Ошибка при попытке создать Doc при помощи textacy для русского языка
Я занимаюсь NLP. Я пытаюсь через textacy обработать русскоязычный документ с помощью команды: doc = textacy.make_spacy_doc(text, lang="ru_core_news_md") получаю следующую ошибку:
Input In [8], in <cell line: 1>() ----> 1 doc = textacy.make_spacy_doc(text, lang="ru_core_news_md")
File ~/anaconda3/envs/Mosoblgas/lib/python3.10/site-packages/textacy/spacier/core.py:150, in make_spacy_doc(data, lang) 82 """ 83 Make a :class:
spacy.tokens.Docfrom valid inputs, and automatically 84 load/validate :class:spacy.language.Languagepipelines to processdata. (...) 147 ValueError 148 """ 149 if isinstance(data, str): --> 150 return _make_spacy_doc_from_text(data, lang) 151 elif isinstance(data, spacy.tokens.Doc): 152 return _make_spacy_doc_from_doc(data, lang)File ~/anaconda3/envs/Mosoblgas/lib/python3.10/site-packages/textacy/spacier/core.py:169, in _make_spacy_doc_from_text(text, lang) 164 def _make_spacy_doc_from_text( 165 text: str, 166 lang: Union[str, Callable[[str], str], Language], 167 ) -> Doc: 168 if isinstance(lang, str): --> 169 spacy_lang = load_spacy_lang(lang) 170 langstr = spacy_lang.lang 171 elif isinstance(lang, spacy.language.Language):
File ~/anaconda3/envs/Mosoblgas/lib/python3.10/site-packages/cachetools/init.py:644, in cached..decorator..wrapper(*args, **kwargs) 642 v = func(*args, **kwargs) 643 try: --> 644 cache[k] = v 645 except ValueError: 646 pass # value too large
File ~/anaconda3/envs/Mosoblgas/lib/python3.10/site-packages/cachetools/init.py:221, in LRUCache.setitem(self, key, value, cache_setitem) 220 def setitem(self, key, value, cache_setitem=Cache.setitem): --> 221 cache_setitem(self, key, value) 222 self.__update(key)
File ~/anaconda3/envs/Mosoblgas/lib/python3.10/site-packages/cachetools/init.py:78, in Cache.setitem(self, key, value) 76 def setitem(self, key, value): 77 maxsize = self.__maxsize ---> 78 size = self.getsizeof(value) 79 if size > maxsize: 80 raise ValueError("value too large")
File ~/anaconda3/envs/Mosoblgas/lib/python3.10/site-packages/textacy/cache.py:35, in _get_size(obj, seen) 33 d = cls.dict["dict"] 34 if inspect.isgetsetdescriptor(d) or inspect.ismemberdescriptor(d): ---> 35 size += _get_size(obj.dict, seen) 36 break 37 if isinstance(obj, dict):
File ~/anaconda3/envs/Mosoblgas/lib/python3.10/site-packages/textacy/cache.py:38, in _get_size(obj, seen) 36 break 37 if isinstance(obj, dict): ---> 38 size += sum((_get_size(v, seen) for v in obj.values())) 39 size += sum((_get_size(k, seen) for k in obj.keys())) 40 elif hasattr(obj, "iter") and not isinstance(obj, (str, bytes, bytearray)):
File ~/anaconda3/envs/Mosoblgas/lib/python3.10/site-packages/textacy/cache.py:38, in (.0) 36 break 37 if isinstance(obj, dict): ---> 38 size += sum((_get_size(v, seen) for v in obj.values())) 39 size += sum((_get_size(k, seen) for k in obj.keys())) 40 elif hasattr(obj, "iter") and not isinstance(obj, (str, bytes, bytearray)):
File ~/anaconda3/envs/Mosoblgas/lib/python3.10/site-packages/textacy/cache.py:41, in _get_size(obj, seen) 39 size += sum((_get_size(k, seen) for k in obj.keys())) 40 elif hasattr(obj, "iter") and not isinstance(obj, (str, bytes, bytearray)): ---> 41 size += sum((_get_size(i, seen) for i in obj)) 42 return size
