Using Windows 10. Pyspark==3.0.1.
My code:
spark = SparkSession.builder.appName("app").getOrCreate()
s = StructType().add("loggedPersonID", StringType(), True).add("latitude", FloatType(), True).add("longitude", FloatType(), True).add("t_from", TimestampType(), True).add("t_to", TimestampType(), True)
json_sdf = spark.readStream.schema(s).json(filepath)
json_sdf.isStreaming
json_sdf.printSchema()
json_sdf.createOrReplaceTempView("snapshot")
d = json_sdf.select("latitude").where("loggedPersonID = 6")
d.writeStream.format("console").start()
Error:
ERROR StreamMetadata: Error writing stream metadata StreamMetadata(320b32f9-c938-410f-8acc-020630570676) to file:/C:/Users/***/AppData/Local/Temp/temporary-baf30601-3b5c-41aa-a211-cfe8cd2fe729/metadata
java.lang.UnsatisfiedLinkError: org.apache.hadoop.io.nativeio.NativeIO$Windows.createFileWithMode0(Ljava/lang/String;JJJI)Ljava/io/FileDescriptor;
at org.apache.hadoop.io.nativeio.NativeIO$Windows.createFileWithMode0(Native Method)
at org.apache.hadoop.io.nativeio.NativeIO$Windows.createFileOutputStreamWithMode(NativeIO.java:559)
at org.apache.hadoop.fs.RawLocalFileSystem$LocalFSFileOutputStream.<init>(RawLocalFileSystem.java:219)
at org.apache.hadoop.fs.RawLocalFileSystem$LocalFSFileOutputStream.<init>(RawLocalFileSystem.java:209)
at org.apache.hadoop.fs.RawLocalFileSystem.createOutputStreamWithMode(RawLocalFileSystem.java:307)
at org.apache.hadoop.fs.RawLocalFileSystem.create(RawLocalFileSystem.java:296)
at org.apache.hadoop.fs.RawLocalFileSystem.create(RawLocalFileSystem.java:328)
at org.apache.hadoop.fs.FileSystem.primitiveCreate(FileSystem.java:1017)
at org.apache.hadoop.fs.DelegateToFileSystem.createInternal(DelegateToFileSystem.java:100)
at org.apache.hadoop.fs.ChecksumFs$ChecksumFSOutputSummer.<init>(ChecksumFs.java:353)
at org.apache.hadoop.fs.ChecksumFs.createInternal(ChecksumFs.java:400)
at org.apache.hadoop.fs.AbstractFileSystem.create(AbstractFileSystem.java:596)
at org.apache.hadoop.fs.FileContext$3.next(FileContext.java:686)
at org.apache.hadoop.fs.FileContext$3.next(FileContext.java:682)
at org.apache.hadoop.fs.FSLinkResolver.resolve(FSLinkResolver.java:90)
at org.apache.hadoop.fs.FileContext.create(FileContext.java:688)
at org.apache.spark.sql.execution.streaming.FileContextBasedCheckpointFileManager.createTempFile(CheckpointFileManager.scala:310)
at org.apache.spark.sql.execution.streaming.CheckpointFileManager$RenameBasedFSDataOutputStream.<init>(CheckpointFileManager.scala:133)
at org.apache.spark.sql.execution.streaming.CheckpointFileManager$RenameBasedFSDataOutputStream.<init>(CheckpointFileManager.scala:136)
at org.apache.spark.sql.execution.streaming.FileContextBasedCheckpointFileManager.createAtomic(CheckpointFileManager.scala:316)
at org.apache.spark.sql.execution.streaming.StreamMetadata$.write(StreamMetadata.scala:78)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$streamMetadata$1(StreamExecution.scala:177)
at scala.Option.getOrElse(Option.scala:189)
at org.apache.spark.sql.execution.streaming.StreamExecution.<init>(StreamExecution.scala:175)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.<init>(MicroBatchExecution.scala:49)
at org.apache.spark.sql.streaming.StreamingQueryManager.createQuery(StreamingQueryManager.scala:317)
at org.apache.spark.sql.streaming.StreamingQueryManager.startQuery(StreamingQueryManager.scala:359)
at org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:366)
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)
[2021-01-24 23:48:57,585] ERROR in app: Exception on /place_matching [POST]
Traceback (most recent call last):
File "C:\Users\***\anaconda3\lib\site-packages\flask\app.py", line 2447, in wsgi_app
response = self.full_dispatch_request()
File "C:\Users\***\anaconda3\lib\site-packages\flask\app.py", line 1952, in full_dispatch_request
rv = self.handle_user_exception(e)
File "C:\Users\***\anaconda3\lib\site-packages\flask\app.py", line 1821, in handle_user_exception
reraise(exc_type, exc_value, tb)
File "C:\Users\***\anaconda3\lib\site-packages\flask\_compat.py", line 39, in reraise
raise value
File "C:\Users\***\anaconda3\lib\site-packages\flask\app.py", line 1950, in full_dispatch_request
rv = self.dispatch_request()
File "C:\Users\***\anaconda3\lib\site-packages\flask\app.py", line 1936, in dispatch_request
return self.view_functions[rule.endpoint](**req.view_args)
File "E:\*****\app.py", line 136, in algorithm
d.writeStream.format("console").start()
File "C:\spark-3.0.1-bin-hadoop2.7\python\pyspark\sql\streaming.py", line 1211, in start
return self._sq(self._jwrite.start())
File "C:\Users\***\anaconda3\lib\site-packages\py4j\java_gateway.py", line 1304, in __call__
return_value = get_return_value(
File "C:\spark-3.0.1-bin-hadoop2.7\python\pyspark\sql\utils.py", line 128, in deco
return f(*a, **kw)
File "C:\Users\***\anaconda3\lib\site-packages\py4j\protocol.py", line 326, in get_return_value
raise Py4JJavaError(
py4j.protocol.Py4JJavaError: An error occurred while calling o39.start.
