Error while loading data from BigQuery table to Dataproc cluster - hadoop

Question

I'm new to Dataproc and PySpark and facing certain issues while integrating BigQuery table to Dataproc cluster via Jupyter Lab API. Below is the code that I used for loading BigQuery table to the Dataproc cluster through Jupyter Notebook API but I am getting an error while loading the table
from pyspark.sql import SparkSession
SparkSession.builder.appName('Jupyter BigQuery Storage').config(
'spark.jars', 'gs://spark-lib/bigquery/spark-bigquery-latest.jar').getOrCreate()
df=spark.read.format("com.google.cloud.spark.bigquery").option(
"table", "publicdata.samples.shakespeare").load()
df.printSchema()
Below, is the error I'm getting
Py4JJavaErrorTraceback (most recent call last)
<ipython-input-17-789ad67053e5> in <module>()
1 table = "publicdata.samples.shakespeare"
----> 2 df = spark.read.format("com.google.cloud.spark.bigquery").option("table",table).load()
3 df.printSchema()
/usr/lib/spark/python/pyspark/sql/readwriter.pyc 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/python2.7/site-packages/py4j/java_gateway.pyc 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.pyc 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/python2.7/site-packages/py4j/protocol.pyc 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 o254.load.
: java.lang.ClassNotFoundException: Failed to find data source: com.google.cloud.spark.bigquery. Please find packages at http://spark.apache.org/third-party-projects.html
at org.apache.spark.sql.execution.datasources.DataSource$.lookupDataSource(DataSource.scala:639)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:190)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:164)
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.ClassNotFoundException: com.google.cloud.spark.bigquery.DefaultSource
at java.net.URLClassLoader.findClass(URLClassLoader.java:382)
at java.lang.ClassLoader.loadClass(ClassLoader.java:418)
at java.lang.ClassLoader.loadClass(ClassLoader.java:351)
at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$23$$anonfun$apply$15.apply(DataSource.scala:622)
at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$23$$anonfun$apply$15.apply(DataSource.scala:622)
at scala.util.Try$.apply(Try.scala:192)
at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$23.apply(DataSource.scala:622)
at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$23.apply(DataSource.scala:622)
at scala.util.Try.orElse(Try.scala:84)
at org.apache.spark.sql.execution.datasources.DataSource$.lookupDataSource(DataSource.scala:622)
... 13 more```

Answer 1

Please assign the SparkSession.builder result to a variable:
spark = SparkSession.builder\
.appName('Jupyter BigQuery Storage')\
.config('spark.jars', 'gs://spark-lib/bigquery/spark-bigquery-latest.jar')\
.getOrCreate()
Also, the reference to the public datasets is bigquery-public-data, so please change the reading to
df = spark.read.format("com.google.cloud.spark.bigquery")\
.option("table", "bigquery-public-data.samples.shakespeare")\
.load()