2

我正在尝试使用 python 在 windows 10 中的 spark-nlp 中安装预训练管道。以下是我目前在本地系统的 Jupyter notebook 中尝试过的代码:

! java -version
# should be Java 8 (Oracle or OpenJDK)
! conda create -n sparknlp python=3.7 -y
! conda activate sparknlp
! pip install --user spark-nlp==2.6.4 pyspark==2.4.5


from sparknlp.base import *
from sparknlp.annotator import *
from sparknlp.pretrained import PretrainedPipeline
import sparknlp

# Start Spark Session with Spark NLP
# start() functions has two parameters: gpu and spark23
# sparknlp.start(gpu=True) will start the session with GPU support
# sparknlp.start(sparrk23=True) is when you have Apache Spark 2.3.x installed
spark = sparknlp.start()

# Download a pre-trained pipeline
pipeline = PretrainedPipeline('explain_document_ml', lang='en')

我收到以下错误:

explain_document_ml download started this may take some time.
Approx size to download 9.4 MB
[OK!]
---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
~\AppData\Roaming\Python\Python37\site-packages\pyspark\sql\utils.py in deco(*a, **kw)
     62         try:
---> 63             return f(*a, **kw)
     64         except py4j.protocol.Py4JJavaError as e:

~\Anaconda3\envs\py37\lib\site-packages\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 z:com.johnsnowlabs.nlp.pretrained.PythonResourceDownloader.downloadPipeline.
: java.lang.IllegalArgumentException: requirement failed: Was not found appropriate resource to download for request: ResourceRequest(explain_document_ml,Some(en),public/models,2.6.4,2.4.4) with downloader: com.johnsnowlabs.nlp.pretrained.S3ResourceDownloader@2570f26e
    at scala.Predef$.require(Predef.scala:224)
    at com.johnsnowlabs.nlp.pretrained.ResourceDownloader$.downloadResource(ResourceDownloader.scala:345)
    at com.johnsnowlabs.nlp.pretrained.ResourceDownloader$.downloadPipeline(ResourceDownloader.scala:376)
    at com.johnsnowlabs.nlp.pretrained.ResourceDownloader$.downloadPipeline(ResourceDownloader.scala:371)
    at com.johnsnowlabs.nlp.pretrained.PythonResourceDownloader$.downloadPipeline(ResourceDownloader.scala:474)
    at com.johnsnowlabs.nlp.pretrained.PythonResourceDownloader.downloadPipeline(ResourceDownloader.scala)
    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)


During handling of the above exception, another exception occurred:

IllegalArgumentException                  Traceback (most recent call last)
<ipython-input-2-d18238e76d9f> in <module>
     11 
     12 # Download a pre-trained pipeline
---> 13 pipeline = PretrainedPipeline('explain_document_ml', lang='en')

~\Anaconda3\envs\py37\lib\site-packages\sparknlp\pretrained.py in __init__(self, name, lang, remote_loc, parse_embeddings, disk_location)
     89     def __init__(self, name, lang='en', remote_loc=None, parse_embeddings=False, disk_location=None):
     90         if not disk_location:
---> 91             self.model = ResourceDownloader().downloadPipeline(name, lang, remote_loc)
     92         else:
     93             self.model = PipelineModel.load(disk_location)

~\Anaconda3\envs\py37\lib\site-packages\sparknlp\pretrained.py in downloadPipeline(name, language, remote_loc)
     58             t1.start()
     59             try:
---> 60                 j_obj = _internal._DownloadPipeline(name, language, remote_loc).apply()
     61                 jmodel = PipelineModel._from_java(j_obj)
     62             finally:

~\Anaconda3\envs\py37\lib\site-packages\sparknlp\internal.py in __init__(self, name, language, remote_loc)
    179 class _DownloadPipeline(ExtendedJavaWrapper):
    180     def __init__(self, name, language, remote_loc):
--> 181         super(_DownloadPipeline, self).__init__("com.johnsnowlabs.nlp.pretrained.PythonResourceDownloader.downloadPipeline", name, language, remote_loc)
    182 
    183 

~\Anaconda3\envs\py37\lib\site-packages\sparknlp\internal.py in __init__(self, java_obj, *args)
    127         super(ExtendedJavaWrapper, self).__init__(java_obj)
    128         self.sc = SparkContext._active_spark_context
--> 129         self._java_obj = self.new_java_obj(java_obj, *args)
    130         self.java_obj = self._java_obj
    131 

~\Anaconda3\envs\py37\lib\site-packages\sparknlp\internal.py in new_java_obj(self, java_class, *args)
    137 
    138     def new_java_obj(self, java_class, *args):
--> 139         return self._new_java_obj(java_class, *args)
    140 
    141     def new_java_array(self, pylist, java_class):

~\AppData\Roaming\Python\Python37\site-packages\pyspark\ml\wrapper.py in _new_java_obj(java_class, *args)
     65             java_obj = getattr(java_obj, name)
     66         java_args = [_py2java(sc, arg) for arg in args]
---> 67         return java_obj(*java_args)
     68 
     69     @staticmethod

~\Anaconda3\envs\py37\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:

~\AppData\Roaming\Python\Python37\site-packages\pyspark\sql\utils.py in deco(*a, **kw)
     77                 raise QueryExecutionException(s.split(': ', 1)[1], stackTrace)
     78             if s.startswith('java.lang.IllegalArgumentException: '):
---> 79                 raise IllegalArgumentException(s.split(': ', 1)[1], stackTrace)
     80             raise
     81     return deco

IllegalArgumentException: 'requirement failed: Was not found appropriate resource to download for request: ResourceRequest(explain_document_ml,Some(en),public/models,2.6.4,2.4.4) with downloader: com.johnsnowlabs.nlp.pretrained.S3ResourceDownloader@2570f26e'

4

1 回答 1

3

当 Java/Spark/Hadoop 未在 Windows 上正确设置时,这是 Apache Spark 和 Spark NLP 的常见问题之一:

您需要正确执行以下步骤以避免常见问题,包括 pretrained() 下载失败:

要么为 python 3.6 创建一个 conda 环境,安装pyspark==2.4.6 spark-nlp numpy和使用 Jupyter/python 控制台,要么在同一个 conda 环境中,你可以去 spark bin for pyspark --packages com.johnsnowlabs.nlp:spark-nlp_2.11:2.6.5.

图片

图片

图片

图片

于 2020-11-29T13:29:01.870 回答