我有这样的错误:我的代码中的语法无效:
with gzip.open('EnCorp2Million.txt.gz', 'rb') as f:
try:
anatxt = f.read().decode('utf-8')
except ValueError as e:
print("Error:",e)
def strip_html(text):
soup = BeautifulSoup(text, "html.parser")
return soup.get_text()
anatxt = strip_html(anatxt)
def remove_between_square_brackets(text):
return re.sub('\[[^]]*\]', '', text)
anatxt = remove_between_square_brackets(anatxt)
def denoise_text(text):
text = strip_html(text)
text = remove_between_square_brackets(text)
return text
anatxt = denoise_text(anatxt)
def replace_contractions(text):
return contractions.fix(text)
anatxt = replace_contractions(anatxt)
words = nltk.word_tokenize(anatxt)
#1gram
onegram = ngrams(words, 1)
fdist_onegram = nltk.FreqDist(onegram)
for c,v in fdist_onegram.items(30):
print (c,v)
#As c,v mais frequentes
print(fdist_onegram.most_common(30))
print(fdist_onegram.plot(30)
#2gram
bigram = ngrams(words, 2)
fdist_bigram = nltk.FreqDist(bigram)
#As c,v mais frequentes
print(fdist_bigram.most_common(30))
print(fdist_bigram.plot(30)
执行时,我收到错误:
bigram = ngrams(words, 2)
^
SyntaxError: invalid syntax
如果我删除了二元组计算,则错误消失,但我需要对7克进行计算
我该如何解决这个问题?
答案 0 :(得分:2)
如果您看到一行看起来很好的语法错误,请查看上一行。在这种情况下,您忘记了右括号。
print(fdist_onegram.plot(30)