创建单独列的GroupBy条件和日期-Python

import pandas as pd

# 创建示例数据集
data = {
    'Date': ['2023-01-01', '2023-01-02', '2023-02-01', '2023-02-02', '2023-01-15'],
    'Region': ['North', 'South', 'North', 'South', 'North'],
    'Sales': [100, 200, 150, 250, 300]
}

df = pd.DataFrame(data)

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

# 创建月份和地区的单独列
df['Month'] = df['Date'].dt.month
df['Year'] = df['Date'].dt.year

# 按月份和地区分组，并对销售额进行求和
grouped = df.groupby(['Year', 'Month', 'Region'])['Sales'].sum().reset_index()

print(grouped)

df['Date'] = pd.to_datetime(df['Date'], errors='coerce')
df = df.dropna(subset=['Date'])  # 删除日期列中的NaT值

import dask.dataframe as dd

ddf = dd.from_pandas(df, npartitions=4)
grouped = ddf.groupby(['Year', 'Month', 'Region'])['Sales'].sum().compute()