How to check in Python if cell value of pyspark dataframe column in UDF function is none or NaN for implementing forward fill?

2
votes

I am basically trying to do a forward fill imputation. Below is the code for that.

df = spark.createDataFrame([(1,1, None), (1,2, 5), (1,3, None), (1,4, None), (1,5, 10), (1,6, None)], ('session',"timestamp", "id"))

PRV_RANK = 0.0
def fun(rank):
    ########How to check if None or Nan?  ###############
    if rank is None or rank is NaN:
        return PRV_RANK
    else:
        PRV_RANK = rank
        return rank        

fuN= F.udf(fun, IntegerType())

df.withColumn("ffill_new", fuN(df["id"])).show()

I am getting weird error in the log.

Edit: The question is related to how to identify null & nan in spark dataframe using python.

Edit: I am assuming the below line of code which checks for NaN & Null is causing the issue. So I have given the title accordingly for this question.

Traceback (most recent call last):

File "", line 1, in df_na.withColumn("ffill_new", forwardFill(df_na["id"])).show()

File "C:\Spark\python\pyspark\sql\dataframe.py", line 318, in show print(self._jdf.showString(n, 20))

File "C:\Spark\python\lib\py4j-0.10.4-src.zip\py4j\java_gateway.py", line 1133, in call answer, self.gateway_client, self.target_id, self.name)

File "C:\Spark\python\pyspark\sql\utils.py", line 63, in deco return f(*a, **kw)

File "C:\Spark\python\lib\py4j-0.10.4-src.zip\py4j\protocol.py", line 319, in get_return_value format(target_id, ".", name), value)

Py4JJavaError: An error occurred while calling o806.showString. : org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 47.0 failed 1 times, most recent failure: Lost task 0.0 in stage 47.0 (TID 83, localhost, executor driver): org.apache.spark.api.python.PythonException: Traceback (most recent call last): File "C:\Spark\python\lib\pyspark.zip\pyspark\worker.py", line 174, in main File "C:\Spark\python\lib\pyspark.zip\pyspark\worker.py", line 169, in process File "C:\Spark\python\lib\pyspark.zip\pyspark\worker.py", line 106, in File "C:\Spark\python\lib\pyspark.zip\pyspark\worker.py", line 92, in File "C:\Spark\python\lib\pyspark.zip\pyspark\worker.py", line 70, in File "", line 5, in forwardfil UnboundLocalError: local variable 'PRV_RANK' referenced before assignment

at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:193) at org.apache.spark.api.python.PythonRunner$$anon$1.(PythonRDD.scala:234) at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:152) at org.apache.spark.sql.execution.python.BatchEvalPythonExec$$anonfun$doExecute$1.apply(BatchEvalPythonExec.scala:144) at org.apache.spark.sql.execution.python.BatchEvalPythonExec$$anonfun$doExecute$1.apply(BatchEvalPythonExec.scala:87) at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:797) at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:797) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87) at org.apache.spark.scheduler.Task.run(Task.scala:99) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:322) 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:748)

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:1925) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1938) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1951) 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$1.apply(Dataset.scala:2386) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57) at org.apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2788) at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$execute$1(Dataset.scala:2385) at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collect(Dataset.scala:2392) at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2128) at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2127) at org.apache.spark.sql.Dataset.withTypedCallback(Dataset.scala:2818) at org.apache.spark.sql.Dataset.head(Dataset.scala:2127) at org.apache.spark.sql.Dataset.take(Dataset.scala:2342) at org.apache.spark.sql.Dataset.showString(Dataset.scala:248) at sun.reflect.GeneratedMethodAccessor35.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:748) Caused by: org.apache.spark.api.python.PythonException: Traceback (most recent call last): File "C:\Spark\python\lib\pyspark.zip\pyspark\worker.py", line 174, in main File "C:\Spark\python\lib\pyspark.zip\pyspark\worker.py", line 169, in process File "C:\Spark\python\lib\pyspark.zip\pyspark\worker.py", line 106, in File "C:\Spark\python\lib\pyspark.zip\pyspark\worker.py", line 92, in File "C:\Spark\python\lib\pyspark.zip\pyspark\worker.py", line 70, in File "", line 5, in forwardfil UnboundLocalError: local variable 'PRV_RANK' referenced before assignment

at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:193) at org.apache.spark.api.python.PythonRunner$$anon$1.(PythonRDD.scala:234) at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:152) at org.apache.spark.sql.execution.python.BatchEvalPythonExec$$anonfun$doExecute$1.apply(BatchEvalPythonExec.scala:144) at org.apache.spark.sql.execution.python.BatchEvalPythonExec$$anonfun$doExecute$1.apply(BatchEvalPythonExec.scala:87) at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:797) at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:797) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87) at org.apache.spark.scheduler.Task.run(Task.scala:99) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:322) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) 1 more

1
pythonapache-sparkpysparkspark-dataframepyspark-sql
Is that the end of the stack trace? – khelwood
Possible duplicate of How to check for NaN in python? – khelwood
your fuN spelling is wrong – Ramesh Maharjan
your question is still misleading. review it please – eliasah

1 Answers

0
votes
df.withColumn("ffill_new", f.UserDefinedFunction(lambda x: x or 0, IntegerType())(df["id"])).show()