spark-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Weizhong (JIRA)" <j...@apache.org>
Subject [jira] [Updated] (SPARK-8071) Run PySpark dataframe.rollup/cube test failed
Date Thu, 04 Jun 2015 05:48:37 GMT

     [ https://issues.apache.org/jira/browse/SPARK-8071?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Weizhong updated SPARK-8071:
----------------------------
    Description: 
I run test for Spark, and failed on PySpark, details are:

File "/xxx/Spark/python/pyspark/sql/dataframe.py", line 837, in pyspark.sql.dataframe.DataFrame.cube

Failed example:
* df.cube('name', df.age).count().show()

Exception raised:
* Traceback (most recent call last):
** File "/usr/lib64/python2.6/doctest.py", line 1253, in __run
*** compileflags, 1) in test.globs
** File "<doctest pyspark.sql.dataframe.DataFrame.cube\[0]>", line 1, in <module>
*** df.cube('name', df.age).count().show()
** File "/xxx/Spark/python/pyspark/sql/dataframe.py", line 291, in show
*** print(self._jdf.showString\(n))
** File "/xxx/Spark/python/lib/py4j-0.8.2.1-src.zip/py4j/java_gateway.py", line 538, in \_\_call\_\_
*** self.target_id, self.name)
** File "/xxx/Spark/python/lib/py4j-0.8.2.1-src.zip/py4j/protocol.py", line 300, in get_return_value
*** format(target_id, '.', name), value)
* Py4JJavaError: An error occurred while calling o212.showString.
* : java.lang.AssertionError: assertion failed: No plan for Cube [name#1,age#0], [name#1,age#0,COUNT(1)
AS count#27L], grouping__id#28
** LogicalRDD [age#0,name#1], MapPartitionsRDD\[7] at applySchemaToPythonRDD at NativeMethodAccessorImpl.java:-2

*** at scala.Predef$.assert(Predef.scala:179)
*** at org.apache.spark.sql.catalyst.planning.QueryPlanner.plan(QueryPlanner.scala:59)
*** at org.apache.spark.sql.catalyst.planning.QueryPlanner.planLater(QueryPlanner.scala:54)
*** at org.apache.spark.sql.execution.SparkStrategies$BasicOperators$.apply(SparkStrategies.scala:312)
*** at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$1.apply(QueryPlanner.scala:58)
*** at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$1.apply(QueryPlanner.scala:58)
*** at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
*** at org.apache.spark.sql.catalyst.planning.QueryPlanner.plan(QueryPlanner.scala:59)
*** at org.apache.spark.sql.SQLContext$QueryExecution.sparkPlan$lzycompute(SQLContext.scala:913)
*** at org.apache.spark.sql.SQLContext$QueryExecution.sparkPlan(SQLContext.scala:911)
*** at org.apache.spark.sql.SQLContext$QueryExecution.executedPlan$lzycompute(SQLContext.scala:917)
*** at org.apache.spark.sql.SQLContext$QueryExecution.executedPlan(SQLContext.scala:917)
*** at org.apache.spark.sql.DataFrame.collect(DataFrame.scala:1255)
*** at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1189)
*** at org.apache.spark.sql.DataFrame.take(DataFrame.scala:1248)
*** at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:176)
*** at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
*** at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
*** at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
*** at java.lang.reflect.Method.invoke(Method.java:606)
*** at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
*** at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:379)
*** 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:207)
*** at java.lang.Thread.run(Thread.java:745)

**********************************************************************
   1 of   1 in pyspark.sql.dataframe.DataFrame.cube
   1 of   1 in pyspark.sql.dataframe.DataFrame.rollup
***Test Failed*** 2 failures.

cc [~davies]

  was:
I run test for Spark, and failed on PySpark, details are:

File "/xxx/Spark/python/pyspark/sql/dataframe.py", line 837, in pyspark.sql.dataframe.DataFrame.cube

Failed example:
* df.cube('name', df.age).count().show()

Exception raised:
* Traceback (most recent call last):
** File "/usr/lib64/python2.6/doctest.py", line 1253, in __run
*** compileflags, 1) in test.globs
** File "<doctest pyspark.sql.dataframe.DataFrame.cube\[0]>", line 1, in <module>
*** df.cube('name', df.age).count().show()
** File "/xxx/Spark/python/pyspark/sql/dataframe.py", line 291, in show
*** print(self._jdf.showString\(n))
** File "/xxx/Spark/python/lib/py4j-0.8.2.1-src.zip/py4j/java_gateway.py", line 538, in \_\_call\_\_
*** self.target_id, self.name)
** File "/xxx/Spark/python/lib/py4j-0.8.2.1-src.zip/py4j/protocol.py", line 300, in get_return_value
*** format(target_id, '.', name), value)
* Py4JJavaError: An error occurred while calling o212.showString.
* : java.lang.AssertionError: assertion failed: No plan for Cube [name#1,age#0], [name#1,age#0,COUNT(1)
AS count#27L], grouping__id#28
** LogicalRDD [age#0,name#1], MapPartitionsRDD\[7] at applySchemaToPythonRDD at NativeMethodAccessorImpl.java:-2

