spark2.2.3 elasticsearch5.3.0

Py4JJavaError Traceback (most recent call last)
in
2 #>>> gateway = JavaGateway()
3 # write ratings data
----> 4 ratings.write.format("es").save("demo/ratings")
5 # check write went ok
6 print("Dataframe count: %d" % ratings.count())

~/es-spark-recommender/spark-2.2.3-bin-hadoop2.7/python/pyspark/sql/readwriter.py in save(self, path, format, mode, partitionBy, **options)
593 self._jwrite.save()
594 else:
--> 595 self._jwrite.save(path)
596
597 @since(1.4)

~/es-spark-recommender/spark-2.2.3-bin-hadoop2.7/python/lib/py4j-0.10.7-src.zip/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:

~/es-spark-recommender/spark-2.2.3-bin-hadoop2.7/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()

~/es-spark-recommender/spark-2.2.3-bin-hadoop2.7/python/lib/py4j-0.10.7-src.zip/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 o199.save.
: java.lang.ClassNotFoundException: Failed to find data source: es. Please find packages at http://spark.apache.org/third-party-projects.html
at org.apache.spark.sql.execution.datasources.DataSource$.lookupDataSource(DataSource.scala:546)
at org.apache.spark.sql.execution.datasources.DataSource.providingClass$lzycompute(DataSource.scala:87)
at org.apache.spark.sql.execution.datasources.DataSource.providingClass(DataSource.scala:87)
at org.apache.spark.sql.execution.datasources.DataSource.write(DataSource.scala:467)
at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:48)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:92)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:92)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:609)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:233)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:217)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:483)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.ClassNotFoundException: es.DefaultSource
at java.net.URLClassLoader$1.run(URLClassLoader.java:372)
at java.net.URLClassLoader$1.run(URLClassLoader.java:361)
at java.security.AccessController.doPrivileged(Native Method)
at java.net.URLClassLoader.findClass(URLClassLoader.java:360)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$22$$anonfun$apply$14.apply(DataSource.scala:530)
at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$22$$anonfun$apply$14.apply(DataSource.scala:530)
at scala.util.Try$.apply(Try.scala:192)
at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$22.apply(DataSource.scala:530)
at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$22.apply(DataSource.scala:530)
at scala.util.Try.orElse(Try.scala:84)
at org.apache.spark.sql.execution.datasources.DataSource$.lookupDataSource(DataSource.scala:530)
... 29 more

Start with the reported ratings.write.format("es").save("demo/ratings") call and the Py4JJavaError showing ClassNotFoundException for es.DefaultSource. Check whether this failure belongs to Jupyter Notebook or to the Spark/Elasticsearch environment; done means reproducing it or narrowing it to an actionable notebook issue.

Written by the indexing model from the issue text.