在Python中删除dataframe每列中的字符和单词重复项

import pandas as pd

# 创建一个示例DataFrame
data = {
    'A': ['helloo', 'worlddd', 'foo', 'bar'],
    'B': ['aaabbb', 'cc', 'dd', 'ee']
}
df = pd.DataFrame(data)

# 定义一个函数来删除字符重复项
def remove_char_duplicates(s):
    return ''.join(sorted(set(s), key=s.index))

# 定义一个函数来删除单词重复项
def remove_word_duplicates(s):
    words = s.split()
    seen = set()
    result = []
    for word in words:
        if word not in seen:
            seen.add(word)
            result.append(word)
    return ' '.join(result)

# 应用函数到DataFrame的每一列
for col in df.columns:
    df[col] = df[col].apply(remove_char_duplicates)
    df[col] = df[col].apply(remove_word_duplicates)

print(df)