*** at scala.Predef$.assert(Predef.scala:179)
*** at org.apache.spark.sql.catalyst.planning.QueryPlanner.plan(QueryPlanner.scala:59)
*** at org.apache.spark.sql.catalyst.planning.QueryPlanner.planLater(QueryPlanner.scala:54)
*** at org.apache.spark.sql.execution.SparkStrategies$BasicOperators$.apply(SparkStrategies.scala:312)
*** at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$1.apply(QueryPlanner.scala:58)
*** at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$1.apply(QueryPlanner.scala:58)
*** at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
*** at org.apache.spark.sql.catalyst.planning.QueryPlanner.plan(QueryPlanner.scala:59)
*** at org.apache.spark.sql.SQLContext$QueryExecution.sparkPlan$lzycompute(SQLContext.scala:913)
*** at org.apache.spark.sql.SQLContext$QueryExecution.sparkPlan(SQLContext.scala:911)
*** at org.apache.spark.sql.SQLContext$QueryExecution.executedPlan$lzycompute(SQLContext.scala:917)
*** at org.apache.spark.sql.SQLContext$QueryExecution.executedPlan(SQLContext.scala:917)
*** at org.apache.spark.sql.DataFrame.collect(DataFrame.scala:1255)
*** at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1189)
*** at org.apache.spark.sql.DataFrame.take(DataFrame.scala:1248)
*** at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:176)
*** at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
*** at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
*** at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
*** at java.lang.reflect.Method.invoke(Method.java:606)
*** at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
*** at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:379)
*** 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:207)
*** at java.lang.Thread.run(Thread.java:745)

**********************************************************************
   1 of   1 in pyspark.sql.dataframe.DataFrame.cube
   1 of   1 in pyspark.sql.dataframe.DataFrame.rollup
***Test Failed*** 2 failures.


> Run PySpark dataframe.rollup/cube test failed
> ---------------------------------------------
>
>                 Key: SPARK-8071
>                 URL: https://issues.apache.org/jira/browse/SPARK-8071
>             Project: Spark
>          Issue Type: Bug
>          Components: PySpark
>         Environment: OS: SUSE 11 SP3; JDK: 1.8.0_40; Python: 2.6.8; Hadoop: 2.7.0; Spark:
master branch
>            Reporter: Weizhong
>            Priority: Minor
>
> I run test for Spark, and failed on PySpark, details are:
> File "/xxx/Spark/python/pyspark/sql/dataframe.py", line 837, in pyspark.sql.dataframe.DataFrame.cube
> Failed example:
> * df.cube('name', df.age).count().show()
> Exception raised:
> * Traceback (most recent call last):
> ** File "/usr/lib64/python2.6/doctest.py", line 1253, in __run
> *** compileflags, 1) in test.globs
> ** File "<doctest pyspark.sql.dataframe.DataFrame.cube\[0]>", line 1, in <module>
> *** df.cube('name', df.age).count().show()
> ** File "/xxx/Spark/python/pyspark/sql/dataframe.py", line 291, in show
> *** print(self._jdf.showString\(n))
> ** File "/xxx/Spark/python/lib/py4j-0.8.2.1-src.zip/py4j/java_gateway.py", line 538,
in \_\_call\_\_
> *** self.target_id, self.name)
> ** File "/xxx/Spark/python/lib/py4j-0.8.2.1-src.zip/py4j/protocol.py", line 300, in get_return_value
> *** format(target_id, '.', name), value)
> * Py4JJavaError: An error occurred while calling o212.showString.
> * : java.lang.AssertionError: assertion failed: No plan for Cube [name#1,age#0], [name#1,age#0,COUNT(1)
AS count#27L], grouping__id#28
> ** LogicalRDD [age#0,name#1], MapPartitionsRDD\[7] at applySchemaToPythonRDD at NativeMethodAccessorImpl.java:-2
> *** at scala.Predef$.assert(Predef.scala:179)
> *** at org.apache.spark.sql.catalyst.planning.QueryPlanner.plan(QueryPlanner.scala:59)
> *** at org.apache.spark.sql.catalyst.planning.QueryPlanner.planLater(QueryPlanner.scala:54)
> *** at org.apache.spark.sql.execution.SparkStrategies$BasicOperators$.apply(SparkStrategies.scala:312)
> *** at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$1.apply(QueryPlanner.scala:58)
> *** at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$1.apply(QueryPlanner.scala:58)
> *** at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
> *** at org.apache.spark.sql.catalyst.planning.QueryPlanner.plan(QueryPlanner.scala:59)
> *** at org.apache.spark.sql.SQLContext$QueryExecution.sparkPlan$lzycompute(SQLContext.scala:913)
> *** at org.apache.spark.sql.SQLContext$QueryExecution.sparkPlan(SQLContext.scala:911)
> *** at org.apache.spark.sql.SQLContext$QueryExecution.executedPlan$lzycompute(SQLContext.scala:917)
> *** at org.apache.spark.sql.SQLContext$QueryExecution.executedPlan(SQLContext.scala:917)
> *** at org.apache.spark.sql.DataFrame.collect(DataFrame.scala:1255)
> *** at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1189)
> *** at org.apache.spark.sql.DataFrame.take(DataFrame.scala:1248)
> *** at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:176)
> *** at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> *** at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> *** at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> *** at java.lang.reflect.Method.invoke(Method.java:606)
> *** at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
> *** at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:379)
> *** 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:207)
> *** at java.lang.Thread.run(Thread.java:745)
> **********************************************************************
>    1 of   1 in pyspark.sql.dataframe.DataFrame.cube
>    1 of   1 in pyspark.sql.dataframe.DataFrame.rollup
> ***Test Failed*** 2 failures.
> cc [~davies]



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org


Mime
View raw message