute cumulative max,
> df = df.withColumn('AmtPaidCumSumMax',
> sf.max(sf.col('AmtPaidCumSum')).over(win_spec_max))
> df.show()
> gives error log
> Py4JJavaError: An error occurred while calling o2609.showString.
> with traceback:
> Py4JJavaErrorTraceback (most recent call last)
> <ipython-input-215-3106d06b6e49> in <module>()
> ----> 1 df.show()
> /Users/<>/spark-2.1.0-bin-hadoop2.7/python/pyspark/sql/dataframe.pyc in
> show(self, n, truncate)
> 316 """
> 317 if isinstance(truncate, bool) and truncate:
> --> 318 print(self._jdf.showString(n, 20))
> 319 else:
> 320 print(self._jdf.showString(n, int(truncate)))
>
> /Users/<>/.virtualenvs/<>/lib/python2.7/site-packages/py4j/java_gateway.pyc
> 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:
> /Users/<>/spark-2.1.0-bin-hadoop2.7/python/pyspark/sql/utils.pyc 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()
> /Users/<>/.virtualenvs/<>/lib/python2.7/site-packages/py4j/protocol.pyc
> 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(
> but interestingly enough, if i introduce another change before sencond window
> operation, say inserting a column then it does not give that error:
> df = df.withColumn('MaxBound', sf.lit(6.))
> df.show()
> +---+-------+-------------+--------+
> | x|AmtPaid|AmtPaidCumSum|MaxBound|
> +---+-------+-------------+--------+
> | 1| 2.0| 2.0| 6.0|
> | 1| 3.0| 5.0| 6.0|
> | 1| 1.0| 6.0| 6.0|
> | 1| -2.0| 4.0| 6.0|
> | 1| -1.0| 3.0| 6.0|
> +---+-------+-------------+--------+
> #then apply the second window operations
> df = df.withColumn('AmtPaidCumSumMax',
> sf.max(sf.col('AmtPaidCumSum')).over(win_spec_max))
> df.show()
> +---+-------+-------------+--------+----------------+
> | x|AmtPaid|AmtPaidCumSum|MaxBound|AmtPaidCumSumMax|
> +---+-------+-------------+--------+----------------+
> | 1| 2.0| 2.0| 6.0| 2.0|
> | 1| 3.0| 5.0| 6.0| 5.0|
> | 1| 1.0| 6.0| 6.0| 6.0|
> | 1| -2.0| 4.0| 6.0| 6.0|
> | 1| -1.0| 3.0| 6.0| 6.0|
> +---+-------+-------------+--------+----------------+
> I do not understand this behaviour
> well, so far so good, but then I try another operation then again get similar
> error:
> def _udf_compare_cumsum_sll(x):
> if x['AmtPaidCumSumMax'] >= x['MaxBound']:
> output = 0
> else:
> output = x['AmtPaid']
> udf_compare_cumsum_sll = sf.udf(_udf_compare_cumsum_sll,
> sparktypes.FloatType())
> df = df.withColumn('AmtPaidAdjusted',
> udf_compare_cumsum_sll(sf.struct([df[x] for x in df.columns])))
> df.show()
> gives,
> Py4JJavaErrorTraceback (most recent call last)
> <ipython-input-18-3106d06b6e49> in <module>()
> ----> 1 df.show()
> /Users/<>/spark-2.1.0-bin-hadoop2.7/python/pyspark/sql/dataframe.pyc in
> show(self, n, truncate)
> 316 """
> 317 if isinstance(truncate, bool) and truncate:
> --> 318 print(self._jdf.showString(n, 20))
> 319 else:
> 320 print(self._jdf.showString(n, int(truncate)))
>
> /Users/<>/.virtualenvs/<>/lib/python2.7/site-packages/py4j/java_gateway.pyc
> 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:
> /Users/<>/spark-2.1.0-bin-hadoop2.7/python/pyspark/sql/utils.pyc 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()
> /Users/<>/.virtualenvs/<>/lib/python2.7/site-packages/py4j/protocol.pyc
> 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 o91.showString.
> : org.apache.spark.SparkException: Job aborted due to stage failure: Task
> 0 in stage 36.0 failed 1 times, most recent failure: Lost task 0.0 in stage
> 36.0 (TID 645, localhost, executor driver):
> org.apache.spark.sql.catalyst.errors.package$TreeNodeException: Binding
> attribute, tree: AmtPaidCumSum#10
>
> I wonder if someone could reproduce this behaviour ...
