我正在使用 GeoSpark (Apache Sedona) 库从 .csv 文件中读取地理空间数据。我想从此 csv 文件中读取多边形，但出现以下错误：
: java.lang.NoClassDefFoundError: org/apache/spark/sql/catalyst/expressions/codegen/CodegenFallback$class
这是代码：
from geospark.register import upload_jars
from geospark.register import GeoSparkRegistrator
from pyspark.sql import SparkSession
spark = SparkSession.builder.master("local") \
.config("spark.jars.packages","org.datasyslab:geospark:1.3.1,org.datasyslab:geospark-sql_2.3:1.3.1") \
.getOrCreate()
GeoSparkRegistrator.registerAll(spark)
df = spark.read.csv(path="D:\\Arshad\\data\\test.csv",
header=True)
df.createOrReplaceTempView("geotbl")
df2 = spark.sql("select country, st_geomFromWKT(polygon) as geometry from geotbl")
我收到以下错误：
Py4JJavaError Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_12340/2742464755.py in <module>
----> 1 df2 = spark.sql("select country, st_geomFromWKT(polygon) as geometry from geotbl")
c:\users\arshad\appdata\local\programs\python\python37\lib\site-packages\pyspark\sql\session.py in sql(self, sqlQuery)
647 [Row(f1=1, f2=u'row1'), Row(f1=2, f2=u'row2'), Row(f1=3, f2=u'row3')]
648 """
--> 649 return DataFrame(self._jsparkSession.sql(sqlQuery), self._wrapped)
650
651 @since(2.0)
c:\users\arshad\appdata\local\programs\python\python37\lib\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:
c:\users\arshad\appdata\local\programs\python\python37\lib\site-packages\pyspark\sql\utils.py in deco(*a, **kw)
126 def deco(*a, **kw):
127 try:
--> 128 return f(*a, **kw)
129 except py4j.protocol.Py4JJavaError as e:
130 converted = convert_exception(e.java_exception)
c:\users\arshad\appdata\local\programs\python\python37\lib\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 o27.sql.
: java.lang.NoClassDefFoundError: org/apache/spark/sql/catalyst/expressions/codegen/CodegenFallback$class
at org.apache.spark.sql.geosparksql.expressions.ST_GeomFromWKT.<init>(Constructors.scala:118)
at org.apache.spark.sql.geosparksql.expressions.ST_GeomFromWKT$.apply(Constructors.scala:117)
at org.apache.spark.sql.geosparksql.expressions.ST_GeomFromWKT$.apply(Constructors.scala:117)
at org.apache.spark.sql.catalyst.analysis.SimpleFunctionRegistry.lookupFunction(FunctionRegistry.scala:121)
at org.apache.spark.sql.catalyst.catalog.SessionCatalog.lookupFunction(SessionCatalog.scala:1439)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveFunctions$$anonfun$apply$16$$anonfun$applyOrElse$103.$anonfun$applyOrElse$106(Analyzer.scala:1852)
at org.apache.spark.sql.catalyst.analysis.package$.withPosition(package.scala:53)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveFunctions$$anonfun$apply$16$$anonfun$applyOrElse$103.applyOrElse(Analyzer.scala:1852)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveFunctions$$anonfun$apply$16$$anonfun$applyOrElse$103.applyOrElse(Analyzer.scala:1835)
at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDown$1(TreeNode.scala:315)
at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:73)
at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:315)
at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDown$3(TreeNode.scala:320)
at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$mapChildren$1(TreeNode.scala:405)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:243)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:403)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:356)
at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:320)
at org.apache.spark.sql.catalyst.plans.QueryPlan.$anonfun$transformExpressionsDown$1(QueryPlan.scala:98)
at org.apache.spark.sql.catalyst.plans.QueryPlan.$anonfun$mapExpressions$1(QueryPlan.scala:120)
at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:73)
at org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpression$1(QueryPlan.scala:120)
at org.apache.spark.sql.catalyst.plans.QueryPlan.recursiveTransform$1(QueryPlan.scala:131)
at org.apache.spark.sql.catalyst.plans.QueryPlan.$anonfun$mapExpressions$3(QueryPlan.scala:136)
at scala.collection.TraversableLike.$anonfun$map$1(TraversableLike.scala:238)
at scala.collection.immutable.List.foreach(List.scala:392)
at scala.collection.TraversableLike.map(TraversableLike.scala:238)
at scala.collection.TraversableLike.map$(TraversableLike.scala:231)
at scala.collection.immutable.List.map(List.scala:298)
at org.apache.spark.sql.catalyst.plans.QueryPlan.recursiveTransform$1(QueryPlan.scala:136)
at org.apache.spark.sql.catalyst.plans.QueryPlan.$anonfun$mapExpressions$4(QueryPlan.scala:141)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:243)
at org.apache.spark.sql.catalyst.plans.QueryPlan.mapExpressions(QueryPlan.scala:141)
at org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsDown(QueryPlan.scala:98)
at org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressions(QueryPlan.scala:89)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveFunctions$$anonfun$apply$16.applyOrElse(Analyzer.scala:1835)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveFunctions$$anonfun$apply$16.applyOrElse(Analyzer.scala:1833)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsUp$3(AnalysisHelper.scala:90)
at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:73)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsUp$1(AnalysisHelper.scala:90)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:212)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsUp(AnalysisHelper.scala:86)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsUp$(AnalysisHelper.scala:84)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsUp(LogicalPlan.scala:29)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveFunctions$.apply(Analyzer.scala:1833)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveFunctions$.apply(Analyzer.scala:1831)
at org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$2(RuleExecutor.scala:149)
at scala.collection.LinearSeqOptimized.foldLeft(LinearSeqOptimized.scala:126)
at scala.collection.LinearSeqOptimized.foldLeft$(LinearSeqOptimized.scala:122)
at scala.collection.immutable.List.foldLeft(List.scala:89)
at org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$1(RuleExecutor.scala:146)
at org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$1$adapted(RuleExecutor.scala:138)
at scala.collection.immutable.List.foreach(List.scala:392)
at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:138)
at org.apache.spark.sql.catalyst.analysis.Analyzer.org$apache$spark$sql$catalyst$analysis$Analyzer$$executeSameContext(Analyzer.scala:171)
at org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:165)
at org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:130)
at org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$executeAndTrack$1(RuleExecutor.scala:116)
at org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:88)
at org.apache.spark.sql.catalyst.rules.RuleExecutor.executeAndTrack(RuleExecutor.scala:116)
at org.apache.spark.sql.catalyst.analysis.Analyzer.$anonfun$executeAndCheck$1(Analyzer.scala:149)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.markInAnalyzer(AnalysisHelper.scala:219)
at org.apache.spark.sql.catalyst.analysis.Analyzer.executeAndCheck(Analyzer.scala:148)
at org.apache.spark.sql.execution.QueryExecution.$anonfun$analyzed$1(QueryExecution.scala:68)
at org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:111)
at org.apache.spark.sql.execution.QueryExecution.$anonfun$executePhase$1(QueryExecution.scala:138)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:764)
at org.apache.spark.sql.execution.QueryExecution.executePhase(QueryExecution.scala:138)
at org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:68)
at org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:66)
at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:58)
at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:764)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:97)
at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:607)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:764)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:602)
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)