NLP-英文文本预处理中的文本清洗内容

记录英文文本中的文本清洗内容：

• 缩略词更改
• 拼写校正
• 标点符号
• 符号替换
• 去除空格

    def clean_text(text):
        """
        Clean text
        :param text: the string of text
        :return: text string after cleaning
        """
        # acronym
        text = re.sub(r"can\'t", "can not", text)
        text = re.sub(r"cannot", "can not ", text)
        text = re.sub(r"what\'s", "what is", text)
        text = re.sub(r"What\'s", "what is", text)
        text = re.sub(r"\'ve ", " have ", text)
        text = re.sub(r"n\'t", " not ", text)
        text = re.sub(r"i\'m", "i am ", text)
        text = re.sub(r"I\'m", "i am ", text)
        text = re.sub(r"\'re", " are ", text)
        text = re.sub(r"\'d", " would ", text)
        text = re.sub(r"\'ll", " will ", text)
        text = re.sub(r" e mail ", " email ", text)
        text = re.sub(r" e \- mail ", " email ", text)
        text = re.sub(r" e\-mail ", " email ", text)

        # spelling correction
        text = re.sub(r"ph\.d", "phd", text)
        text = re.sub(r"PhD", "phd", text)
        text = re.sub(r" e g ", " eg ", text)
        text = re.sub(r" fb ", " facebook ", text)
        text = re.sub(r"facebooks", " facebook ", text)
        text = re.sub(r"facebooking", " facebook ", text)
        text = re.sub(r" usa ", " america ", text)
        text = re.sub(r" us ", " america ", text)
        text = re.sub(r" u s ", " america ", text)
        text = re.sub(r" U\.S\. ", " america ", text)
        text = re.sub(r" US ", " america ", text)
        text = re.sub(r" American ", " america ", text)
        text = re.sub(r" America ", " america ", text)
        text = re.sub(r" mbp ", " macbook-pro ", text)
        text = re.sub(r" mac ", " macbook ", text)
        text = re.sub(r"macbook pro", "macbook-pro", text)
        text = re.sub(r"macbook-pros", "macbook-pro", text)
        text = re.sub(r" 1 ", " one ", text)
        text = re.sub(r" 2 ", " two ", text)
        text = re.sub(r" 3 ", " three ", text)
        text = re.sub(r" 4 ", " four ", text)
        text = re.sub(r" 5 ", " five ", text)
        text = re.sub(r" 6 ", " six ", text)
        text = re.sub(r" 7 ", " seven ", text)
        text = re.sub(r" 8 ", " eight ", text)
        text = re.sub(r" 9 ", " nine ", text)
        text = re.sub(r"googling", " google ", text)
        text = re.sub(r"googled", " google ", text)
        text = re.sub(r"googleable", " google ", text)
        text = re.sub(r"googles", " google ", text)
        text = re.sub(r"dollars", " dollar ", text)

        # punctuation
        text = re.sub(r"\+", " + ", text)
        text = re.sub(r"'", " ", text)
        text = re.sub(r"-", " - ", text)
        text = re.sub(r"/", " / ", text)
        text = re.sub(r"\\", " \ ", text)
        text = re.sub(r"=", " = ", text)
        text = re.sub(r"\^", " ^ ", text)
        text = re.sub(r":", " : ", text)
        text = re.sub(r"\.", " . ", text)
        text = re.sub(r",", " , ", text)
        text = re.sub(r"\?", " ? ", text)
        text = re.sub(r"!", " ! ", text)
        text = re.sub(r"\"", " \" ", text)
        text = re.sub(r"&", " & ", text)
        text = re.sub(r"\|", " | ", text)
        text = re.sub(r";", " ; ", text)
        text = re.sub(r"\(", " ( ", text)
        text = re.sub(r"\)", " ( ", text)

        # symbol replacement
        text = re.sub(r"&", " and ", text)
        text = re.sub(r"\|", " or ", text)
        text = re.sub(r"=", " equal ", text)
        text = re.sub(r"\+", " plus ", text)
        text = re.sub(r"\$", " dollar ", text)

        # remove extra space
        text = ' '.join(text.split())

        return text