Hi,
I am trying to connect to AWS S3 and read a csv file (running POC) from a
bucket.
I have s3cmd and and being able to run ls and other operation from cli.
*Present Configuration:*
Python 3.7
Spark 2.3.1
*JARs added:*
hadoop-aws-2.7.3.jar (in sync with the hadoop version used with spark)
aws-java-sdk-1.11.472.jar
Trying out the following code:
>>> sc=spark.sparkContext
>
> >>> hadoop_conf=sc._jsc.hadoopConfiguration()
>
> >>> hadoop_conf.set("fs.s3n.awsAccessKeyId", "abcd")
>
> >>> hadoop_conf.set("fs.s3n.awsSecretAccessKey", "xyz123")
>
> >>> a = spark.read.csv("s3a://test-bucket/breast-cancer-wisconsin.csv",
> header=True)
>
> Traceback (most recent call last):
>
> File "<stdin>", line 1, in <module>
>
> File
> "/Users/aakash/Downloads/spark-2.3.1-bin-hadoop2.7/python/pyspark/sql/readwriter.py",
> line 441, in csv
>
> return
> self._df(self._jreader.csv(self._spark._sc._jvm.PythonUtils.toSeq(path)))
>
> File
> "/Users/aakash/Downloads/spark-2.3.1-bin-hadoop2.7/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py",
> line 1257, in __call__
>
> File
> "/Users/aakash/Downloads/spark-2.3.1-bin-hadoop2.7/python/pyspark/sql/utils.py",
> line 63, in deco
>
> return f(*a, **kw)
>
> File
> "/Users/aakash/Downloads/spark-2.3.1-bin-hadoop2.7/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 o33.csv.
>
> : java.lang.NoClassDefFoundError: com/amazonaws/auth/AWSCredentialsProvider
>
> 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:354)
>
> at
> org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:239)
>
> at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:227)
>
> at org.apache.spark.sql.DataFrameReader.csv(DataFrameReader.scala:596)
>
> 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.auth.AWSCredentialsProvider
>
> at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
>
> 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
>
>
> >>> a = spark.read.csv("s3a://test-bucket/breast-cancer-wisconsin.csv",
> header=True)
>
> Traceback (most recent call last):
>
> File "<stdin>", line 1, in <module>
>
> File
> "/Users/aakash/Downloads/spark-2.3.1-bin-hadoop2.7/python/pyspark/sql/readwriter.py",
> line 441, in csv
>
> return
> self._df(self._jreader.csv(self._spark._sc._jvm.PythonUtils.toSeq(path)))
>
> File
> "/Users/aakash/Downloads/spark-2.3.1-bin-hadoop2.7/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py",
> line 1257, in __call__
>
> File
> "/Users/aakash/Downloads/spark-2.3.1-bin-hadoop2.7/python/pyspark/sql/utils.py",
> line 63, in deco
>
> return f(*a, **kw)
>
> File
> "/Users/aakash/Downloads/spark-2.3.1-bin-hadoop2.7/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 o67.csv.
>
> : java.lang.NoClassDefFoundError: com/amazonaws/auth/AWSCredentialsProvider
>
> 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:354)
>
> at
> org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:239)
>
> at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:227)
>
> at org.apache.spark.sql.DataFrameReader.csv(DataFrameReader.scala:596)
>
> 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.auth.AWSCredentialsProvider
>
> at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
>
> 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
>
Any help?
Thanks,
Aakash.
>
>
