我将字符串列转换为带有UDF的哈希：
import pyspark.sql.functions as func
from pyspark.sql.types import TimestampType
from datetime import datetime
import hashlib
hash_udf = func.udf(lambda x: hashlib.sha256(str(x)).hexdigest().upper())
udf_dt = func.udf(lambda x: datetime.strptime(str(x), date_format), TimestampType())
df.show()
id | timestamp
1121234 | 20151112030203
9121234 | 20151112050203
8171234 | 20161112055211
df = df.withColumn('hashed', hash_udf(df.id))
df.show()
但它会生成
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-10-3106d06b6e49> in <module>()
----> 1 df.show()
/usr/hdp/2.3.4.1-10/spark/python/pyspark/sql/dataframe.py in show(self, n, truncate)
255 +---+-----+
256 """
--> 257 print(self._jdf.showString(n, truncate))
258
259 def __repr__(self):
/usr/hdp/2.3.4.1-10/spark/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/hdp/2.3.4.1-10/spark/python/pyspark/sql/utils.py 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/hdp/2.3.4.1-10/spark/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 o44.showString.
: org.apache.spark.SparkException: Job aborted due to stage failure: Total size of serialized results of 9113 tasks (1024.0 MB) is bigger than spark.driver.maxResultSize (1024.0 MB)
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 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:1952)
at org.apache.spark.rdd.RDD$$anonfun$reduce$1.apply(RDD.scala:1025)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.RDD.reduce(RDD.scala:1007)
at org.apache.spark.rdd.RDD$$anonfun$takeOrdered$1.apply(RDD.scala:1383)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.RDD.takeOrdered(RDD.scala:1370)
at org.apache.spark.sql.execution.TakeOrderedAndProject.collectData(basicOperators.scala:213)
at org.apache.spark.sql.execution.TakeOrderedAndProject.doExecute(basicOperators.scala:223)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130)
at org.apache.spark.sql.execution.BatchPythonEvaluation.doExecute(python.scala:359)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130)
at org.apache.spark.sql.execution.Project.doExecute(basicOperators.scala:46)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130)
at org.apache.spark.sql.execution.ConvertToSafe.doExecute(rowFormatConverters.scala:56)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:187)
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:1538)
at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1538)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
at org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:2125)
at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$execute$1(DataFrame.scala:1537)
at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$collect(DataFrame.scala:1544)
at org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1414)
at org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1413)
at org.apache.spark.sql.DataFrame.withCallback(DataFrame.scala:2138)
at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1413)
at org.apache.spark.sql.DataFrame.take(DataFrame.scala:1495)
at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:171)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
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:745)
所以看起来结果太大而无法序列化，因为
: org.apache.spark.SparkException: Job aborted due to stage failure: Total size of serialized results of 9113 tasks (1024.0 MB) is bigger than spark.driver.maxResultSize (1024.0 MB)
但即使增加了这个错误仍然存在。应该更改哪些配置，以便可以处理这个小数据集？