Невозможно загрузить файл JSON в коалах, ошибка при получении соединения отклонена - PullRequest
1 голос
/ 06 января 2020

Описание проблемы

Я попытался загрузить файл JSON, используя koalas, но соединение сбрасывает, из-за ошибки отказано. Может кто-нибудь помочь мне разобраться в проблеме, если я что-то здесь упустил?

Версии пакета

Pyspark : '2.4.3'
koalas: '0.19.0'
Python : Python 3.6.9 :: Anaconda, Inc.

Фрагмент кода

import databricks.koalas as ks
data = ks.read_json('dataset/mydata.json')
data.head()

Ошибка

ERROR:py4j.java_gateway:An error occurred while trying to connect to the Java server (127.0.0.1:50306)
Traceback (most recent call last):
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/py4j/java_gateway.py", line 929, in _get_connection
    connection = self.deque.pop()
IndexError: pop from an empty deque

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/py4j/java_gateway.py", line 1067, in start
    self.socket.connect((self.address, self.port))
ConnectionRefusedError: [Errno 61] Connection refused
---------------------------------------------------------------------------
IndexError                                Traceback (most recent call last)
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/py4j/java_gateway.py in _get_connection(self)
    928         try:
--> 929             connection = self.deque.pop()
    930         except IndexError:

IndexError: pop from an empty deque

During handling of the above exception, another exception occurred:

ConnectionRefusedError                    Traceback (most recent call last)
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/py4j/java_gateway.py in start(self)
   1066         try:
-> 1067             self.socket.connect((self.address, self.port))
   1068             self.stream = self.socket.makefile("rb")

ConnectionRefusedError: [Errno 61] Connection refused

During handling of the above exception, another exception occurred:

Py4JNetworkError                          Traceback (most recent call last)
<ipython-input-7-06373fe8f71d> in <module>
----> 1 job = ks.read_json('data/job/job_tenant_ingersollauto_0.json')
      2 job.head()

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/databricks/koalas/namespace.py in read_json(path, index_col, **options)
    282     1     c     d
    283     """
--> 284     return read_spark_io(path, format='json', index_col=index_col, options=options)
    285 
    286 

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/databricks/koalas/namespace.py in read_spark_io(path, format, schema, index_col, **options)
    411     0   0
    412     """
--> 413     sdf = default_session().read.load(path=path, format=format, schema=schema, options=options)
    414     index_map = _get_index_map(sdf, index_col)
    415 

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/databricks/koalas/utils.py in default_session(conf)
    267     for key, value in conf.items():
    268         builder = builder.config(key, value)
--> 269     return builder.getOrCreate()
    270 
    271 

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/pyspark/sql/session.py in getOrCreate(self)
    181                     session = SparkSession(sc)
    182                 for key, value in self._options.items():
--> 183                     session._jsparkSession.sessionState().conf().setConfString(key, value)
    184                 for key, value in self._options.items():
    185                     session.sparkContext._conf.set(key, value)

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/py4j/java_gateway.py in __call__(self, *args)
   1253             proto.END_COMMAND_PART
   1254 
-> 1255         answer = self.gateway_client.send_command(command)
   1256         return_value = get_return_value(
   1257             answer, self.gateway_client, self.target_id, self.name)

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/py4j/java_gateway.py in send_command(self, command, retry, binary)
    981          if `binary` is `True`.
    982         """
--> 983         connection = self._get_connection()
    984         try:
    985             response = connection.send_command(command)

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/py4j/java_gateway.py in _get_connection(self)
    929             connection = self.deque.pop()
    930         except IndexError:
--> 931             connection = self._create_connection()
    932         return connection
    933 

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/py4j/java_gateway.py in _create_connection(self)
    935         connection = GatewayConnection(
    936             self.gateway_parameters, self.gateway_property)
--> 937         connection.start()
    938         return connection
    939 

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/py4j/java_gateway.py in start(self)
   1077                 "server ({0}:{1})".format(self.address, self.port)
   1078             logger.exception(msg)
-> 1079             raise Py4JNetworkError(msg, e)
   1080 
   1081     def _authenticate_connection(self):

Py4JNetworkError: An error occurred while trying to connect to the Java server (127.0.0.1:50306)
...