Pandas分组聚合之使用自定义函数方法transform()、apply()_python

import pandas as pd

df = pd.DataFrame(
    data={
        'name': ['z_s', 'l_s', 'w_w', 'z_l', 'y_s', 'j_j', 'l_b', 'z_f', 'hs_q', 'lbl_k', 'qy_n', 'mg_n'],
        'score': [100, 97, 98, 89, 67, 59, 29, 87, 78, 89, 88, 80],
        'group': [1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2],
        'cls': ['A', 'A', 'A', 'B', 'B', 'B', 'A', 'A', 'A', 'B', 'B', 'B'],
        'height': [178.0, 180.0, 176.0, 182.0, 189.0, 190.0, 172.5, 175.0, 165.0, 160.0, 158.5, 159.0]
    },
    index=['stu_' + str(i) for i in np.arange(1, 13, 1)]
)
print('df:\n', df)

def func_add_one(x):
    return x + 1

# 调用自定义函数
ret = df.loc[:, 'score'].transform(func_add_one)
print('ret1:\n',ret)
# 调用numpy指标 求均值
ret = df.groupby(by=['cls'])['score'].transform(np.mean)
print('ret2:\n', ret)
# 求 多列的均值
ret = df.groupby(by=['cls'])[['score','height']].transform(np.mean)
print('ret3:\n', ret)

# 调用自定义函数
ret = df.loc[:, 'score'].apply(func_add_one)
print('ret1:\n',ret)

# 调用numpy指标
ret = df.groupby(by=['cls'])[['score','height']].apply(np.mean)
print('ret2:\n', ret)

def func_get_firstnameword(x):
    return x[0]

ret = df['name'].transform(func_get_firstnameword)
print('ret:\n', ret)

ret = df['name'].str.split('_', expand=True)[0]
print('ret:\n', ret)

ret = df['name'].str.split('_')[0]
print('ret:\n', ret)