> here is complete log ..
> Py4JJavaErrorTraceback (most recent call last)
> <ipython-input-69-3106d06b6e49> in <module>()
> ----> 1 df.show()
> /Users/<>/spark-2.1.0-bin-hadoop2.7/python/pyspark/sql/dataframe.pyc in
> show(self, n, truncate)
> 316 """
> 317 if isinstance(truncate, bool) and truncate:
> --> 318 print(self._jdf.showString(n, 20))
> 319 else:
> 320 print(self._jdf.showString(n, int(truncate)))
>
> /Users/<>/.virtualenvs/<>/lib/python2.7/site-packages/py4j/java_gateway.pyc
> in __call__(self, *args)
> 1131 answer = self.gateway_client.send_command(command)
> 1132 return_value = get_return_value(
> -> 1133 answer, self.gateway_client, self.target_id,
> self.name)
> 1134
> 1135 for temp_arg in temp_args:
> /Users/<>/spark-2.1.0-bin-hadoop2.7/python/pyspark/sql/utils.pyc in
> deco(*a, **kw)
> 61 def deco(*a, **kw):
> 62 try:
> ---> 63 return f(*a, **kw)
> 64 except py4j.protocol.Py4JJavaError as e:
> 65 s = e.java_exception.toString()
> /Users/<>/.virtualenvs/<>/lib/python2.7/site-packages/py4j/protocol.pyc
> in get_return_value(answer, gateway_client, target_id, name)
> 317 raise Py4JJavaError(
> 318 "An error occurred while calling
> {0}{1}{2}.\n".
> --> 319 format(target_id, ".", name), value)
> 320 else:
> 321 raise Py4JError(
> Py4JJavaError: An error occurred while calling o703.showString.
> : org.apache.spark.SparkException: Job aborted due to stage failure: Task
> 0 in stage 119.0 failed 1 times, most recent failure: Lost task 0.0 in stage
> 119.0 (TID 1817, localhost, executor driver):
> org.apache.spark.sql.catalyst.errors.package$TreeNodeException: Binding
> attribute, tree: AmtPaidCumSum#2076
> at
> org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:56)
> at
> org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:88)
> at
> org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:87)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:288)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:288)
> at
> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:287)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:293)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:293)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5$$anonfun$apply$11.apply(TreeNode.scala:360)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at scala.collection.immutable.List.foreach(List.scala:381)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at scala.collection.immutable.List.map(List.scala:285)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:358)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:188)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:329)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:293)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:277)
> at
> org.apache.spark.sql.catalyst.expressions.BindReferences$.bindReference(BoundAttribute.scala:87)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$$anonfun$bind$1.apply(GenerateMutableProjection.scala:38)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$$anonfun$bind$1.apply(GenerateMutableProjection.scala:38)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at scala.collection.AbstractTraversable.map(Traversable.scala:104)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.bind(GenerateMutableProjection.scala:38)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.generate(GenerateMutableProjection.scala:44)
> at
> org.apache.spark.sql.execution.SparkPlan.newMutableProjection(SparkPlan.scala:353)
> at
> org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$org$apache$spark$sql$execution$window$WindowExec$$anonfun$$processor$1$1.apply(WindowExec.scala:203)
> at
> org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$org$apache$spark$sql$execution$window$WindowExec$$anonfun$$processor$1$1.apply(WindowExec.scala:202)
> at
> org.apache.spark.sql.execution.window.AggregateProcessor$.apply(AggregateProcessor.scala:98)
> at
> org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2.org$apache$spark$sql$execution$window$WindowExec$$anonfun$$processor$1(WindowExec.scala:198)
> at
> org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$6.apply(WindowExec.scala:225)
> at
> org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$6.apply(WindowExec.scala:222)
> at
> org.apache.spark.sql.execution.window.WindowExec$$anonfun$14$$anon$1$$anonfun$16.apply(WindowExec.scala:318)
> at
> org.apache.spark.sql.execution.window.WindowExec$$anonfun$14$$anon$1$$anonfun$16.apply(WindowExec.scala:318)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
> at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:186)
> at
> org.apache.spark.sql.execution.window.WindowExec$$anonfun$14$$anon$1.<init>(WindowExec.scala:318)
> at
> org.apache.spark.sql.execution.window.WindowExec$$anonfun$14.apply(WindowExec.scala:290)
> at
> org.apache.spark.sql.execution.window.WindowExec$$anonfun$14.apply(WindowExec.scala:289)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:796)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:796)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
> at org.apache.spark.scheduler.Task.run(Task.scala:99)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: java.lang.RuntimeException: Couldn't find AmtPaidCumSum#2076
> in [sum#2299,max#2300,x#2066L,AmtPaid#2067]
> at scala.sys.package$.error(package.scala:27)
> at
> org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:94)