: java.lang.UnsatisfiedLinkError: org.apache.hadoop.io.nativeio.NativeIO$Windows.createFileWithMode0(Ljava/lang/String;JJJI)Ljava/io/FileDescriptor;
at org.apache.hadoop.io.nativeio.NativeIO$Windows.createFileWithMode0(Native Method)
at org.apache.hadoop.io.nativeio.NativeIO$Windows.createFileOutputStreamWithMode(NativeIO.java:559)
at org.apache.hadoop.fs.RawLocalFileSystem$LocalFSFileOutputStream.<init>(RawLocalFileSystem.java:219)
at org.apache.hadoop.fs.RawLocalFileSystem$LocalFSFileOutputStream.<init>(RawLocalFileSystem.java:209)
at org.apache.hadoop.fs.RawLocalFileSystem.createOutputStreamWithMode(RawLocalFileSystem.java:307)
at org.apache.hadoop.fs.RawLocalFileSystem.create(RawLocalFileSystem.java:296)
at org.apache.hadoop.fs.RawLocalFileSystem.create(RawLocalFileSystem.java:328)
at org.apache.hadoop.fs.FileSystem.primitiveCreate(FileSystem.java:1017)
at org.apache.hadoop.fs.DelegateToFileSystem.createInternal(DelegateToFileSystem.java:100)
at org.apache.hadoop.fs.ChecksumFs$ChecksumFSOutputSummer.<init>(ChecksumFs.java:353)
at org.apache.hadoop.fs.ChecksumFs.createInternal(ChecksumFs.java:400)
at org.apache.hadoop.fs.AbstractFileSystem.create(AbstractFileSystem.java:596)
at org.apache.hadoop.fs.FileContext$3.next(FileContext.java:686)
at org.apache.hadoop.fs.FileContext$3.next(FileContext.java:682)
at org.apache.hadoop.fs.FSLinkResolver.resolve(FSLinkResolver.java:90)
at org.apache.hadoop.fs.FileContext.create(FileContext.java:688)
at org.apache.spark.sql.execution.streaming.FileContextBasedCheckpointFileManager.createTempFile(CheckpointFileManager.scala:310)
at org.apache.spark.sql.execution.streaming.CheckpointFileManager$RenameBasedFSDataOutputStream.<init>(CheckpointFileManager.scala:133)
at org.apache.spark.sql.execution.streaming.CheckpointFileManager$RenameBasedFSDataOutputStream.<init>(CheckpointFileManager.scala:136)
at org.apache.spark.sql.execution.streaming.FileContextBasedCheckpointFileManager.createAtomic(CheckpointFileManager.scala:316)
at org.apache.spark.sql.execution.streaming.StreamMetadata$.write(StreamMetadata.scala:78)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$streamMetadata$1(StreamExecution.scala:177)
at scala.Option.getOrElse(Option.scala:189)
at org.apache.spark.sql.execution.streaming.StreamExecution.<init>(StreamExecution.scala:175)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.<init>(MicroBatchExecution.scala:49)
at org.apache.spark.sql.streaming.StreamingQueryManager.createQuery(StreamingQueryManager.scala:317)
at org.apache.spark.sql.streaming.StreamingQueryManager.startQuery(StreamingQueryManager.scala:359)
at org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:366)
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)
I have tried all the answers from the questions:
