Pandas入门之五：自定义元素处理函数

已信任
Jupyter 服务器: 本地
Python 3: Not Started

[1]



import pandas as pd
import numpy as np



[4]




# 表格函数的自定义
# 将df中所有的元素加2
def add(ele1,ele2):
    return ele1+ele2

df = pd.DataFrame(np.random.randn(5,3), columns=['col1','col2','col3'])
    
df
col1    col2    col3
0    -1.444341    -0.354099    -0.744866
1    0.381602    -0.858716    -0.258652
2    -1.215713    0.058596    0.818322
3    0.750133    1.183576    -0.414067
4    1.929578    1.520465    0.356050
[5]



# 自定义管道函数
df.pipe(add,2)
col1    col2    col3
0    0.555659    1.645901    1.255134
1    2.381602    1.141284    1.741348
2    0.784287    2.058596    2.818322
3    2.750133    3.183576    1.585933
4    3.929578    3.520465    2.356050
[7]



# 按列求平均apply()
df.apply(np.mean)
col1    0.080252
col2    0.309964
col3   -0.048642
dtype: float64
[9]



# 设置轴长，按行
df.apply(np.std, axis=1)
0    0.450998
1    0.506447
2    0.839202
3    0.674594
4    0.666602
dtype: float64
[10]



# 每个元素进行一次操作
df.applymap(lambda x:x*100)
col1    col2    col3
0    -144.434121    -35.409873    -74.486626
1    38.160219    -85.871639    -25.865169
2    -121.571271    5.859575    81.832235
3    75.013306    118.357622    -41.406672
4    192.957780    152.046490    35.604997
[-]