import pandas as pd
import numpy as np

# 创建一个示例数据框
df = pd.DataFrame({'A': ['foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'foo'],
                   'B': ['one', 'one', 'two', 'three', 'two', 'two', 'one', 'three'],
                   'C': np.random.randn(8),
                   'D': np.random.randn(8)})

# 将数据框按A列分组
grouped = df.groupby('A')

# 使用for循环遍历分组数据框
for name, group in grouped:
    print(name)
    print(group)

bar
     A      B         C         D
1  bar    one  0.169335  0.567679
3  bar  three  1.603023  1.273033
5  bar    two -0.855585 -0.291572
foo
     A    B         C         D
0  foo  one  0.265250 -0.330777
2  foo  two  0.210874 -1.313437
4  foo  two -0.692464 -1.352743
6  foo  one  1.005244  0.042469
7  foo  three  0.395754 -0.029910

import pandas as pd
import numpy as np

# 创建一个示例数据框
df = pd.DataFrame({'A': ['foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'foo'],
                   'B': ['one', 'one', 'two', 'three', 'two', 'two', 'one', 'three'],
                   'C': np.random.randn(8),
                   'D': np.random.randn(8)})

# 将数据框按A列分组
grouped = df.groupby('A')

# 定义一个函数
def custom_func(x):
    """
    对分组数据框执行操作
    """
    return x['C'].mean()

# 使用apply方法执行操作
result = grouped.apply(custom_func)

# 打印结果
print(result)

A
bar    0.305258
foo    0.244931
dtype: float64

import pandas as pd
import numpy as np

# 创建一个示例数据框
df = pd.DataFrame({'A': ['foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'foo'],
                   'B': ['one', 'one', 'two', 'three', 'two', 'two', 'one', 'three'],
                   'C': np.random.randn(8),
                   'D': np.random.randn(8)})

# 将数据框按A列分组
grouped = df.groupby('A')

# 使用agg方法执行多个操作
result = grouped['C', 'D'].agg({'C': 'mean', 'D': 'sum'})

# 打印结果
print(result)

            C         D
A                      
bar  0.580638 -1.047794
foo  0.449211 -2.152899