> at
> org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:88)
> at
> org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:52)
> ... 62 more
> 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.sql.execution.SparkPlan.executeTake(SparkPlan.scala:333)
> at
> org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38)
> 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$$anonfun$head$1.apply(Dataset.scala:2113)
> at
> org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2112)
> at org.apache.spark.sql.Dataset.withTypedCallback(Dataset.scala:2795)
> at org.apache.spark.sql.Dataset.head(Dataset.scala:2112)
> at org.apache.spark.sql.Dataset.take(Dataset.scala:2327)
> at org.apache.spark.sql.Dataset.showString(Dataset.scala:248)
> at sun.reflect.GeneratedMethodAccessor83.invoke(Unknown Source)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:498)
> at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
> at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
> at py4j.Gateway.invoke(Gateway.java:280)
> at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
> at py4j.commands.CallCommand.execute(CallCommand.java:79)
> at py4j.GatewayConnection.run(GatewayConnection.java:214)
> at java.lang.Thread.run(Thread.java:745)
> Caused by:
> org.apache.spark.sql.catalyst.errors.package$TreeNodeException: Binding
> attribute, tree: null
> at
> org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:56)
> at
> org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:88)
> at
> org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:87)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:288)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:288)
> at
> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:287)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:293)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:293)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5$$anonfun$apply$11.apply(TreeNode.scala:360)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at scala.collection.immutable.List.foreach(List.scala:381)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at scala.collection.immutable.List.map(List.scala:285)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:358)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:188)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:329)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:293)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:277)
> at
> org.apache.spark.sql.catalyst.expressions.BindReferences$.bindReference(BoundAttribute.scala:87)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$$anonfun$bind$1.apply(GenerateMutableProjection.scala:38)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$$anonfun$bind$1.apply(GenerateMutableProjection.scala:38)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at scala.collection.AbstractTraversable.map(Traversable.scala:104)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.bind(GenerateMutableProjection.scala:38)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.generate(GenerateMutableProjection.scala:44)
> at
> org.apache.spark.sql.execution.SparkPlan.newMutableProjection(SparkPlan.scala:353)
> at
> org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$org$apache$spark$sql$execution$window$WindowExec$$anonfun$$processor$1$1.apply(WindowExec.scala:203)
> at
> org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$org$apache$spark$sql$execution$window$WindowExec$$anonfun$$processor$1$1.apply(WindowExec.scala:202)
> at
> org.apache.spark.sql.execution.window.AggregateProcessor$.apply(AggregateProcessor.scala:98)
> at
> org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2.org$apache$spark$sql$execution$window$WindowExec$$anonfun$$processor$1(WindowExec.scala:198)
> at
> org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$6.apply(WindowExec.scala:225)
> at
> org.apache.spark.sql.execution.window.WindowExec$$anonfun$windowFrameExpressionFactoryPairs$2$$anonfun$6.apply(WindowExec.scala:222)
> at
> org.apache.spark.sql.execution.window.WindowExec$$anonfun$14$$anon$1$$anonfun$16.apply(WindowExec.scala:318)
> at
> org.apache.spark.sql.execution.window.WindowExec$$anonfun$14$$anon$1$$anonfun$16.apply(WindowExec.scala:318)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
> at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:186)
> at
> org.apache.spark.sql.execution.window.WindowExec$$anonfun$14$$anon$1.<init>(WindowExec.scala:318)
> at
> org.apache.spark.sql.execution.window.WindowExec$$anonfun$14.apply(WindowExec.scala:290)
> at
> org.apache.spark.sql.execution.window.WindowExec$$anonfun$14.apply(WindowExec.scala:289)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:796)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:796)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
> at org.apache.spark.scheduler.Task.run(Task.scala:99)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> ... 1 more
> Caused by: java.lang.RuntimeException: Couldn't find AmtPaidCumSum#2076
> in [sum#2299,max#2300,x#2066L,AmtPaid#2067]
> at scala.sys.package$.error(package.scala:27)
> at
> org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:94)
> at
> org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:88)
> at
> org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:52)
> ... 62 more
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
