[Python] Py4JJavaError: Using Pyspark in Jupyter notebook trying to run examples using "spark."

Discussão em 'Python' iniciado por Stack, Julho 12, 2025.

  1. Stack

    Stack Membro Participativo

    I'm trying to run the examples (for example spark/examples/src/main/python/ml/fpgrowth_example.py) for PySpark in Jupyter notebook. However, I am getting exceptions any time I try to do "spark.(some function)" In the case of this example, it is spark.createDataFrame, but I have also tried spark.read and it resulted in the same exception. I have also tried creating my own sparkSession, and using the one that is already in Jupyter notebook on start, and neither worked correctly. The main excpetion I can find is AnalysisException: 'java.lang.RuntimeException: java.lang.RuntimeException: Unable to instantiate org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient;'

    Code:

    # $example on$
    from pyspark.ml.fpm import FPGrowth
    # $example off$
    from pyspark.sql import SparkSession

    if __name__ == "__main__":
    spark = SparkSession\
    .builder\
    .appName("FPGrowthExample")\
    .getOrCreate()

    # $example on$
    df = spark.createDataFrame([
    (0, [1, 2, 5]),
    (1, [1, 2, 3, 5]),
    (2, [1, 2])
    ], ["id", "items"])


    Exception:


    AnalysisException Traceback (most recent call last)
    <ipython-input-2-512249e97d93> in <module>()
    3 (1, [1, 2, 3, 5]),
    4 (2, [1, 2])
    ----> 5 ], ["id", "items"])

    D:\spark\spark-2.3.1-bin-hadoop2.7\python\pyspark\sql\session.py in createDataFrame(self, data, schema, samplingRatio, verifySchema)
    691 rdd, schema = self._createFromLocal(map(prepare, data), schema)
    692 jrdd = self._jvm.SerDeUtil.toJavaArray(rdd._to_java_object_rdd())
    --> 693 jdf = self._jsparkSession.applySchemaToPythonRDD(jrdd.rdd(), schema.json())
    694 df = DataFrame(jdf, self._wrapped)
    695 df._schema = schema

    D:\spark\spark-2.3.1-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:

    D:\spark\spark-2.3.1-bin-hadoop2.7\python\pyspark\sql\utils.py in deco(*a, **kw)
    67 e.java_exception.getStackTrace()))
    68 if s.startswith('org.apache.spark.sql.AnalysisException: '):
    ---> 69 raise AnalysisException(s.split(': ', 1)[1], stackTrace)
    70 if s.startswith('org.apache.spark.sql.catalyst.analysis'):
    71 raise AnalysisException(s.split(': ', 1)[1], stackTrace)

    AnalysisException: 'java.lang.RuntimeException: java.lang.RuntimeException: Unable to instantiate org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient;'
    ---------------------------------------------------------------------------
    Py4JJavaError Traceback (most recent call last)
    D:\spark\spark-2.3.1-bin-hadoop2.7\python\pyspark\sql\utils.py in deco(*a, **kw)
    62 try:
    ---> 63 return f(*a, **kw)
    64 except py4j.protocol.Py4JJavaError as e:

    D:\spark\spark-2.3.1-bin-hadoop2.7\python\lib\py4j-0.10.7-src.zip\py4j\protocol.py in get_return_value(answer, gateway_client, target_id, name)
    327 "An error occurred while calling {0}{1}{2}.\n".
    --> 328 format(target_id, ".", name), value)
    329 else:

