使用SequenceMatcher Python查找pandas中的所有相似值

from difflib import SequenceMatcher

import pandas as pd

# 创建一个示例DataFrame
data = {'col1': ['apple', 'banana', 'orange', 'grape'],
        'col2': ['apple', 'banana', 'orange', 'grapefruit']}
df = pd.DataFrame(data)

# 获取所有相似值的匹配块
similar_values = []
for i, row in df.iterrows():
    for j, value in enumerate(row):
        if j > 0:
            matcher = SequenceMatcher(None, row[j-1], value)
            matching_blocks = matcher.get_matching_blocks()
            similar_values.extend([row[j-1][block.a:block.a+block.size] for block in matching_blocks])

# 去除重复值
similar_values = list(set(similar_values))