dispute_df.join(comments_df, $"dispute_df.COMMENTID" ===
$"comments_df.COMMENTID").first()
If you are using DataFrame API, and some of them are trick for first time user,
my suggestion is to always referring the unit tests. That is in fact the way I
tried to find out how to do it for lots of cases.
https://github.com/apache/spark/blob/master/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala
Yong
> Subject: Re: Java exception when showing join
> From: webe...@aim.com
> To: java8...@hotmail.com; user@spark.apache.org
> Date: Mon, 25 Apr 2016 07:45:12 -0500
>
> I get an invalid syntax error when I do that.
>
> On Fri, 2016-04-22 at 20:06 -0400, Yong Zhang wrote:
> > use "dispute_df.join(comments_df, dispute_df.COMMENTID ===
> > comments_df.COMMENTID).first()" instead.
> >
> > Yong
> >
> > Date: Fri, 22 Apr 2016 17:42:26 -0400
> > From: webe...@aim.com
> > To: user@spark.apache.org
> > Subject: Java exception when showing join
> >
> > I am using pyspark with netezza. I am getting a java exception when
> > trying to show the first row of a join. I can show the first row for
> > of the two dataframes separately but not the result of a join. I get
> > the same error for any action I take(first, collect, show). Am I
> > doing something wrong?
> >
> > from pyspark.sql import SQLContext
> > sqlContext = SQLContext(sc)
> > dispute_df =
> > sqlContext.read.format('com.ibm.spark.netezza').options(url='jdbc:net
> > ezza://***:5480/db', user='***', password='***', dbtable='table1',
> > driver='com.ibm.spark.netezza').load()
> > dispute_df.printSchema()
> > comments_df =
> > sqlContext.read.format('com.ibm.spark.netezza').options(url='jdbc:net
> > ezza://***:5480/db', user='***', password='***', dbtable='table2',
> > driver='com.ibm.spark.netezza').load()
> > comments_df.printSchema()
> > dispute_df.join(comments_df, dispute_df.COMMENTID ==
> > comments_df.COMMENTID).first()
> >
> >
> > root
> > |-- COMMENTID: string (nullable = true)
> > |-- EXPORTDATETIME: timestamp (nullable = true)
> > |-- ARTAGS: string (nullable = true)
> > |-- POTAGS: string (nullable = true)
> > |-- INVTAG: string (nullable = true)
> > |-- ACTIONTAG: string (nullable = true)
> > |-- DISPUTEFLAG: string (nullable = true)
> > |-- ACTIONFLAG: string (nullable = true)
> > |-- CUSTOMFLAG1: string (nullable = true)
> > |-- CUSTOMFLAG2: string (nullable = true)
> >
> > root
> > |-- COUNTRY: string (nullable = true)
> > |-- CUSTOMER: string (nullable = true)
> > |-- INVNUMBER: string (nullable = true)
> > |-- INVSEQNUMBER: string (nullable = true)
> > |-- LEDGERCODE: string (nullable = true)
> > |-- COMMENTTEXT: string (nullable = true)
> > |-- COMMENTTIMESTAMP: timestamp (nullable = true)
> > |-- COMMENTLENGTH: long (nullable = true)
> > |-- FREEINDEX: long (nullable = true)
> > |-- COMPLETEDFLAG: long (nullable = true)
> > |-- ACTIONFLAG: long (nullable = true)
> > |-- FREETEXT: string (nullable = true)
> > |-- USERNAME: string (nullable = true)
> > |-- ACTION: string (nullable = true)
> > |-- COMMENTID: string (nullable = true)
> >
> > -------------------------------------------------------------------
> > --------
> > Py4JJavaError Traceback (most recent call
> > last)
> > <ipython-input-19-0cb9eb943052> in <module>()
> > 5 comments_df =
> > sqlContext.read.format('com.ibm.spark.netezza').options(url='jdbc:net
> > ezza://dstbld-pda02.bld.dst.ibm.com:5480/BACC_DEV_CSP_NBAAR',
> > user='rnahar', password='Sfeb2016',
> > dbtable='UK_METRICS.EU_COMMENTS2',
> > driver='com.ibm.spark.netezza').load()
> > 6 comments_df.printSchema()
> > ----> 7 dispute_df.join(comments_df, dispute_df.COMMENTID ==
> > comments_df.COMMENTID).first()
> >
> > /usr/local/src/spark/spark-1.6.1-bin-
