我正在使用 jupyter lab 运行 spark-nlp 文本分析。目前我只是运行示例代码：
import sparknlp
from pyspark.sql import SparkSession
from sparknlp.pretrained import PretrainedPipeline
#create or get Spark Session
#spark = sparknlp.start()
spark = SparkSession.builder \
.appName("ner")\
.master("local[4]")\
.config("spark.driver.memory","8G")\
.config("spark.driver.maxResultSize", "2G") \
.config("spark.jars.packages", "com.johnsnowlabs.nlp:spark-nlp_2.11:2.6.5")\
.config("spark.kryoserializer.buffer.max", "500m")\
.getOrCreate()
print("sparknlp version", sparknlp.version(), "sparkversion", spark.version)
#download, load, and annotate a text by pre-trained pipeline
pipeline = PretrainedPipeline('recognize_entities_dl', 'en')
result = pipeline.annotate('Harry Potter is a great movie')
我收到以下错误：
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-4-bfd6884be04c> in <module>
15
16 #download, load, and annotate a text by pre-trained pipeline
---> 17 pipeline = PretrainedPipeline('recognize_entities_dl', 'en')
18 result = pipeline.annotate('Harry Potter is a great movie')
~/.pyenv/versions/3.7.9/lib/python3.7/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)
~/.pyenv/versions/3.7.9/lib/python3.7/site-packages/sparknlp/pretrained.py in downloadPipeline(name, language, remote_loc)
49 def downloadPipeline(name, language, remote_loc=None):
50 print(name + " download started this may take some time.")
---> 51 file_size = _internal._GetResourceSize(name, language, remote_loc).apply()
52 if file_size == "-1":
53 print("Can not find the model to download please check the name!")
~/.pyenv/versions/3.7.9/lib/python3.7/site-packages/sparknlp/internal.py in __init__(self, name, language, remote_loc)
190 def __init__(self, name, language, remote_loc):
191 super(_GetResourceSize, self).__init__(
--> 192 "com.johnsnowlabs.nlp.pretrained.PythonResourceDownloader.getDownloadSize", name, language, remote_loc)
193
194
~/.pyenv/versions/3.7.9/lib/python3.7/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
~/.pyenv/versions/3.7.9/lib/python3.7/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):
~/.pyenv/versions/3.7.9/lib/python3.7/site-packages/pyspark/ml/wrapper.py in _new_java_obj(java_class, *args)
67 java_obj = getattr(java_obj, name)
68 java_args = [_py2java(sc, arg) for arg in args]
---> 69 return java_obj(*java_args)
70
71 @staticmethod
TypeError: 'JavaPackage' object is not callable
我阅读了一些开发人员在 spark-nlp 存储库中提出的 github 问题，但这些修复对我不起作用。我想知道使用 pyenv 是否会导致问题，但它适用于其他一切。我的 jupyter 实验室是这样启动的：
/home/myuser/.pyenv/shims/jupyter lab --no-browser --allow-root --notebook-dir /home/myuser/workdir/notebooks
我的环境配置：
ubuntu：20.10
Apache Spark：3.0.1
pyspark：2.4.4
spark-nlp：2.6.5
pyenv：1.2.21
爪哇：
openjdk 11.0.9 2020-10-20
OpenJDK Runtime Environment (build 11.0.9+10-post-Ubuntu-0ubuntu1)
OpenJDK 64-Bit Server VM (build 11.0.9+10-post-Ubuntu-0ubuntu1, mixed mode, sharing)
朱皮特：
jupyter core : 4.7.0
jupyter-notebook : 6.1.5
qtconsole : 5.0.1
ipython : 7.19.0
ipykernel : 5.4.2
jupyter client : 6.1.7
jupyter lab : 2.2.9
nbconvert : 6.0.7
ipywidgets : 7.5.1
nbformat : 5.0.8
traitlets : 5.0.5
感谢您的帮助..谢谢