So I have parquet files in S3 bucket and I want to load it using pyspark in python, but I'm getting some error, here's what I have tried so far. I'm using Juputer Notebook in EMR Cluster.
spark = SparkSession.builder.master("local").appName("app name").config("spark.some.config.option", True).getOrCreate()
file = s3://somelocation
df = spark.read.parquet(file)
This is giving me following error:
Py4JJavaError Traceback (most recent call last)
/tmp/ipykernel_3146/2307354378.py in <module>
----> 1 df = spark.read.parquet(file)
2 df
~/anaconda3/envs/python3/lib/python3.7/site-packages/pyspark/sql/readwriter.py in parquet(self, *paths, **options)
456 modifiedAfter=modifiedAfter)
457
--> 458 return self._df(self._jreader.parquet(_to_seq(self._spark._sc, paths)))
459
460 def text(self, paths, wholetext=False, lineSep=None, pathGlobFilter=None,
~/anaconda3/envs/python3/lib/python3.7/site-packages/py4j/java_gateway.py in __call__(self, *args)
1303 answer = self.gateway_client.send_command(command)
1304 return_value = get_return_value(
-> 1305 answer, self.gateway_client, self.target_id, self.name)
1306
1307 for temp_arg in temp_args:
~/anaconda3/envs/python3/lib/python3.7/site-packages/pyspark/sql/utils.py in deco(*a, **kw)
109 def deco(*a, **kw):
110 try:
--> 111 return f(*a, **kw)
112 except py4j.protocol.Py4JJavaError as e:
113 converted = convert_exception(e.java_exception)
~/anaconda3/envs/python3/lib/python3.7/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 o60.parquet.
: org.apache.hadoop.fs.UnsupportedFileSystemException: No FileSystem for scheme "s3"
at org.apache.hadoop.fs.FileSystem.getFileSystemClass(FileSystem.java:3281)
at org.apache.hadoop.fs.FileSystem.createFileSystem(FileSystem.java:3301)
at org.apache.hadoop.fs.FileSystem.access$200(FileSystem.java:124)
at org.apache.hadoop.fs.FileSystem$Cache.getInternal(FileSystem.java:3352)
at org.apache.hadoop.fs.FileSystem$Cache.get(FileSystem.java:3320)
at org.apache.hadoop.fs.FileSystem.get(FileSystem.java:479)
at org.apache.hadoop.fs.Path.getFileSystem(Path.java:361)
at org.apache.spark.sql.execution.streaming.FileStreamSink$.hasMetadata(FileStreamSink.scala:46)
at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:377)
at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:325)
at org.apache.spark.sql.DataFrameReader.$anonfun$load$3(DataFrameReader.scala:307)
at scala.Option.getOrElse(Option.scala:189)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:307)
at org.apache.spark.sql.DataFrameReader.parquet(DataFrameReader.scala:833)
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)
I checked multiple similar post and tried everything, still nothing is working. I tried to change the s3 path to s3a as mentioned in one post, then I got another error:
Py4JJavaError: An error occurred while calling o64.parquet.
: java.lang.RuntimeException: java.lang.ClassNotFoundException: Class org.apache.hadoop.fs.s3a.S3AFileSystem not found
at org.apache.hadoop.conf.Configuration.getClass(Configuration.java:2595)
at org.apache.hadoop.fs.FileSystem.getFileSystemClass(FileSystem.java:3269)
at org.apache.hadoop.fs.FileSystem.createFileSystem(FileSystem.java:3301)
at org.apache.hadoop.fs.FileSystem.access$200(FileSystem.java:124)
at org.apache.hadoop.fs.FileSystem$Cache.getInternal(FileSystem.java:3352)
at org.apache.hadoop.fs.FileSystem$Cache.get(FileSystem.java:3320)
at org.apache.hadoop.fs.FileSystem.get(FileSystem.java:479)
at org.apache.hadoop.fs.Path.getFileSystem(Path.java:361)
at org.apache.spark.sql.execution.streaming.FileStreamSink$.hasMetadata(FileStreamSink.scala:46)
at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:377)
at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:325)
at org.apache.spark.sql.DataFrameReader.$anonfun$load$3(DataFrameReader.scala:307)
at scala.Option.getOrElse(Option.scala:189)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:307)
at org.apache.spark.sql.DataFrameReader.parquet(DataFrameReader.scala:833)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.lang.ClassNotFoundException: Class org.apache.hadoop.fs.s3a.S3AFileSystem not found
at org.apache.hadoop.conf.Configuration.getClassByName(Configuration.java:2499)
at org.apache.hadoop.conf.Configuration.getClass(Configuration.java:2593)
... 25 more
So I also tried to download the data to my instance locally and then tried:
spark = (SparkSession
.builder
.appName('loss_comfal')
.config('spark.executor.memory', '110G')
.config('spark.driver.memory', '110G')
.config('spark.driver.maxResultSize', '110G')
.getOrCreate())
files = glob.glob('data/*')
df = spark.read.parquet(files)
which returned me another error:
Py4JJavaError: An error occurred while calling o69.parquet.
: java.lang.ClassCastException: java.util.ArrayList cannot be cast to java.lang.String
at org.apache.spark.sql.internal.SessionState.$anonfun$newHadoopConfWithOptions$1(SessionState.scala:102)
at org.apache.spark.sql.internal.SessionState.$anonfun$newHadoopConfWithOptions$1$adapted(SessionState.scala:102)
at scala.collection.immutable.Map$Map1.foreach(Map.scala:128)
at org.apache.spark.sql.internal.SessionState.newHadoopConfWithOptions(SessionState.scala:102)
at org.apache.spark.sql.execution.datasources.DataSource.newHadoopConfiguration(DataSource.scala:115)
at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:376)
at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:325)
at org.apache.spark.sql.DataFrameReader.$anonfun$load$3(DataFrameReader.scala:307)
at scala.Option.getOrElse(Option.scala:189)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:307)
at org.apache.spark.sql.DataFrameReader.parquet(DataFrameReader.scala:833)
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)
I know there are similar post solved, and I have tried all of them but none is working.