PySpark MongoDB::java.lang.NoClassDefFoundError:com/MongoDB/client/model/Collation

PySpark MongoDB::java.lang.NoClassDefFoundError:com/MongoDB/client/model/Collation,mongodb,apache-spark,pyspark,Mongodb,Apache Spark,Pyspark,我试图从PySpark连接到MongoDB Atlas,但出现以下问题: from pyspark import SparkContext from pyspark.sql import SparkSession from pyspark.sql.types import * from pyspark.sql.functions import * sc = SparkContext spark = SparkSession.builder \ .config("spark.m

我试图从PySpark连接到MongoDB Atlas,但出现以下问题:

from pyspark import SparkContext
from pyspark.sql import SparkSession
from pyspark.sql.types import *
from pyspark.sql.functions import *

sc = SparkContext

spark = SparkSession.builder \
        .config("spark.mongodb.input.uri", "mongodb+srv://#USER#:#PASS#@test00-la3lt.mongodb.net/db.BUSQUEDAS?retryWrites=true") \
        .config("spark.mongodb.output.uri", "mongodb+srv://#USER#:#PASS#@test00-la3lt.mongodb.net/db.BUSQUEDAS?retryWrites=true") \
        .getOrCreate()

df = spark.read.format("com.mongodb.spark.sql.DefaultSource").load()
返回此代码的错误如下:

---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
<ipython-input-3-346df2de8d22> in <module>()
----> 1 df = spark.read.format("com.mongodb.spark.sql.DefaultSource").load()

c:\users\andres\appdata\local\programs\python\python36\lib\site-packages\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)

c:\users\andres\appdata\local\programs\python\python36\lib\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:

c:\users\andres\appdata\local\programs\python\python36\lib\site-packages\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()

c:\users\andres\appdata\local\programs\python\python36\lib\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 o34.load.
: java.lang.NoClassDefFoundError: com/mongodb/client/model/Collation
    at com.mongodb.spark.config.ReadConfig$.<init>(ReadConfig.scala:50)
    at com.mongodb.spark.config.ReadConfig$.<clinit>(ReadConfig.scala)
    at com.mongodb.spark.sql.DefaultSource.createRelation(DefaultSource.scala:67)
    at com.mongodb.spark.sql.DefaultSource.createRelation(DefaultSource.scala:50)
    at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:340)
    at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:239)
    at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:227)
    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.mongodb.client.model.Collation

Spark版本为2.3.1,Scala版本为2.11.8。出现此错误的原因是因为有必要添加以下参考:


当我添加这个时,问题就解决了

你能分享一下你是如何写推荐信的吗?你必须将那些罐子添加到你的spark/jars/文件夹中,这会起作用的。这对我帮助很大!如果任何人在使用pyspark时遇到“classnotfound”或“nosuchmethod”错误,请执行此操作。如果您有上述文件的任何其他版本,请尝试改用这些版本。非常感谢,但是您是如何找到这些丢失的jar文件的,比如在哪里以及如何获得搜索它们的提示?可能对未来有所帮助。奇怪的是Mongo没有将这些依赖项与连接器jar一起提供。
./bin/pyspark --conf "spark.mongodb.input.uri=mongodb+srv://#USER#:#PASS#@test00-la3lt.mongodb.net/db.BUSQUEDAS?readPreference=primaryPreferred" \
--conf "spark.mongodb.output.uri=mongodb+srv://#USER#:#PASS#@test00-la3lt.mongodb.net/db.BUSQUEDAS" \
--packages org.mongodb.spark:mongo-spark-connector_2.11:2.1.3