df = pd.DataFrame(data=data, index=index, columns=columns)

print(df)

print(“=================================================”)

df1 = df.groupby([‘class_1’, ‘class_2’]).sum() # 分组统计求和

print(df1)

1.3 对DataFrameGroupBy对象列名索引（对指定列统计计算）

其中，df.groupby(‘class_1’)得到一个DataFrameGroupBy对象，对该对象可以使用列名进行索引，以对指定的列进行统计。

如：df.groupby(‘class_1’)[‘num’].sum()

import pandas as pd

data = [[‘a’, ‘A’, ‘1等’, 109], [‘b’, ‘B’, ‘1等’, 112], [‘c’, ‘A’, ‘1等’, 125], [‘d’, ‘B’, ‘2等’, 120],

[‘e’, ‘B’, ‘1等’, 126], [‘f’, ‘B’, ‘2等’, 133], [‘g’, ‘A’, ‘2等’, 124], [‘h’, ‘B’, ‘1等’, 134],

[‘i’, ‘A’, ‘2等’, 117], [‘j’, ‘A’, ‘2等’, 128], [‘h’, ‘A’, ‘1等’, 130], [‘i’, ‘B’, ‘2等’, 122]]

index = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]

columns = [‘name’, ‘class_1’, ‘class_2’, ‘num’]

df = pd.DataFrame(data=data, index=index, columns=columns)

print(df)

print(“=================================================”)

df1 = df.groupby(‘class_1’)[‘num’].sum()

print(df1)

代码运行结果同上。

2. 对分组数据进行迭代

===================================================================================

2.1 对一级分类的DataFrameGroupBy对象进行遍历

for name, group in DataFrameGroupBy_object

其中，name指分类的类名，group指该类的所有数据。

import pandas as pd

data = [[‘a’, ‘A’, ‘1等’, 109], [‘b’, ‘C’, ‘1等’, 112], [‘c’, ‘A’, ‘1等’, 125], [‘d’, ‘B’, ‘2等’, 120],

[‘e’, ‘B’, ‘1等’, 126], [‘f’, ‘B’, ‘2等’, 133], [‘g’, ‘C’, ‘2等’, 124], [‘h’, ‘A’, ‘1等’, 134],

[‘i’, ‘C’, ‘2等’, 117], [‘j’, ‘A’, ‘2等’, 128], [‘h’, ‘B’, ‘1等’, 130], [‘i’, ‘C’, ‘2等’, 122]]

index = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]

columns = [‘name’, ‘class_1’, ‘class_2’, ‘num’]

df = pd.DataFrame(data=data, index=index, columns=columns)

print(df)

print(“====================