    Py4JJavaError: An error occurred while calling o24.applySchemaToPythonRDD.
    : org.apache.spark.sql.AnalysisException: java.lang.RuntimeException: java.lang.RuntimeException: Unable to instantiate org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient;
    at org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:106)
    at org.apache.spark.sql.hive.HiveExternalCatalog.databaseExists(HiveExternalCatalog.scala:194)
    at org.apache.spark.sql.internal.SharedState.externalCatalog$lzycompute(SharedState.scala:114)
    at org.apache.spark.sql.internal.SharedState.externalCatalog(SharedState.scala:102)
    at org.apache.spark.sql.hive.HiveSessionStateBuilder.externalCatalog(HiveSessionStateBuilder.scala:39)
    at org.apache.spark.sql.hive.HiveSessionStateBuilder.catalog$lzycompute(HiveSessionStateBuilder.scala:54)
    at org.apache.spark.sql.hive.HiveSessionStateBuilder.catalog(HiveSessionStateBuilder.scala:52)
    at org.apache.spark.sql.hive.HiveSessionStateBuilder$$anon$1.<init>(HiveSessionStateBuilder.scala:69)
    at org.apache.spark.sql.hive.HiveSessionStateBuilder.analyzer(HiveSessionStateBuilder.scala:69)
    at org.apache.spark.sql.internal.BaseSessionStateBuilder$$anonfun$build$2.apply(BaseSessionStateBuilder.scala:293)
    at org.apache.spark.sql.internal.BaseSessionStateBuilder$$anonfun$build$2.apply(BaseSessionStateBuilder.scala:293)
    at org.apache.spark.sql.internal.SessionState.analyzer$lzycompute(SessionState.scala:79)
    at org.apache.spark.sql.internal.SessionState.analyzer(SessionState.scala:79)
    at org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:57)
    at org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:55)
    at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:47)
    at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:74)
    at org.apache.spark.sql.SparkSession.internalCreateDataFrame(SparkSession.scala:577)
    at org.apache.spark.sql.SparkSession.applySchemaToPythonRDD(SparkSession.scala:752)
    at org.apache.spark.sql.SparkSession.applySchemaToPythonRDD(SparkSession.scala:737)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
    at java.lang.reflect.Method.invoke(Unknown Source)
    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(Unknown Source)
    Caused by: java.lang.RuntimeException: java.lang.RuntimeException: Unable to instantiate org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient
    at org.apache.hadoop.hive.ql.session.SessionState.start(SessionState.java:522)
    at org.apache.spark.sql.hive.client.HiveClientImpl.newState(HiveClientImpl.scala:180)
    at org.apache.spark.sql.hive.client.HiveClientImpl.<init>(HiveClientImpl.scala:114)
    at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
    at sun.reflect.NativeConstructorAccessorImpl.newInstance(Unknown Source)
    at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(Unknown Source)
    at java.lang.reflect.Constructor.newInstance(Unknown Source)
    at org.apache.spark.sql.hive.client.IsolatedClientLoader.createClient(IsolatedClientLoader.scala:264)
    at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:385)
    at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:287)
    at org.apache.spark.sql.hive.HiveExternalCatalog.client$lzycompute(HiveExternalCatalog.scala:66)
    at org.apache.spark.sql.hive.HiveExternalCatalog.client(HiveExternalCatalog.scala:65)
    at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$databaseExists$1.apply$mcZ$sp(HiveExternalCatalog.scala:195)
    at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$databaseExists$1.apply(HiveExternalCatalog.scala:195)
    at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$databaseExists$1.apply(HiveExternalCatalog.scala:195)
    at org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:97)
    ... 30 more
    Caused by: java.lang.RuntimeException: Unable to instantiate org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient
    at org.apache.hadoop.hive.metastore.MetaStoreUtils.newInstance(MetaStoreUtils.java:1523)
    at org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.<init>(RetryingMetaStoreClient.java:86)
    at org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.getProxy(RetryingMetaStoreClient.java:132)
    at org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.getProxy(RetryingMetaStoreClient.java:104)
    at org.apache.hadoop.hive.ql.metadata.Hive.createMetaStoreClient(Hive.java:3005)
    at org.apache.hadoop.hive.ql.metadata.Hive.getMSC(Hive.java:3024)
    at org.apache.hadoop.hive.ql.session.SessionState.start(SessionState.java:503)
    ... 45 more
    Caused by: java.lang.reflect.InvocationTargetException
    at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
    at sun.reflect.NativeConstructorAccessorImpl.newInstance(Unknown Source)
    at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(Unknown Source)
    at java.lang.reflect.Constructor.newInstance(Unknown Source)
    at org.apache.hadoop.hive.metastore.MetaStoreUtils.newInstance(MetaStoreUtils.java:1521)
    ... 51 more​

    Continue reading...

Compartilhe esta Página