Python 3.x PySpark-检查某些列中是否有NaN时出错

尝试检查我是否在某些列中使用NaN值

ddf_temp = ddf.select('col1', 'col2' ...) # all int type
ddf_temp.select([count(when(isnull(c), c)).alias(c) for c in ddf_temp.columns]).show()

我可以找出哪些列给了我这些错误，但我无法找出为什么我会得到这些：

---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
<ipython-input-47-76c75cf06695> in <module>()
      3 # ddf_temp = ddf10.select('state_bottle_cost')
      4 ddf_temp = ddf10.where(col('state_bottle_retail').isNull())
----> 5 ddf_temp.show()
      6 # ddf_temp = ddf10.select('store_number', 'zip_code', 'county_number', 'category', 'vendor_number', 'pack', 'bottles_sold')
      7 # ddf_temp.select([count(when(isnull(c), c)).alias(c) for c in ddf_temp.columns]).show()

3 frames
/content/spark-2.4.3-bin-hadoop2.7/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
    326                 raise Py4JJavaError(
    327                     "An error occurred while calling {0}{1}{2}.\n".
--> 328                     format(target_id, ".", name), value)
    329             else:
    330                 raise Py4JError(

Py4JJavaError: An error occurred while calling o2010.showString.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 43.0 failed 1 times, most recent failure: Lost task 0.0 in stage 43.0 (TID 233, localhost, executor driver): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
  File "/content/spark-2.4.3-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/worker.py", line 377, in main
    process()
  File "/content/spark-2.4.3-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/worker.py", line 372, in process
    serializer.dump_stream(func(split_index, iterator), outfile)
  File "/content/spark-2.4.3-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/serializers.py", line 345, in dump_stream
    self.serializer.dump_stream(self._batched(iterator), stream)
  File "/content/spark-2.4.3-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/serializers.py", line 141, in dump_stream
    for obj in iterator:
  File "/content/spark-2.4.3-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/serializers.py", line 334, in _batched
    for item in iterator:
  File "<string>", line 1, in <lambda>
  File "/content/spark-2.4.3-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/worker.py", line 85, in <lambda>
    return lambda *a: f(*a)
  File "/content/spark-2.4.3-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/util.py", line 99, in wrapper
    return f(*args, **kwargs)
  File "<ipython-input-11-9ec9e286520d>", line 3, in <lambda>
TypeError: 'NoneType' object is not subscriptable

    at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.handlePythonException(PythonRunner.scala:452)
    at org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$1.read(PythonUDFRunner.scala:81)
    at org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$1.read(PythonUDFRunner.scala:64)
    at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:406)
    at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
    at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
    at scala.collection.Iterator$GroupedIterator.fill(Iterator.scala:1124)
    at scala.collection.Iterator$GroupedIterator.hasNext(Iterator.scala:1130)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
    at scala.collection.Iterator$class.foreach(Iterator.scala:891)
    at scala.collection.AbstractIterator.foreach(Iterator.scala:1334)
    at org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:224)
    at org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$2.writeIteratorToStream(PythonUDFRunner.scala:50)
    at org.apache.spark.api.python.BasePythonRunner$WriterThread$$anonfun$run$1.apply(PythonRunner.scala:345)
    at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1945)
    at org.apache.spark.api.python.BasePythonRunner$WriterThread.run(PythonRunner.scala:194)

