I have followed this post pyspark error reading bigquery: java.lang.ClassNotFoundException: org.apache.spark.internal.Logging$class
and followed the resolution provided but still getting the same error. Please help.
I am trying to run this using Jupyter lab created using data proc cluster in GCP.
I am using Python 3 kernel (not PySpark) to allow you to configure the SparkSession in the notebook and include the spark-bigquery-connector required to use the BigQuery Storage API.
!scala -version
scala version is Scala code runner version 2.11.12 -- Copyright 2002-2017, LAMP/EPFL
from pyspark.sql import SparkSession
spark = SparkSession.builder \
.appName('1.2. BigQuery Storage & Spark SQL - Python')\
.config('spark.jars', 'gs://spark-lib/bigquery/spark-bigquery-latest_2.12.jar')\
.config("viewsEnabled","true")\
.getOrCreate()
spark.conf.set("spark.sql.repl.eagerEval.enabled",True)
df = spark.read \
.format('bigquery') \
.option('table', 'table_name') \
.load()
below is the error, i am getting
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-30-bcc65722cf80> in <module>
1 df = spark.read \
2 .format('bigquery') \
----> 3 .option('table', 'wmt-rdl-stage.dim_tables.store_dim') \
4 .load()
/usr/lib/spark/python/pyspark/sql/readwriter.py in load(self, path, format, schema, **options)
170 return self._df(self._jreader.load(self._spark._sc._jvm.PythonUtils.toSeq(path)))
171 else:
--> 172 return self._df(self._jreader.load())
173
174 @since(1.4)
/opt/conda/anaconda/lib/python3.6/site-packages/py4j/java_gateway.py in __call__(self, *args)
1255 answer = self.gateway_client.send_command(command)
1256 return_value = get_return_value(
-> 1257 answer, self.gateway_client, self.target_id, self.name)
1258
1259 for temp_arg in temp_args:
/usr/lib/spark/python/pyspark/sql/utils.py in deco(*a, **kw)
61 def deco(*a, **kw):
62 try:
---> 63 return f(*a, **kw)
64 except py4j.protocol.Py4JJavaError as e:
65 s = e.java_exception.toString()
/opt/conda/anaconda/lib/python3.6/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 o411.load.
: java.util.ServiceConfigurationError: org.apache.spark.sql.sources.DataSourceRegister: Provider com.google.cloud.spark.bigquery.BigQueryRelationProvider could not be instantiated
at java.util.ServiceLoader.fail(ServiceLoader.java:232)
at java.util.ServiceLoader.access$100(ServiceLoader.java:185)
at java.util.ServiceLoader$LazyIterator.nextService(ServiceLoader.java:384)
at java.util.ServiceLoader$LazyIterator.next(ServiceLoader.java:404)
at java.util.ServiceLoader$1.next(ServiceLoader.java:480)
at scala.collection.convert.Wrappers$JIteratorWrapper.next(Wrappers.scala:43)
at scala.collection.Iterator$class.foreach(Iterator.scala:891)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1334)
at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
at scala.collection.AbstractIterable.foreach(Iterable.scala:54)
at scala.collection.TraversableLike$class.filterImpl(TraversableLike.scala:247)
at scala.collection.TraversableLike$class.filter(TraversableLike.scala:259)
at scala.collection.AbstractTraversable.filter(Traversable.scala:104)
at org.apache.spark.sql.execution.datasources.DataSource$.lookupDataSource(DataSource.scala:630)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:194)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:167)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.lang.NoClassDefFoundError: Could not initialize class com.google.cloud.spark.bigquery.BigQueryUtilScala$
at com.google.cloud.spark.bigquery.BigQueryRelationProvider.<init>(BigQueryRelationProvider.scala:42)
at com.google.cloud.spark.bigquery.BigQueryRelationProvider.<init>(BigQueryRelationProvider.scala:49)
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:423)
at java.lang.Class
.newInstance(Class.java:442) at java.util.Se
CodePudding user response:
Please switch to gs://spark-lib/bigquery/spark-bigquery-latest_2.11.jar
. The number after the _
is the Scala binary version.