Issue with df.show() in pyspark

﹥>﹥吖頭↗ 提交于 2021-01-28 09:19:37

问题


I have the following code:

import pyspark 
import pandas as pd
from pyspark.sql import SQLContext
from pyspark.sql.functions import udf
from pyspark.sql.types import IntegerType, StringType
sc = pyspark.SparkContext()
sqlCtx = SQLContext(sc)

df_pd = pd.DataFrame(
    data={'integers': [1, 2, 3],
     'floats': [-1.0, 0.5, 2.7],
     'integer_arrays': [[1, 2], [3, 4, 5], [6, 7, 8, 9]]}
)
df = sqlCtx.createDataFrame(df_pd)
df.printSchema()

Runs fine until here, but when I run:

df.show()

It gives this error:

---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
<ipython-input-10-1a6ce2362cd4> in <module>()
----> 1 df.show()

C:\Anaconda\lib\site-packages\pyspark\sql\dataframe.py in show(self, n, truncate, vertical)
    376         """
    377         if isinstance(truncate, bool) and truncate:
--> 378             print(self._jdf.showString(n, 20, vertical))
    379         else:
    380             print(self._jdf.showString(n, int(truncate), vertical))

C:\Anaconda\lib\site-packages\py4j\java_gateway.py in __call__(self, *args)
   1255         answer = self.gateway_client.send_command(command)
   1256         return_value = get_return_value(
-> 1257             answer, self.gateway_client, self.target_id, self.name)
   1258 
   1259         for temp_arg in temp_args:

C:\Anaconda\lib\site-packages\pyspark\sql\utils.py in deco(*a, **kw)
     61     def deco(*a, **kw):
     62         try:
---> 63             return f(*a, **kw)
     64         except py4j.protocol.Py4JJavaError as e:
     65             s = e.java_exception.toString()

C:\Anaconda\lib\site-packages\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 o42.showString.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 1.0 failed 1 times, most recent failure: Lost task 0.0 in stage 1.0 (TID 1, localhost, executor driver): org.apache.spark.SparkException: Python worker failed to connect back.
    at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:170)
    at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:97)
    at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:117)
    at org.apache.spark.api.python.BasePythonRunner.compute(PythonRunner.scala:108)
    at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:65)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
    at org.apache.spark.scheduler.Task.run(Task.scala:121)
    at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:402)
    at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:408)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
    at java.lang.Thread.run(Unknown Source)
Caused by: java.net.SocketTimeoutException: Accept timed out
    at java.net.DualStackPlainSocketImpl.waitForNewConnection(Native Method)
    at java.net.DualStackPlainSocketImpl.socketAccept(Unknown Source)
    at java.net.AbstractPlainSocketImpl.accept(Unknown Source)
    at java.net.PlainSocketImpl.accept(Unknown Source)
    at java.net.ServerSocket.implAccept(Unknown Source)
    at java.net.ServerSocket.accept(Unknown Source)
    at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:164)
    ... 35 more

Driver stacktrace:
    at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1887)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1875)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1874)
    at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
    at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
    at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1874)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
    at scala.Option.foreach(Option.scala:257)
    at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:926)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2108)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2057)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2046)
    at org.apache.spark.util.EventLoop$$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$$collectFromPlan(Dataset.scala:3384)
    at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2545)
    at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2545)
    at org.apache.spark.sql.Dataset$$anonfun$53.apply(Dataset.scala:3365)
    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:3364)
    at org.apache.spark.sql.Dataset.head(Dataset.scala:2545)
    at org.apache.spark.sql.Dataset.take(Dataset.scala:2759)
    at org.apache.spark.sql.Dataset.getRows(Dataset.scala:255)
    at org.apache.spark.sql.Dataset.showString(Dataset.scala:292)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
    at java.lang.reflect.Method.invoke(Unknown Source)
    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(Unknown Source)
Caused by: org.apache.spark.SparkException: Python worker failed to connect back.
    at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:170)
    at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:97)
    at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:117)
    at org.apache.spark.api.python.BasePythonRunner.compute(PythonRunner.scala:108)
    at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:65)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
    at org.apache.spark.scheduler.Task.run(Task.scala:121)
    at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:402)
    at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:408)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
    ... 1 more
Caused by: java.net.SocketTimeoutException: Accept timed out
    at java.net.DualStackPlainSocketImpl.waitForNewConnection(Native Method)
    at java.net.DualStackPlainSocketImpl.socketAccept(Unknown Source)
    at java.net.AbstractPlainSocketImpl.accept(Unknown Source)
    at java.net.PlainSocketImpl.accept(Unknown Source)
    at java.net.ServerSocket.implAccept(Unknown Source)
    at java.net.ServerSocket.accept(Unknown Source)
    at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:164)
    ... 35 more

How can I solve this?

I am using:

  • python 3.6.5
  • Spark v2.4.0
  • pyspark 2.4.0

回答1:


"Accept timed out" generally points to a problem with your spark instance. It may be overloaded or not enough resources (memory/cpu) to start your job or it might be a temporary network issue. You can monitor you jobs on Spark UI.

Also there is some issue with your code. You can use spark session object directly to create dataframe.

import pandas as pd

df_pd = pd.DataFrame(
    data={'integers': [1, 2, 3],
     'floats': [-1.0, 0.5, 2.7],
     'integer_arrays': [[1, 2], [3, 4, 5], [6, 7, 8, 9]]}
)
df = spark.createDataFrame(df_pd)
df.printSchema()


来源:https://stackoverflow.com/questions/53641328/issue-with-df-show-in-pyspark

易学教程内所有资源均来自网络或用户发布的内容,如有违反法律规定的内容欢迎反馈
该文章没有解决你所遇到的问题?点击提问,说说你的问题,让更多的人一起探讨吧!