У меня проблема с конфигурацией, настроенной на использование Pyspark для чтения данных s3. Я скачал oop - aws .jar и aws - java -sdk-1.11.734.jar. Это единая кластерная среда.
Вот код, который я набираю в pyspark
import os
import pyspark
from pyspark.sql import SparkSession
spark = SparkSession.builder\
.config("spark.hadoop.fs.s3a.access.key", 'xxxxx')\
.config("spark.hadoop.fs.s3a.secret.key", 'xxxxx')\
.config("spark.jars.packages",'/spark/jars/aws-java-sdk-1.11.734.jar:/spark/jars/hadoop-aws-2.10.0.jar') \
.getOrCreate()
df = spark.read.format('json').load('s3a://folder/file_1.json')
А вот и сообщения об ошибках:
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/spark/python/pyspark/sql/readwriter.py", line 166, in load
return self._df(self._jreader.load(path))
File "/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py", line 1257, in __call__
File "/spark/python/pyspark/sql/utils.py", line 63, in deco
return f(*a, **kw)
File "/spark/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py", line 328, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o99.load.
: java.lang.NoClassDefFoundError: com/amazonaws/AmazonClientException
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:348)
at org.apache.hadoop.conf.Configuration.getClassByNameOrNull(Configuration.java:2134)
at org.apache.hadoop.conf.Configuration.getClassByName(Configuration.java:2099)
at org.apache.hadoop.conf.Configuration.getClass(Configuration.java:2193)
at org.apache.hadoop.fs.FileSystem.getFileSystemClass(FileSystem.java:2654)
at org.apache.hadoop.fs.FileSystem.createFileSystem(FileSystem.java:2667)
at org.apache.hadoop.fs.FileSystem.access$200(FileSystem.java:94)
at org.apache.hadoop.fs.FileSystem$Cache.getInternal(FileSystem.java:2703)
at org.apache.hadoop.fs.FileSystem$Cache.get(FileSystem.java:2685)
at org.apache.hadoop.fs.FileSystem.get(FileSystem.java:373)
at org.apache.hadoop.fs.Path.getFileSystem(Path.java:295)
at org.apache.spark.sql.execution.streaming.FileStreamSink$.hasMetadata(FileStreamSink.scala:45)
at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:332)
at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:223)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:211)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:178)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
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: java.lang.ClassNotFoundException: com.amazonaws.AmazonClientException
at java.net.URLClassLoader.findClass(URLClassLoader.java:382)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:349)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
... 28 more
Как решить "java .lang. ClassNotFoundException: com.amazon aws .AmazonClientException "ошибка? Пожалуйста, покажите мне, как я должен изменить настройки. Большое спасибо.