File ~/anaconda3/envs/Mosoblgas/lib/python3.10/site-packages/textacy/cache.py:41, in (.0) 39 size += sum((_get_size(k, seen) for k in obj.keys())) 40 elif hasattr(obj, "iter") and not isinstance(obj, (str, bytes, bytearray)): ---> 41 size += sum((_get_size(i, seen) for i in obj)) 42 return size
File ~/anaconda3/envs/Mosoblgas/lib/python3.10/site-packages/textacy/cache.py:41, in _get_size(obj, seen) 39 size += sum((_get_size(k, seen) for k in obj.keys())) 40 elif hasattr(obj, "iter") and not isinstance(obj, (str, bytes, bytearray)): ---> 41 size += sum((_get_size(i, seen) for i in obj)) 42 return size
File ~/anaconda3/envs/Mosoblgas/lib/python3.10/site-packages/textacy/cache.py:41, in (.0) 39 size += sum((_get_size(k, seen) for k in obj.keys())) 40 elif hasattr(obj, "iter") and not isinstance(obj, (str, bytes, bytearray)): ---> 41 size += sum((_get_size(i, seen) for i in obj)) 42 return size
File ~/anaconda3/envs/Mosoblgas/lib/python3.10/site-packages/textacy/cache.py:35, in _get_size(obj, seen) 33 d = cls.dict["dict"] 34 if inspect.isgetsetdescriptor(d) or inspect.ismemberdescriptor(d): ---> 35 size += _get_size(obj.dict, seen) 36 break 37 if isinstance(obj, dict):
File ~/anaconda3/envs/Mosoblgas/lib/python3.10/site-packages/textacy/cache.py:38, in _get_size(obj, seen) 36 break 37 if isinstance(obj, dict): ---> 38 size += sum((_get_size(v, seen) for v in obj.values())) 39 size += sum((_get_size(k, seen) for k in obj.keys())) 40 elif hasattr(obj, "iter") and not isinstance(obj, (str, bytes, bytearray)):
File ~/anaconda3/envs/Mosoblgas/lib/python3.10/site-packages/textacy/cache.py:38, in (.0) 36 break 37 if isinstance(obj, dict): ---> 38 size += sum((_get_size(v, seen) for v in obj.values())) 39 size += sum((_get_size(k, seen) for k in obj.keys())) 40 elif hasattr(obj, "iter") and not isinstance(obj, (str, bytes, bytearray)):
File ~/anaconda3/envs/Mosoblgas/lib/python3.10/site-packages/textacy/cache.py:35, in _get_size(obj, seen) 33 d = cls.dict["dict"] 34 if inspect.isgetsetdescriptor(d) or inspect.ismemberdescriptor(d): ---> 35 size += _get_size(obj.dict, seen) 36 break 37 if isinstance(obj, dict):
File ~/anaconda3/envs/Mosoblgas/lib/python3.10/site-packages/textacy/cache.py:38, in _get_size(obj, seen) 36 break 37 if isinstance(obj, dict): ---> 38 size += sum((_get_size(v, seen) for v in obj.values())) 39 size += sum((_get_size(k, seen) for k in obj.keys())) 40 elif hasattr(obj, "iter") and not isinstance(obj, (str, bytes, bytearray)):
File ~/anaconda3/envs/Mosoblgas/lib/python3.10/site-packages/textacy/cache.py:38, in (.0) 36 break 37 if isinstance(obj, dict): ---> 38 size += sum((_get_size(v, seen) for v in obj.values())) 39 size += sum((_get_size(k, seen) for k in obj.keys())) 40 elif hasattr(obj, "iter") and not isinstance(obj, (str, bytes, bytearray)):
File ~/anaconda3/envs/Mosoblgas/lib/python3.10/site-packages/textacy/cache.py:41, in _get_size(obj, seen) 39 size += sum((_get_size(k, seen) for k in obj.keys())) 40 elif hasattr(obj, "iter") and not isinstance(obj, (str, bytes, bytearray)): ---> 41 size += sum((_get_size(i, seen) for i in obj)) 42 return size
TypeError: 'type' object is not iterable
python - Python 3.10.4 spacy - 3.3.0 ru-core-news-md 3- .3.0 textacy - 0.10.0 В чем может быть проблема?