Python Pandas夜间数据分组

import pandas as pd

data = {
    'date': ['2023-01-01', '2023-01-01', '2023-01-02', '2023-01-02'],
    'product': ['A', 'B', 'A', 'B'],
    'sales': [100, 200, 150, 250]
}

df = pd.DataFrame(data)
df['date'] = pd.to_datetime(df['date'])

# 按日期和产品分组，并计算总销售额
result = df.groupby(['date', 'product'])['sales'].sum().reset_index()
print(result)

         date product  sales
0 2023-01-01       A    100
1 2023-01-01       B    200
2 2023-01-02       A    150
3 2023-01-02       B    250

# 示例：分块处理数据
chunksize = 100000
chunks = pd.read_csv('large_data.csv', chunksize=chunksize)

result = pd.DataFrame()
for chunk in chunks:
    grouped_chunk = chunk.groupby(['date', 'product'])['sales'].sum()
    result = result.add(grouped_chunk, fill_value=0)

result = result.reset_index()
print(result)

# 示例：填充缺失值
df['product'] = df['product'].fillna('Unknown')
result = df.groupby(['date', 'product'])['sales'].sum().reset_index()
print(result)