如何清理带有特殊字符的数据集？

import re

def clean_dataset(dataset):
    pattern = r'[^\w\s]'  # 正则表达式定义特殊字符范围
    cleaned_dataset = []
    for data in dataset:
        cleaned_data = re.sub(pattern, '', data)  # 删除特殊字符
        cleaned_dataset.append(cleaned_data)
    return cleaned_dataset

dataset = ['Hello, World!', '123@456', 'abc$def']
cleaned_dataset = clean_dataset(dataset)
print(cleaned_dataset)

import java.util.regex.Pattern;
import java.util.regex.Matcher;

public class DatasetCleaner {
    public static String[] cleanDataset(String[] dataset) {
        String pattern = "[^\\w\\s]";  // 正则表达式定义特殊字符范围
        String[] cleanedDataset = new String[dataset.length];
        for (int i = 0; i < dataset.length; i++) {
            String cleanedData = dataset[i].replaceAll(pattern, "");  // 删除特殊字符
            cleanedDataset[i] = cleanedData;
        }
        return cleanedDataset;
    }

    public static void main(String[] args) {
        String[] dataset = {"Hello, World!", "123@456", "abc$def"};
        String[] cleanedDataset = cleanDataset(dataset);
        for (String data : cleanedDataset) {
            System.out.println(data);
        }
    }
}