本文整理汇总了Python中string.punctuation方法的典型用法代码示例。如果您正苦于以下问题:Python string.punctuation方法的具体用法?Python string.punctuation怎么用?Python string.punctuation使用的例子?那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在模块string的用法示例。
在下文中一共展示了string.punctuation方法的25个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于我们的系统推荐出更棒的Python代码示例。
示例1: clean_captions
点赞 6
# 需要导入模块: import string [as 别名]
# 或者: from string import punctuation [as 别名]
def clean_captions(captions):
# Prepare translation table for removing punctuation
table = str.maketrans('', '', string.punctuation)
for _, caption_list in captions.items():
for i in range(len(caption_list)):
caption = caption_list[i]
# Tokenize i.e. split on white spaces
caption = caption.split()
# Convert to lowercase
caption = [word.lower() for word in caption]
# Remove punctuation from each token
caption = [w.translate(table) for w in caption]
# Remove hanging 's' and 'a'
caption = [word for word in caption if len(word)>1]
# Remove tokens with numbers in them
caption = [word for word in caption if word.isalpha()]
# Store as string
caption_list[i] = ' '.join(caption)
开发者ID:dabasajay,项目名称:Image-Caption-Generator,代码行数:20,
示例2: normalize_answer
点赞 6
# 需要导入模块: import string [as 别名]
# 或者: from string import punctuation [as 别名]
def normalize_answer(s):
"""Lower text and remove extra whitespace."""
def remove_articles(text):
return re_art.sub(' ', text)
def remove_punc(text):
return re_punc.sub(' ', text) # convert punctuation to spaces
def white_space_fix(text):
return ' '.join(text.split())
def lower(text):
return text.lower()
return white_space_fix(remove_articles(remove_punc(lower(s))))
开发者ID:hugochan,项目名称:BAMnet,代码行数:17,
示例3: random_string
点赞 6
# 需要导入模块: import string [as 别名]
# 或者: from string import punctuation [as 别名]
def random_string(n):
if n == 0:
return ""
x = random.random()
if x > 0.5:
pad = " " * n
elif x > 0.3:
pad = "".join(random.choices(digits + " \t\n", k=n))
elif x > 0.2:
pad = "".join(random.choices(ascii_uppercase + " \t\n", k=n))
elif x > 0.1:
pad = "".join(random.choices(ascii_uppercase + digits + " \t\n", k=n))
else:
pad = "".join(
random.choices(ascii_uppercase + digits + punctuation + " \t\n", k=n)
)
return pad
开发者ID:zzzDavid,项目名称:ICDAR-2019-SROIE,代码行数:21,
示例4: tokenize_sentence
点赞 6
# 需要导入模块: import string [as 别名]
# 或者: from string import punctuation [as 别名]
def tokenize_sentence(sentence):
"""
Splits a sentence into words, strips punctuation and turns it to lowercase.
:param sentence : the sentence to tokenize.
:type sentence : str
:return : list of words
"""
# Get rid of non-ascii characters to avoid errors with unrecognised characters
sentence = "".join([c for c in sentence if 0 < ord(c) < 127])
sentence = sentence.encode("ascii", errors="ignore").decode()
# Only works in Python 3
sentenceNoPunctuation = sentence.translate(str.maketrans("", "", string.punctuation))
sentenceLower = sentenceNoPunctuation.lower()
sentenceWords = sentenceLower.split()
return sentenceWords
开发者ID:Wluper,项目名称:edm,代码行数:24,
示例5: __init__
点赞 6
# 需要导入模块: import st