计算pandas中分组元素之间的差异

import pandas as pd

# 创建示例数据
data = {
    'date': ['2023-01-01', '2023-01-02', '2023-01-01', '2023-01-02'],
    'region': ['A', 'A', 'B', 'B'],
    'sales': [100, 150, 200, 220]
}

df = pd.DataFrame(data)

# 将日期列转换为 datetime 类型
df['date'] = pd.to_datetime(df['date'])

# 按地区和日期分组
grouped = df.groupby(['region', 'date'])

# 计算每个组内的销售额差异
df['sales_diff'] = grouped['sales'].diff()

print(df)

        date region  sales  sales_diff
0 2023-01-01      A    100         NaN
1 2023-01-02      A    150        50.0
2 2023-01-01      B    200         NaN
3 2023-01-02      B    220        20.0

# 填充 NaN 值
df['sales_diff'] = df['sales_diff'].fillna(0)

print(df)

        date region  sales  sales_diff
0 2023-01-01      A    100        0.0
1 2023-01-02      A    150        50.0
2 2023-01-01      B    200        0.0
3 2023-01-02      B    220        20.0