python - 自动更正功能错误：字符串 2 列表

Question

我正在尝试自动更正提取的推文中的单词。我检查了文本类型。<>

但错误显示“AttributeError：'list' 对象没有属性'lower'”，即它是一个列表对象......我该如何解决这个问题。

我对python很陌生...请帮助我解决错误。

text=remove_punctuation(clean_emoji(remove_rt(strip_links(tweet.text))))
print(type(text)) 

#SOURCE_CODE: https://norvig.com/spell-correct.html

def words(text): return re.findall(r'\w+', text.lower())
WORDS = Counter(words(open('C:/Users/Paromita/Desktop/Travel Recommendation/big.txt').read()))     #count all the words in "big.txt" document
                                                                                                   #import Counter
def P(word, N=sum(WORDS.values())):                                                                #provides probability of the word
    return WORDS[word] / N

def known(words):                                                                                  #The subset of `words` that appear in the dictionary of WORDS.
    return set(w for w in words if w in WORDS)

def edits1(word):                                                                                  #All edits that are one edit away from `word`
    letters    = 'abcdefghijklmnopqrstuvwxyz'
    splits     = [(word[:i], word[i:])    for i in range(len(word) + 1)]
    deletes    = [L + R[1:]               for L, R in splits if R]
    transposes = [L + R[1] + R[0] + R[2:] for L, R in splits if len(R)>1]
    replaces   = [L + c + R[1:]           for L, R in splits if R for c in letters]
    inserts    = [L + c + R               for L, R in splits for c in letters]
    return set(deletes + transposes + replaces + inserts)

def edits2(word):                                                                                  #All edits that are two edits away from `word`
    return (e2 for e1 in edits1(word) for e2 in edits1(e1))

def candidates(word):                                                                              #Generate possible spelling corrections for word.
    return (known([word]) or known(edits1(word)) or known(edits2(word)) or [word])

def correction(word):                                                                              #  Most probable spelling correction for word
    return max(candidates(word), key=P)

def autocorrect(word):
    for w in words(text):
        word=word.replace(w,correction(w))
    return word

错误：

<ipython-input-124-2d46c58aaf5d> in autocorrect(word)
     29 
     30 def autocorrect(word):
---> 31     for w in words(text):
     32         word=word.replace(w,correction(w))
     33     return word

<ipython-input-124-2d46c58aaf5d> in words(text)
      1 #SOURCE_CODE: https://norvig.com/spell-correct.html
      2 
----> 3 def words(text): return re.findall(r'\w+', text.lower())
      4 WORDS = Counter(words(open('C:/Users/Paromita/Desktop/Travel Recommendation/big.txt').read()))     #count all the words in "big.txt" document
      5                                                                                                    #import Counter

AttributeError: 'list' object has no attribute 'lower'

标签： pythonstringlist

Answer 1

看起来像是text一个字符串列表。

尝试：

def words(text):
    return re.findall(r'\w+', " ".join(text).lower())