> > hadoop2.6/python/pyspark/sql/dataframe.pyc in first(self)
> > 802 Row(age=2, name=u'Alice')
> > 803 """
> > --> 804 return self.head()
> > 805
> > 806 @ignore_unicode_prefix
> >
> > /usr/local/src/spark/spark-1.6.1-bin-
> > hadoop2.6/python/pyspark/sql/dataframe.pyc in head(self, n)
> > 790 """
> > 791 if n is None:
> > --> 792 rs = self.head(1)
> > 793 return rs[0] if rs else None
> > 794 return self.take(n)
> >
> > /usr/local/src/spark/spark-1.6.1-bin-
> > hadoop2.6/python/pyspark/sql/dataframe.pyc in head(self, n)
> > 792 rs = self.head(1)
> > 793 return rs[0] if rs else None
> > --> 794 return self.take(n)
> > 795
> > 796 @ignore_unicode_prefix
> >
> > /usr/local/src/spark/spark-1.6.1-bin-
> > hadoop2.6/python/pyspark/sql/dataframe.pyc in take(self, num)
> > 304 with SCCallSiteSync(self._sc) as css:
> > 305 port =
> > self._sc._jvm.org.apache.spark.sql.execution.EvaluatePython.takeAndSe
> > rve(
> > --> 306 self._jdf, num)
> > 307 return list(_load_from_socket(port,
> > BatchedSerializer(PickleSerializer())))
> > 308
> >
> > /usr/local/src/spark/spark-1.6.1-bin-hadoop2.6/python/lib/py4j-0.9-
> > src.zip/py4j/java_gateway.py in __call__(self, *args)
> > 811 answer = self.gateway_client.send_command(command)
> > 812 return_value = get_return_value(
> > --> 813 answer, self.gateway_client, self.target_id,
> > self.name)
> > 814
> > 815 for temp_arg in temp_args:
> >
> > /usr/local/src/spark/spark-1.6.1-bin-
> > hadoop2.6/python/pyspark/sql/utils.pyc in deco(*a, **kw)
> > 43 def deco(*a, **kw):
> > 44 try:
> > ---> 45 return f(*a, **kw)
> > 46 except py4j.protocol.Py4JJavaError as e:
> > 47 s = e.java_exception.toString()
> >
> > /usr/local/src/spark/spark-1.6.1-bin-hadoop2.6/python/lib/py4j-0.9-
> > src.zip/py4j/protocol.py in get_return_value(answer, gateway_client,
> > target_id, name)
> > 306 raise Py4JJavaError(
> > 307 "An error occurred while calling
> > {0}{1}{2}.\n".
> > --> 308 format(target_id, ".", name), value)
> > 309 else:
> > 310 raise Py4JError(
> >
> > Py4JJavaError: An error occurred while calling
> > z:org.apache.spark.sql.execution.EvaluatePython.takeAndServe.
> > : org.apache.spark.SparkException: Job aborted due to stage failure:
> > Task 2 in stage 59.0 failed 1 times, most recent failure: Lost task
> > 2.0 in stage 59.0 (TID 1406, localhost): java.io.IOException: EOF
> > whilst processing escape sequence
> > at org.apache.commons.csv.Lexer.readEscape(Lexer.java:346)
> > at org.apache.commons.csv.Lexer.parseSimpleToken(Lexer.java:200)
> > at org.apache.commons.csv.Lexer.nextToken(Lexer.java:161)
> > at
> > org.apache.commons.csv.CSVParser.nextRecord(CSVParser.java:498)
> > at
> > org.apache.commons.csv.CSVParser.getRecords(CSVParser.java:365)
> > at
> > com.ibm.spark.netezza.NetezzaRecordParser.parse(NetezzaRecordParser.s
> > cala:43)
> > at
> > com.ibm.spark.netezza.NetezzaDataReader.next(NetezzaDataReader.scala:
> > 136)
> > at
> > com.ibm.spark.netezza.NetezzaRDD$$anon$1.getNext(NetezzaRDD.scala:77)
> > at
> > com.ibm.spark.netezza.NetezzaRDD$$anon$1.hasNext(NetezzaRDD.scala:106
> > )
> > at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> > at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> > at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> > at
> > org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(Bypa
> > ssMergeSortShuffleWriter.java:126)
> > at
> > org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scal
> > a:73)
> > at
> > org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scal
> > a:41)
> > at org.apache.spark.scheduler.Task.run(Task.scala:89)
> > at
> > org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
> > at
> > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.
