Pre_process一列tweet并创建一个dataframe

import pandas as pd
import re
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from nltk.stem import WordNetLemmatizer

# 假设我们有一个包含tweets的列表
tweets = [
    "This is an example tweet! #example",
    "Another tweet with some @mentions and #hashtags.",
    "Yet another tweet with numbers 123 and punctuation."
]

# 预处理函数
def preprocess_tweet(tweet):
    # 转换为小写
    tweet = tweet.lower()
    # 去除标点符号和数字
    tweet = re.sub(r'[^\w\s]', '', tweet)
    tweet = re.sub(r'\d+', '', tweet)
    # 分词
    words = word_tokenize(tweet)
    # 去除停用词
    stop_words = set(stopwords.words('english'))
    words = [word for word in words if word not in stop_words]
    # 词形还原
    lemmatizer = WordNetLemmatizer()
    words = [lemmatizer.lemmatize(word) for word in words]
    return ' '.join(words)

# 应用预处理函数
processed_tweets = [preprocess_tweet(tweet) for tweet in tweets]

# 创建DataFrame
df = pd.DataFrame(processed_tweets, columns=['processed_tweet'])

print(df)