在Python中对数据集中的值进行分组和标注

import pandas as pd

# 创建一个示例数据集
data = {'Name': ['Tom', 'Nick', 'John', 'Tom', 'John'],
        'Age': [20, 21, 19, 20, 18],
        'Gender': ['M', 'M', 'M', 'M', 'F']}
df = pd.DataFrame(data)

# 按照Name列进行分组，并计算每个分组的平均年龄
grouped = df.groupby('Name')
average_age = grouped['Age'].mean()

# 将每个人的年龄与平均年龄进行比较，并进行标注
df['Age_Label'] = df.apply(lambda row: 'Above Average' if row['Age'] > average_age[row['Name']] else 'Below Average', axis=1)

# 打印结果
print(df)

   Name  Age Gender      Age_Label
0   Tom   20      M  Above Average
1  Nick   21      M  Above Average
2  John   19      M  Below Average
3   Tom   20      M  Above Average
4  John   18      F  Below Average