pandas数据帧中基于相应列值的重复列和基于合计值的行

import pandas as pd

# 创建一个示例数据帧
data = {'Name': ['Alice', 'Bob', 'Charlie', 'Alice', 'Bob'],
        'Age': [25, 30, 35, 25, 30],
        'Salary': [5000, 6000, 7000, 5000, 6000]}
df = pd.DataFrame(data)

# 基于相应列值的重复列
df['TotalSalary'] = df.groupby('Name')['Salary'].transform('sum')

# 基于合计值的行
total_salary_threshold = 10000
df_filtered = df[df.groupby('Name')['Salary'].transform('sum') > total_salary_threshold]

print(df)
print(df_filtered)

      Name  Age  Salary  TotalSalary
0    Alice   25    5000        10000
1      Bob   30    6000        12000
2  Charlie   35    7000         7000
3    Alice   25    5000        10000
4      Bob   30    6000        12000

    Name  Age  Salary  TotalSalary
1    Bob   30    6000        12000
4    Bob   30    6000        12000