Токенизация работает нормально, но когда я пытаюсь выполнить распознавание именованных сущностей namedEnt = ne_chunk (tagged, binary = True)
, появляется следующая ошибка. Я установил NumPy из cmd с помощью pip install numpy, но все равно выдает ошибку
import nltk
from nltk.corpus import state_union
from nltk.tokenize import PunktSentenceTokenizer, word_tokenize
from nltk.chunk import ne_chunk
train_text = state_union.raw("2005-GWBush.txt")
sample_text = state_union.raw("2006-GWBush.txt")
# print(train_text)
custom_sent_tokenizer = PunktSentenceTokenizer(train_text)
tokenized = custom_sent_tokenizer.tokenize(sample_text)
def process_content():
for i in tokenized:
words = word_tokenize(i)
tagged = nltk.pos_tag(words)
namedEnt = ne_chunk(tagged, binary=True)
print(namedEnt)
process_content()
Ошибка:
PS D:\Python\nltk> & C:/Users/Talha/AppData/Local/Programs/Python/Python37/python.exe d:/Python/nltk/nltk_task.py
Traceback (most recent call last):
File "d:/Python/nltk/nltk_task.py", line 64, in <module>
process_content()
File "d:/Python/nltk/nltk_task.py", line 60, in process_content
namedEnt = ne_chunk(tagged, binary=True)
File "C:\Users\Talha\AppData\Local\Programs\Python\Python37\lib\site-packages\nltk\chunk\__init__.py", line 185, in ne_chunk
chunker = load(chunker_pickle)
File "C:\Users\Talha\AppData\Local\Programs\Python\Python37\lib\site-packages\nltk\data.py", line 757, in load
resource_val = pickle.load(opened_resource)
ModuleNotFoundError: No module named 'numpy'