R Royer Andino | Big Data Forum

how to fix syntax error when saving a dataframe as a hive table. PySpark

event 2022-12-26 visibility 900 comment 4 insights
more_vert
insights Stats

Code:

import findspark
findspark.init()

from pyspark.sql import SparkSession
from pyspark.sql.functions import *
from pyspark.sql.functions import broadcast
from pyspark.sql.types import *

spark = SparkSession.builder.getOrCreate()

emp = [(1, "AAA", "dept1", 1000),
    (2, "BBB", "dept1", 1100),
    (3, "CCC", "dept1", 3000),
    (4, "DDD", "dept1", 1500),
    (5, "EEE", "dept2", 8000),
    (6, "FFF", "dept2", 7200),
    (7, "GGG", "dept3", 7100),
    (None, None, None, 7500),
    (9, "III", None, 4500),
    (10, None, "dept5", 2500)]

dept = [("dept1", "Department - 1"),
        ("dept2", "Department - 2"),
        ("dept3", "Department - 3"),
        ("dept4", "Department - 4")
       ]

df = spark.createDataFrame(emp, ["id", "name", "dept", "salary"])
deptdf = spark.createDataFrame(dept, ["id", "name"])

df.createOrReplaceTempView("empdf")
deptdf.createOrReplaceTempView("deptdf")

df.write.saveAsTable("hive_empdf", mode = "overwrite")
deptdf.write.saveAsTable("hive_deptdf", mode = "overwrite")


Error:

Py4JJavaError                             Traceback (most recent call last)
~\AppData\Local\Temp\ipykernel_13920\1501817596.py in <module>
     24
     25 # Save as HIVE tables.
---> 26 df.write.saveAsTable("hive_empdf", mode = "overwrite")
     27 deptdf.write.saveAsTable("hive_deptdf", mode = "overwrite")

C:\spark\python\pyspark\sql\readwriter.py in saveAsTable(self, name, format, mode, partitionBy, **options)
   1039         if format is not None:
   1040             self.format(format)
-> 1041         self._jwrite.saveAsTable(name)
   1042
   1043     def json(

C:\spark\python\lib\py4j-0.10.9.5-src.zip\py4j\java_gateway.py in _call_(self, *args)
   1319
   1320         answer = self.gateway_client.send_command(command)
-> 1321         return_value = get_return_value(
   1322             answer, self.gateway_client, self.target_id, self.name)
   1323

C:\spark\python\pyspark\sql\utils.py in deco(*a, **kw)
    188     def deco(*a: Any, **kw: Any) -> Any:
    189         try:
--> 190             return f(*a, **kw)
    191         except Py4JJavaError as e:
    192             converted = convert_exception(e.java_exception)

C:\spark\python\lib\py4j-0.10.9.5-src.zip\py4j\protocol.py in get_return_value(answer, gateway_client, target_id, name)
    324             value = OUTPUT_CONVERTER[type](answer[2:], gateway_client)
    325             if answer[1] == REFERENCE_TYPE:
--> 326                 raise Py4JJavaError(
    327                     "An error occurred while calling {0}{1}{2}.\n".
    328                     format(target_id, ".", name), value)

Py4JJavaError: An error occurred while calling o57.saveAsTable.
: java.lang.UnsatisfiedLinkError: org.apache.hadoop.io.nativeio.NativeIO$Windows.access0(Ljava/lang/String;I)Z
    at org.apache.hadoop.io.nativeio.NativeIO$Windows.access0(Native Method)
    at org.apache.hadoop.io.nativeio.NativeIO$Windows.access(NativeIO.java:793)
    at org.apache.hadoop.fs.FileUtil.canRead(FileUtil.java:1218)
    at org.apache.hadoop.fs.FileUtil.list(FileUtil.java:1423)
    at org.apache.hadoop.fs.RawLocalFileSystem.listStatus(RawLocalFileSystem.java:601)
    at org.apache.hadoop.fs.FileSystem.listStatus(FileSystem.java:1972)
    at org.apache.hadoop.fs.FileSystem.listStatus(FileSystem.java:2014)
    at org.apache.hadoop.fs.ChecksumFileSystem.listStatus(ChecksumFileSystem.java:761)
    at org.apache.spark.sql.catalyst.catalog.SessionCatalog.validateTableLocation(SessionCatalog.scala:384)
    at org.apache.spark.sql.execution.command.CreateDataSourceTableAsSelectCommand.run(createDataSourceTables.scala:175)
    at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:113)
    at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:111)
    at org.apache.spark.sql.execution.command.DataWritingCommandExec.executeCollect(commands.scala:125)
    at org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.$anonfun$applyOrElse$1(QueryExecution.scala:98)
    at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:109)
    at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:169)
    at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:95)
    at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779)
    at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
    at org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:98)
    at org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:94)
    at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$1(TreeNode.scala:584)
    at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:176)
    at org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:584)
    at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDownWithPruning(LogicalPlan.scala:30)
    at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning(AnalysisHelper.scala:267)
    at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning$(AnalysisHelper.scala:263)
    at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
    at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
    at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:560)
    at org.apache.spark.sql.execution.QueryExecution.eagerlyExecuteCommands(QueryExecution.scala:94)
    at org.apache.spark.sql.execution.QueryExecution.commandExecuted$lzycompute(QueryExecution.scala:81)
    at org.apache.spark.sql.execution.QueryExecution.commandExecuted(QueryExecution.scala:79)
    at org.apache.spark.sql.execution.QueryExecution.assertCommandExecuted(QueryExecution.scala:116)
    at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:860)
    at org.apache.spark.sql.DataFrameWriter.createTable(DataFrameWriter.scala:701)
    at org.apache.spark.sql.DataFrameWriter.saveAsTable(DataFrameWriter.scala:679)
    at org.apache.spark.sql.DataFrameWriter.saveAsTable(DataFrameWriter.scala:573)
    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.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)
    at py4j.ClientServerConnection.run(ClientServerConnection.java:106)
    at java.lang.Thread.run(Thread.java:750)

More from Kontext
comment Comments
Raymond Raymond #1780 access_time 2 years ago more_vert

Hi Royer,

Just follow up on this - is your issue now resolved?

Raymond Raymond #1779 access_time 2 years ago more_vert

Can you add the following configuration when init Spark session?

.config("spark.sql.warehouse.dir", warehouseLocation)

Change warehouseLocation to a folder that your running account has write access to. By default, we can use Derby (file based database) as warehouse. 


format_quote

person Royer access_time 2 years ago

Hi. Version 3.3.120221226221957-IMG-20221127-WA0005.jpg

R Royer Andino #1778 access_time 2 years ago more_vert

Hi. Version 3.3.120221226221957-IMG-20221127-WA0005.jpg

format_quote

person Raymond access_time 2 years ago

What is your pyspark version, Royer?

Raymond Raymond #1777 access_time 2 years ago more_vert

What is your pyspark version, Royer?

Please log in or register to comment.

account_circle Log in person_add Register

Log in with external accounts