In [1]: 
import warnings
import math
import pandas as pd
import numpy as np
import matplotlib

warnings.filterwarnings('ignore')
pd.options.display.max_rows = 100
pd.options.display.max_columns = 100
pd.set_option('max_colwidth', 500)

get_ipython().magic(u'matplotlib inline')
matplotlib.style.use('ggplot')

from matplotlib import pyplot as plt
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False

myfont = matplotlib.font_manager.FontProperties(fname=u'simsun.ttc', size=14)
In [11]: 
data = pd.DataFrame({
    'age' : np.random.randint(15, 100, 100),
    'height':np.random.randint(140, 180, 100),
    'weight':np.random.randint(40, 80, 100),
    'gender':np.random.randint(0,2, 100),
    'salary':np.random.randint(3000, 30000, 100)
})
data.head()
Out[11]:  
  age height weight gender salary
0 68 140 58 0 15988
1 22 160 59 0 5807
2 90 160 60 0 21741
3 71 178 45 0 14133
4 61 165 59 1 14346
In [12]: 
# series map:值转换
data['gender'] = data.gender.map({0:'man', 1:'women'})
data.head()
Out[12]:  
  age height weight gender salary
0 68 140 58 man 15988
1 22 160 59 man 5807
2 90 160 60 man 21741
3 71 178 45 man 14133
4 61 165 59 women 14346
In [14]: 
# series map: 也可以使用字符串format
data.gender.map('i am a {} '.format).head()
Out[14]: 
0      i am a man 
1      i am a man 
2      i am a man 
3      i am a man 
4    i am a women 
Name: gender, dtype: object
In [19]: 
# series apply: 对序列的每个值做相应操作
data.salary = data.salary.apply(lambda x: x* 1.3)
data.head()
Out[19]:  
  age height weight gender salary
0 68 140 58 man 35125.636
1 22 160 59 man 12757.979
2 90 160 60 man 47764.977
3 71 178 45 man 31050.201
4 61 165 59 women 31518.162
In [33]: 
# series apply: 对序列的每个值做相应操作，可传递复杂参数和函数
def fun1(x, bias):
    return x * bias
data.salary = data.salary.apply(fun1, args=(1.3,))
data.head()
Out[33]:  
  age height weight gender salary
0 68 140 58 man 45663.3268
1 22 160 59 man 16585.3727
2 90 160 60 man 62094.4701
3 71 178 45 man 40365.2613
4 61 165 59 women 40973.6106
In [36]: 
# series apply: 对序列的每个值做相应操作，可传递复杂参数和函数
def fun2(x, **kwargs):
    for month in kwargs:
        x += kwargs[month] * 100
    return x 
data.salary = data.salary.apply(fun2, june=30, july=20, august=25)
data.head()
Out[36]:  
  age height weight gender salary
0 68 140 58 man 53238.3268
1 22 160 59 man 24160.3727
2 90 160 60 man 69669.4701
3 71 178 45 man 47940.2613
4 61 165 59 women 48548.6106
In [28]: 
# dataframe apply:根据函数对行或者列应用对应操作
data[['age','height', 'weight']].apply(np.sqrt).head()
Out[28]:  
  age height weight
0 8.246211 11.832160 7.615773
1 4.690416 12.649111 7.681146
2 9.486833 12.649111 7.745967
3 8.426150 13.341664 6.708204
4 7.810250 12.845233 7.681146
In [37]: 
# dataframe apply:根据函数对行或者列应用对应操作
data[['age','height', 'weight']].apply(np.sum).head()
Out[37]: 
age        5818
height    16225
weight     6081
dtype: int64
In [29]: 
# dataframe apply:根据函数对行应用对应操作，做比较复杂计算
def BMI(series):
    height = series['height']/100.0
    weight = series['weight']
    return weight / height ** 2

data.apply(BMI, axis = 1).head()
Out[29]: 
0    29.591837
1    23.046875
2    23.437500
3    14.202752
4    21.671258
dtype: float64
In [43]: 
data[['age','height', 'weight']].head()
Out[43]:  
  age height weight
0 68 140 58
1 22 160 59
2 90 160 60
3 71 178 45
4 61 165 59
In [44]: 
# dataframe applymap:对每个元素操作
data[['age','height', 'weight']].applymap(lambda x:x-2).head()
Out[44]:  
  age height weight
0 66 138 56
1 20 158 57
2 88 158 58
3 69 176 43
4 59 163 57
扫码关注我们
微信号：SRE实战
拒绝背锅 运筹帷幄

SRE实战 互联网时代守护先锋，助力企业售后服务体系运筹帷幄！一键直达领取阿里云限量特价优惠。