Блог

Ниже приведен код, который выдает ошибку значения Python: слишком много значений для распаковки (ожидаемое решение 2)

 import math
import os
import random
import re
import sys
import zipfile
os.environ['NLTK_DATA'] = os.getcwd()   "/nltk_data"

import nltk

from nltk import word_tokenize, ConditionalFreqDist, Text
from nltk.tokenize import regexp_tokenize
from nltk.corpus import stopwords

def performBigramsAndCollocations(textcontent, word):
    # Write your code here
    tokenizedwords = regexp_tokenize(textcontent, "[w] ")
    tokenizedwords = [x.lower() for x in tokenizedwords if x != '']
    tokenizedwordsbigrams = list(nltk.bigrams(tokenizedwords))
    stop_words = stopwords.words('english')
    lc_stop_words = [word.lower() for word in stop_words]
    tokenizednonstopwordsbigrams = [(n1,n2) for n1, n2 in tokenizedwords if n1 not in lc_stop_words and n2 not in lc_stop_words]
    cfd_bigrams = ConditionalFreqDist(tokenizednonstopwordsbigrams)
    mostfrequentwordafter = cfd_bigrams[word].most_common(3)
    words = Text(tokenizedwords)
    collectionwords = words.collection_list()
    return mostfrequentwordafter, collectionwords
    

if __name__ == '__main__':
    textcontent = input()

    word = input()

    if not os.path.exists(os.getcwd()   "/nltk_data"):
        with zipfile.ZipFile("nltk_data.zip", 'r') as zip_ref:
            zip_ref.extractall(os.getcwd())

    mostfrequentwordafter, collocationwords = performBigramsAndCollocations(textcontent, word)
    print(sorted(mostfrequentwordafter, key=lambda element: (element[1], element[0]), reverse=True))
    print(sorted(collocationwords))
 

Сообщение об ошибке для данного кода
Произошла ошибка для следующей строки
, обозначенной как nonstopwordsbigrams = [(n1,n2) для n1, n2 в обозначенных словах, если n1 не в lc_stop_words и n2 не в lc_stop_words]

 Traceback (most recent call last):
  File "Solution.py", line 48, in <module>
    mostfrequentwordafter, collocationwords = performBigramsAndCollocations(textcontent, word)
  File "Solution.py", line 31, in performBigramsAndCollocations
    tokenizednonstopwordsbigrams = [(n1,n2) for n1, n2 in tokenizedwords if n1 not in lc_stop_words and n2 not in lc_stop_words]
  File "Solution.py", line 31, in <listcomp>
    tokenizednonstopwordsbigrams = [(n1,n2) for n1, n2 in tokenizedwords if n1 not in lc_stop_words and n2 not in lc_stop_words]
ValueError: too many values to unpack (expected 2)