根据列表中字符串的出现情况对数据帧行进行分类

import pandas as pd

# 示例数据集
data = {
    'text': ['apple is red', 'banana is yellow', 'cherry is red', 'date is brown', 'elderberry is purple']
}
df = pd.DataFrame(data)

# 关键词列表
keywords = ['red', 'yellow']

# 创建一个新的列来存储分类结果
df['category'] = ''

# 根据关键词列表对数据进行分类
for index, row in df.iterrows():
    for keyword in keywords:
        if keyword in row['text']:
            df.at[index, 'category'] = keyword
            break  # 找到匹配的关键词后跳出循环

print(df)

                     text category
0          apple is red      red
1       banana is yellow   yellow
2         cherry is red      red
3          date is brown        
4  elderberry is purple        

import re

# 使用正则表达式进行模糊匹配
for index, row in df.iterrows():
    for keyword in keywords:
        if re.search(keyword, row['text'], re.IGNORECASE):
            df.at[index, 'category'] = keyword
            break