Driver stacktrace:
    at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1889)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1877)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1876)
    at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
    at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
    at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1876)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
    at scala.Option.foreach(Option.scala:257)
    at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:926)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2110)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2059)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2048)
    at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
    at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:737)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2061)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2082)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2101)
    at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:365)
    at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38)
    at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collectFromPlan(Dataset.scala:3383)
    at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2544)
    at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2544)
    at org.apache.spark.sql.Dataset$$anonfun$53.apply(Dataset.scala:3364)
    at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78)
    at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
    at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
    at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3363)
    at org.apache.spark.sql.Dataset.head(Dataset.scala:2544)
    at org.apache.spark.sql.Dataset.take(Dataset.scala:2758)
    at org.apache.spark.sql.Dataset.getRows(Dataset.scala:254)
    at org.apache.spark.sql.Dataset.showString(Dataset.scala:291)
    at sun.reflect.GeneratedMethodAccessor122.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:282)
    at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
    at py4j.commands.CallCommand.execute(CallCommand.java:79)
    at py4j.GatewayConnection.run(GatewayConnection.java:238)
    at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.spark.api.python.PythonException: Traceback (most recent call last):
  File "/content/spark-2.4.3-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/worker.py", line 377, in main
    process()
  File "/content/spark-2.4.3-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/worker.py", line 372, in process
    serializer.dump_stream(func(split_index, iterator), outfile)
  File "/content/spark-2.4.3-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/serializers.py", line 345, in dump_stream
    self.serializer.dump_stream(self._batched(iterator), stream)
  File "/content/spark-2.4.3-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/serializers.py", line 141, in dump_stream
    for obj in iterator:
  File "/content/spark-2.4.3-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/serializers.py", line 334, in _batched
    for item in iterator:
  File "<string>", line 1, in <lambda>
  File "/content/spark-2.4.3-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/worker.py", line 85, in <lambda>
    return lambda *a: f(*a)
  File "/content/spark-2.4.3-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/util.py", line 99, in wrapper
    return f(*args, **kwargs)
  File "<ipython-input-11-9ec9e286520d>", line 3, in <lambda>
TypeError: 'NoneType' object is not subscriptable

    at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.handlePythonException(PythonRunner.scala:452)
    at org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$1.read(PythonUDFRunner.scala:81)
    at org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$1.read(PythonUDFRunner.scala:64)
    at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:406)
    at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
    at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
    at scala.collection.Iterator$GroupedIterator.fill(Iterator.scala:1124)
    at scala.collection.Iterator$GroupedIterator.hasNext(Iterator.scala:1130)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
    at scala.collection.Iterator$class.foreach(Iterator.scala:891)
    at scala.collection.AbstractIterator.foreach(Iterator.scala:1334)
    at org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:224)
    at org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$2.writeIteratorToStream(PythonUDFRunner.scala:50)
    at org.apache.spark.api.python.BasePythonRunner$WriterThread$$anonfun$run$1.apply(PythonRunner.scala:345)
    at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1945)
    at org.apache.spark.api.python.BasePythonRunner$WriterThread.run(PythonRunner.scala:194)

---

您的数据帧中有Nones，通过应用UDF，它将执行

None[1://code>，这会导致错误
TypeError:“NoneType”对象不可下标（您可以在python shell中尝试）

当使用内置pyspark函数时，它将始终映射null->null。如果您希望通过UDF执行此操作（由于spark对内置sql函数进行内部优化，因此不建议使用UDF），则需要捕获
None
案例：
lambda x:x If not x else x[1://code>
ddf\u temp.show（）是否有效？您是在应用udf之前还是直接从磁盘读取它？由于延迟执行，实际错误可能在本次演示之前就已经出现，并且可能与count null无关。show（）工作，是的，给我带来麻烦的列之前已经通过UDF进行了争论。这不会是一个问题，因为内存使用？这是因为UDF。如果我对pre-UDF列执行相同的操作，我不会有任何问题。从UDF返回的对象的类型是什么？如果是pandas或numpy，请尝试将其转换为float（）或int（）。谢谢你的技巧。。。是的，在阅读了额外的文档之后，我完全明白，如果我想要高效的代码，我需要使用pyspark的内置函数来完成所有事情。。那将迫使我去做和学习函数式编程。
remove_first_char = udf(lambda x: x[1:])
ddf4 = ddf3.withColumn('State Bottle Cost', remove_first_char('State Bottle Cost'))

multiply_by_100 = udf(lambda x: x*100)

ddf5 = ddf4.withColumn('State Bottle Cost', ddf4['State Bottle Cost'].cast(DoubleType()))
ddf5 = ddf5.withColumn('State Bottle Cost', multiply_by_100('State Bottle Cost'))
ddf5 = ddf5.withColumn('State Bottle Cost', ddf5['State Bottle Cost'].cast(IntegerType()))