I am trying out pyspark on windows by following this article.
The article asks to run pyspark from command prompt.
When I run pyspark in command prompt, it starts jupyter notebook. But in example, it seems that running pyspark in command line starts interactive command line python shell. Why is this so?
The article next asks to read readme file:
>>>textFile = spark.read.text("README.md")
I tried running that in jupyter notebook. But I got following error:
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
D:\Sanjeev\Programs\spark\spark-2.3.0-bin-hadoop2.7\python\pyspark\sql\utils.py in deco(*a, **kw)
62 try:
---> 63 return f(*a, **kw)
64 except py4j.protocol.Py4JJavaError as e:
D:\Sanjeev\Programs\spark\spark-2.3.0-bin-hadoop2.7\python\lib\py4j-0.10.6-src.zip\py4j\protocol.py in get_return_value(answer, gateway_client, target_id, name)
319 "An error occurred while calling {0}{1}{2}.\n".
--> 320 format(target_id, ".", name), value)
321 else:
Py4JJavaError: An error occurred while calling o30.text.
: org.apache.spark.sql.AnalysisException: java.lang.RuntimeException: ExitCodeException exitCode=-1073741515: ;
at org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:106)
at org.apache.spark.sql.hive.HiveExternalCatalog.databaseExists(HiveExternalCatalog.scala:194)
at org.apache.spark.sql.internal.SharedState.externalCatalog$lzycompute(SharedState.scala:114)
at org.apache.spark.sql.internal.SharedState.externalCatalog(SharedState.scala:102)
at org.apache.spark.sql.hive.HiveSessionStateBuilder.externalCatalog(HiveSessionStateBuilder.scala:39)
at org.apache.spark.sql.hive.HiveSessionStateBuilder.catalog$lzycompute(HiveSessionStateBuilder.scala:54)
at org.apache.spark.sql.hive.HiveSessionStateBuilder.catalog(HiveSessionStateBuilder.scala:52)
at org.apache.spark.sql.hive.HiveSessionStateBuilder$$anon$1.<init>(HiveSessionStateBuilder.scala:69)
at org.apache.spark.sql.hive.HiveSessionStateBuilder.analyzer(HiveSessionStateBuilder.scala:69)
at org.apache.spark.sql.internal.BaseSessionStateBuilder$$anonfun$build$2.apply(BaseSessionStateBuilder.scala:293)
at org.apache.spark.sql.internal.BaseSessionStateBuilder$$anonfun$build$2.apply(BaseSessionStateBuilder.scala:293)
at org.apache.spark.sql.internal.SessionState.analyzer$lzycompute(SessionState.scala:79)
at org.apache.spark.sql.internal.SessionState.analyzer(SessionState.scala:79)
at org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:57)
at org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:55)
at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:47)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:74)
at org.apache.spark.sql.SparkSession.baseRelationToDataFrame(SparkSession.scala:428)
at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:233)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:227)
at org.apache.spark.sql.DataFrameReader.text(DataFrameReader.scala:691)
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:497)
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:214)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.RuntimeException: ExitCodeException exitCode=-1073741515:
at org.apache.hadoop.hive.ql.session.SessionState.start(SessionState.java:522)
at org.apache.spark.sql.hive.client.HiveClientImpl.newState(HiveClientImpl.scala:180)
at org.apache.spark.sql.hive.client.HiveClientImpl.<init>(HiveClientImpl.scala:114)
at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:422)
at org.apache.spark.sql.hive.client.IsolatedClientLoader.createClient(IsolatedClientLoader.scala:264)
at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:385)
at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:287)
at org.apache.spark.sql.hive.HiveExternalCatalog.client$lzycompute(HiveExternalCatalog.scala:66)
at org.apache.spark.sql.hive.HiveExternalCatalog.client(HiveExternalCatalog.scala:65)
at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$databaseExists$1.apply$mcZ$sp(HiveExternalCatalog.scala:195)
at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$databaseExists$1.apply(HiveExternalCatalog.scala:195)
at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$databaseExists$1.apply(HiveExternalCatalog.scala:195)
at org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:97)
... 31 more
Caused by: ExitCodeException exitCode=-1073741515:
at org.apache.hadoop.util.Shell.runCommand(Shell.java:582)
at org.apache.hadoop.util.Shell.run(Shell.java:479)
at org.apache.hadoop.util.Shell$ShellCommandExecutor.execute(Shell.java:773)
at org.apache.hadoop.util.Shell.execCommand(Shell.java:866)
at org.apache.hadoop.util.Shell.execCommand(Shell.java:849)
at org.apache.hadoop.fs.RawLocalFileSystem.setPermission(RawLocalFileSystem.java:733)
at org.apache.hadoop.fs.RawLocalFileSystem.mkOneDirWithMode(RawLocalFileSystem.java:491)
at org.apache.hadoop.fs.RawLocalFileSystem.mkdirsWithOptionalPermission(RawLocalFileSystem.java:532)
at org.apache.hadoop.fs.RawLocalFileSystem.mkdirs(RawLocalFileSystem.java:509)
at org.apache.hadoop.fs.FilterFileSystem.mkdirs(FilterFileSystem.java:305)
at org.apache.hadoop.hive.ql.exec.Utilities.createDirsWithPermission(Utilities.java:3679)
at org.apache.hadoop.hive.ql.session.SessionState.createRootHDFSDir(SessionState.java:597)
at org.apache.hadoop.hive.ql.session.SessionState.createSessionDirs(SessionState.java:554)
at org.apache.hadoop.hive.ql.session.SessionState.start(SessionState.java:508)
... 46 more
During handling of the above exception, another exception occurred:
AnalysisException Traceback (most recent call last)
<ipython-input-1-9f78f301aea9> in <module>()
----> 1 textFile = spark.read.text("README.md")
D:\Sanjeev\Programs\spark\spark-2.3.0-bin-hadoop2.7\python\pyspark\sql\readwriter.py in text(self, paths, wholetext)
326 if isinstance(paths, basestring):
327 paths = [paths]
--> 328 return self._df(self._jreader.text(self._spark._sc._jvm.PythonUtils.toSeq(paths)))
329
330 @since(2.0)
D:\Sanjeev\Programs\spark\spark-2.3.0-bin-hadoop2.7\python\lib\py4j-0.10.6-src.zip\py4j\java_gateway.py in __call__(self, *args)
1158 answer = self.gateway_client.send_command(command)
1159 return_value = get_return_value(
-> 1160 answer, self.gateway_client, self.target_id, self.name)
1161
1162 for temp_arg in temp_args:
D:\Sanjeev\Programs\spark\spark-2.3.0-bin-hadoop2.7\python\pyspark\sql\utils.py in deco(*a, **kw)
67 e.java_exception.getStackTrace()))
68 if s.startswith('org.apache.spark.sql.AnalysisException: '):
---> 69 raise AnalysisException(s.split(': ', 1)[1], stackTrace)
70 if s.startswith('org.apache.spark.sql.catalyst.analysis'):
71 raise AnalysisException(s.split(': ', 1)[1], stackTrace)
AnalysisException: 'java.lang.RuntimeException: ExitCodeException exitCode=-1073741515: ;'
I am finding absolutely no explanation in that stack trace. Earlier I got stack trace with last line AnalysisException: 'Path does not exist: file:/C:/Users/Mahesha999/README.md;' which hinted me that I should be running pyspark from %SPARK_HOME% instead of user directory. But above I am not getting any such hint from stack trace. What am missing?
