熟练掌握 Pandas 透视表，数据统计汇总利器

import pandas
df = pandas.pivot_table(
    data="要进行汇总的数据集（DataFrame）",
    values="要聚合的列或列的列表", 
    index="要作为行索引的列或列的列表",
    columns="要作为列索引的列或列的列表",
    aggfunc="用于聚合数据的函数或函数列表,默认是 numpy.mean",
    fill_value="填充缺失值的标量值",
    margins="布尔值,是否添加行和列的总计,默认是 False",
    margins_name="总计行和列的名称,默认是 All", 
    dropna="布尔值,是否删除所有结果为全 NaN 的列,默认是 True",
    observed="布尔值,对于分类列,是否只显示实际出现的类别,默认是 False",
    sort="布尔值,是否对结果进行排序,默认是 True"
)

import pandas as pd

# 生成一个数据集 df 
data = {
    'Region': ['North', 'South', 'East', 'West', 'North', 'South', 'East', 'West'],
    'Product': ['A', 'A', 'B', 'B', 'C', 'C', 'A', 'A'],
    'Sales': [100, 150, 200, 130, 120, 180, 220, 210],
    'Quantity': [10, 15, 20, 13, 12, 18, 22, 21]
}
df = pd.DataFrame(data)

In [53]: df
Out[53]:
  Region Product  Sales  Quantity
0  North       A    100        10
1  South       A    150        15
2   East       B    200        20
3   West       B    130        13
4  North       C    120        12
5  South       C    180        18
6   East       A    220        22
7   West       A    210        21

# 对 Sales 进行求和操作，行索引是Region，列索引是各个 Product，
# 对行和列增加统计 total
In [56]: pd.pivot_table(df, values='Sales', index='Region', 
columns='Product', aggfunc='sum', margins=True, 
margins_name='Total')

Out[56]:
Product      A      B      C    Total
Region
East       220.0  200.0    NaN    420
North      100.0    NaN  120.0    220
South      150.0    NaN  180.0    330
West       210.0  130.0    NaN    340
Total      680.0  330.0  300.0   1310

In [57]: pd.pivot_table(df, values='Sales', 
index=['Region', 'Product'], aggfunc='sum')
Out[57]:
                Sales
Region Product
East   A          220
       B          200
North  A          100
       C          120
South  A          150
       C          180
West   A          210
       B          130