我有一个包含以下架构的数据框：
last_year_df.printSchema()
root
|-- invNum: string (nullable = true)
|-- custNum: string (nullable = true)
|-- entprsNum: string (nullable = true)
|-- billTp: string (nullable = true)
|-- invAmtUSD: string (nullable = true)
|-- invRevenueTp: string (nullable = true)
|-- entryDt: string (nullable = true)
|-- dueDt: string (nullable = true)
|-- settledDt: string (nullable = true)
|-- days_to_settle: integer (nullable = true)
我可以在字段上执行show（）并在days_上描述（）以解决问题。 我想通过以下功能调整天数。
def days_adjust(days):
if days < 0:
ret_days = 0
elif days > 120:
ret_days = 120
else:
ret_days = days
return ret_days
adjust_udf = udf(days_adjust, IntegerType())
last_year_df = last_year_df.withColumn("days_to_settle_adjusted",adjust_udf(last_year_df['days_to_settle']))
#last_year_df = last_year_df.withColumn("days_to_settle_adjusted", last_year_df['days_to_settle'] + 100)
last_year_df.select("settledDt").show()
在带有udf的withColumn之后，我在数据帧上尝试的任何操作都会出错。如果我在没有udf的情况下使用colmented withColumn，那么数据帧就可以了。这是错误：
Py4JJavaError Traceback (most recent call last)
<ipython-input-23-900db0b86899> in <module>()
15 #last_year_df = last_year_df.withColumn("days_to_settle_adjusted", last_year_df['days_to_settle'] + 100)
16
--> 17 last_year_df.select("settledDt").show()
18 last_year_df.select("dueDt").show()
19 last_year_df.select("days_to_settle").show()
/usr/local/src/spark/spark-1.6.1-bin-hadoop2.6/python/pyspark /sql/dataframe.pyc in show(self, n, truncate)
255 +---+-----+
256 """
--> 257 print(self._jdf.showString(n, truncate))
258
259 def __repr__(self):
/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 o317.showString.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 54.0 failed 1 times, most recent failure: Lost task 0.0 in stage 54.0 (TID 806, localhost): java.lang.ArrayIndexOutOfBoundsException
at org.apache.spark.sql.catalyst.CatalystTypeConverters$StructConverter.toCatalystImpl(CatalystTypeConverters.scala:260)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$StructConverter.toCatalystImpl(CatalystTypeConverters.scala:250)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$CatalystTypeConverter.toCatalyst(CatalystTypeConverters.scala:102)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$$anonfun$createToCatalystConverter$2.apply(CatalystTypeConverters.scala:401)
at org.apache.spark.sql.execution.RDDConversions$$anonfun$rowToRowRdd$1$$anonfun$apply$2.apply(ExistingRDD.scala:59)
at org.apache.spark.sql.execution.RDDConversions$$anonfun$rowToRowRdd$1$$anonfun$apply$2.apply(ExistingRDD.scala:56)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$14.hasNext(Iterator.scala:389)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at scala.collection.Iterator$GroupedIterator.fill(Iterator.scala:966)
at scala.collection.Iterator$GroupedIterator.hasNext(Iterator.scala:972)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:452)
at org.apache.spark.api.python.PythonRunner$WriterThread$$anonfun$run$3.apply(PythonRDD.scala:280)
at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1765)
at org.apache.spark.api.python.PythonRunner$WriterThread.run(PythonRDD.scala:239)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at java.lang.Thread.getStackTrace(Thread.java:1117)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1858)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:212)
at org.apache.spark.sql.execution.Limit.executeCollect(basicOperators.scala:165)
at org.apache.spark.sql.execution.SparkPlan.executeCollectPublic(SparkPlan.scala:174)
at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1499)
at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1499)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
at org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:2086)
at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$execute$1(DataFrame.scala:1498)
at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$collect(DataFrame.scala:1505)
at org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1375)
at org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1374)
at org.apache.spark.sql.DataFrame.withCallback(DataFrame.scala:2099)
at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1374)
at org.apache.spark.sql.DataFrame.take(DataFrame.scala:1456)
at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:170)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:95)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:55)
at java.lang.reflect.Method.invoke(Method.java:507)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381)
at py4j.Gateway.invoke(Gateway.java:259)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:209)
at java.lang.Thread.run(Thread.java:785)
Caused by: java.lang.ArrayIndexOutOfBoundsException
at org.apache.spark.sql.catalyst.CatalystTypeConverters$StructConverter.toCatalystImpl(CatalystTypeConverters.scala:260)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$StructConverter.toCatalystImpl(CatalystTypeConverters.scala:250)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$CatalystTypeConverter.toCatalyst(CatalystTypeConverters.scala:102)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$$anonfun$createToCatalystConverter$2.apply(CatalystTypeConverters.scala:401)
at org.apache.spark.sql.execution.RDDConversions$$anonfun$rowToRowRdd$1$$anonfun$apply$2.apply(ExistingRDD.scala:59)
at org.apache.spark.sql.execution.RDDConversions$$anonfun$rowToRowRdd$1$$anonfun$apply$2.apply(ExistingRDD.scala:56)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$14.hasNext(Iterator.scala:389)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at scala.collection.Iterator$GroupedIterator.fill(Iterator.scala:966)
at scala.collection.Iterator$GroupedIterator.hasNext(Iterator.scala:972)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:452)
at org.apache.spark.api.python.PythonRunner$WriterThread$$anonfun$run$3.apply(PythonRDD.scala:280)
at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1765)
at org.apache.spark.api.python.PythonRunner$WriterThread.run(PythonRDD.scala:239)
为什么带有udf的withColumn会破坏日期帧？