Pandas聚合:如何从一个列生成多个新列，反之亦然

import pandas as pd

# 创建示例数据
data = {'A': ['foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'foo'],
        'B': ['one', 'one', 'two', 'two', 'two', 'one', 'two', 'one'],
        'C': [1, 2, 3, 4, 5, 6, 7, 8],
        'D': [10, 20, 30, 40, 50, 60, 70, 80]}

df = pd.DataFrame(data)

# 使用pivot_table函数进行聚合
pivot_df = pd.pivot_table(df, values=['C', 'D'], index='A', columns='B', aggfunc='sum')

print(pivot_df)

       C             D        
B    one  two  one  two
A                        
bar   20  40.0   80  40.0
foo   9  10.0   90  37.0

import pandas as pd

# 创建示例数据
data = {'A': ['foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'foo'],
        'B': ['one', 'one', 'two', 'two', 'two', 'one', 'two', 'one'],
        'C': [1, 2, 3, 4, 5, 6, 7, 8],
        'D': [10, 20, 30, 40, 50, 60, 70, 80]}

df = pd.DataFrame(data)

# 定义一个函数，用于生成多个新列
def generate_new_columns(group):
    return pd.Series({'C_sum': group['C'].sum(), 'D_mean': group['D'].mean()})

# 使用groupby函数结合apply函数进行聚合
grouped_df = df.groupby('A').apply(generate_new_columns)

print(grouped_df)

     C_sum  D_mean
A                 
bar     10    40.0
foo     16    45.0