> > java:1143)
> > at
> > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor
> > .java:618)
> > at java.lang.Thread.run(Thread.java:785)
> >
> > Driver stacktrace:
> > at
> > org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DA
> > GScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431)
> > at
> > org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(D
> > AGScheduler.scala:1419)
> > at
> > org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(D
> > AGScheduler.scala:1418)
> > at
> > scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.
> > scala:59)
> > at
> > scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
> > at
> > org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala
> > :1418)
> > at
> > org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$
> > 1.apply(DAGScheduler.scala:799)
> > at
> > org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$
> > 1.apply(DAGScheduler.scala:799)
> > at scala.Option.foreach(Option.scala:236)
> > at
> > org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGSchedu
> > ler.scala:799)
> > at
> > org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(D
> > AGScheduler.scala:1640)
> > at
> > org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAG
> > Scheduler.scala:1599)
> > at
> > org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAG
> > Scheduler.scala:1588)
> > at
> > org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
> > at java.lang.Thread.getStackTrace(Thread.java:1117)
> > at
> > org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620
> > )
> > at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
> > at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845)
> > at org.apache.spark.SparkContext.runJob(SparkContext.scala:1858)
> > at
> > org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:
> > 212)
> > at
> > org.apache.spark.sql.execution.EvaluatePython$$anonfun$takeAndServe$1
> > .apply$mcI$sp(python.scala:126)
> > at
> > org.apache.spark.sql.execution.EvaluatePython$$anonfun$takeAndServe$1
> > .apply(python.scala:124)
> > at
> > org.apache.spark.sql.execution.EvaluatePython$$anonfun$takeAndServe$1
> > .apply(python.scala:124)
> > at
> > org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLEx
> > ecution.scala:56)
> > at
> > org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:208
> > 6)
> > at
> > org.apache.spark.sql.execution.EvaluatePython$.takeAndServe(python.sc
> > ala:124)
> > at
> > org.apache.spark.sql.execution.EvaluatePython.takeAndServe(python.sca
> > la)
> > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> > at
> > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.
> > java:95)
> > at
> > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAcces
> > sorImpl.java:55)
> > at java.lang.reflect.Method.invoke(Method.java:507)
> > at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
> > at
> > py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381)
> > at py4j.Gateway.invoke(Gateway.java:259)
> > at
> > py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
> > at py4j.commands.CallCommand.execute(CallCommand.java:79)
> > at py4j.GatewayConnection.run(GatewayConnection.java:209)
> > at java.lang.Thread.run(Thread.java:785)
> > Caused by: java.io.IOException: EOF whilst processing escape sequence
> > at org.apache.commons.csv.Lexer.readEscape(Lexer.java:346)
> > at org.apache.commons.csv.Lexer.parseSimpleToken(Lexer.java:200)
> > at org.apache.commons.csv.Lexer.nextToken(Lexer.java:161)
> > at
> > org.apache.commons.csv.CSVParser.nextRecord(CSVParser.java:498)
> > at
> > org.apache.commons.csv.CSVParser.getRecords(CSVParser.java:365)
> > at
> > com.ibm.spark.netezza.NetezzaRecordParser.parse(NetezzaRecordParser.s
> > cala:43)
> > at
> > com.ibm.spark.netezza.NetezzaDataReader.next(NetezzaDataReader.scala:
> > 136)
> > at
> > com.ibm.spark.netezza.NetezzaRDD$$anon$1.getNext(NetezzaRDD.scala:77)
> > at
> > com.ibm.spark.netezza.NetezzaRDD$$anon$1.hasNext(NetezzaRDD.scala:106
> > )
> > at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> > at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> > at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> > at
> > org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(Bypa
> > ssMergeSortShuffleWriter.java:126)
> > at
> > org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scal
> > a:73)
> > at
> > org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scal
> > a:41)
> > at org.apache.spark.scheduler.Task.run(Task.scala:89)
> > at
> > org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
> > at
> > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.
> > java:1143)
> > at
> > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor
> > .java:618)
> > ... 1 more
> >
> >
> > In [ ]:
> >
> >
>
