在Pandas列中将数字与日期分开

import pandas as pd

# 创建示例数据
data = {'column': ['12345-2022-01-01', '67890-2022-01-02']}
df = pd.DataFrame(data)

# 将列转换为字符串类型
df['column'] = df['column'].astype(str)

# 使用正则表达式提取数字和日期部分
df['number'] = df['column'].str.extract(r'(\d+)-')
df['date'] = df['column'].str.extract(r'-(\d{4}-\d{2}-\d{2})')

# 将数字部分转换为数值类型
df['number'] = df['number'].astype(int)

# 将日期部分转换为日期类型
df['date'] = pd.to_datetime(df['date'])

# 打印结果
print(df)

              column  number       date
0  12345-2022-01-01   12345 2022-01-01
1  67890-2022-01-02   67890 2022-01-02