pandas.Series学习

#pandas 基础
import numpy as np

import pandas as pd 

#Series是一个随机数组
ar=np.random.rand(5)
print (ar)
s=pd.Series(ar)

print (s)

[0.48942827 0.47321657 0.37859367 0.86765122 0.89666973]
0    0.489428
1    0.473217
2    0.378594
3    0.867651
4    0.896670
dtype: float64

#name属性
a=pd.Series(np.random.rand(100),name='fasdfdas')


b=pd.Series([90,92,89,65],index=['Jack','Marry','Tom','Zack'],name='作业',dtype=np.float64)

b

Jack     90.0
Marry    92.0
Tom      89.0
Zack     65.0
Name: 作业, dtype: float64

#Series索引
s=pd.Series(np.random.rand(10))
print (s)

print (s[5],type(s[5]),s[5].dtype)

0    0.555260
1    0.925801
2    0.354234
3    0.597488
4    0.652729
5    0.216476
6    0.269461
7    0.957974
8    0.625409
9    0.727877
dtype: float64
0.21647554176678407 <class 'numpy.float64'> float64

#标签索引
s=pd.Series(np.random.rand(5),index=['a','b','c','d','e'])
print (s)

print (s[['a','b','c']])#注意要选取多个索引记住多加括号,位置自己随意

<div><br class="Apple-interchange-newline">#标签索引 s=pd.Series(np.random.rand(5),index=['a','b','c','d','e']) print (s) print (s[['a','b','c']])#注意要选取多个索引记住多加括号,位置自己随意</div>

#标签索引

s=pd.Series(np.random.rand(5),index=['a','b','c','d','e'])

print (s)

print (s[['a','b','c']])#注意要选取多个索引记住多加括号,位置自己随意

a    0.106773
b    0.461048
c    0.209971
d    0.281229
e    0.586447
dtype: float64
a    0.106773
b    0.461048
c    0.209971
dtype: float64

#切片
s1=pd.Series(np.random.rand(5))
s2=pd.Series(np.random.rand(5),index=['a','b','c','d','e'])
print (s1[1:4])#下标
print (s2['a':'c'])#标签index

#有标签用标签，没标签用下标，用index做切片是末端包含的

1    0.129370
2    0.220584
3    0.144212
dtype: float64
a    0.653526
b    0.153144
c    0.466642
dtype: float64

#布尔型索引
s=pd.Series(np.random.rand(3)*100)
s[3]=None
bs1=s>50
bs2=s.isnull()
bs3=s.notnull()
print (bs1)
print (bs2)

print (bs3)

0     True
1     True
2    False
3    False
dtype: bool
0    False
1    False
2    False
3     True
dtype: bool
0     True
1     True
2     True
3    False
dtype: bool

#Series 重建索引，对齐，添加，修改，删除
s=pd.Series(np.random.rand(5),index=['a','b','c','d','e'])
print (s)
s1=s.reindex(['c','d','a','f','g'])#保留原有索引，如果有新名称，返回Nan
print (s1)
s2=s.reindex(['c','a','d','f'],fill_value=0)#填充为0

print (s2)

a    0.136703
b    0.735538
c    0.693360
d    0.224563
e    0.523118
dtype: float64
c    0.693360
d    0.224563
a    0.136703
f         NaN
g         NaN
dtype: float64
c    0.693360
a    0.136703
d    0.224563
f    0.000000
dtype: float64

#对齐
s1=pd.Series(np.random.rand(3),index=['Jack','Marry','Tom'])
s2=pd.Series(np.random.rand(3),index=['Jack','Marry','wang'])

print (s1+s2)

Jack     1.254179
Marry    0.976891
Tom           NaN
wang          NaN
dtype: float64

#删除和添加
s=pd.Series(np.random.rand(5),index=list('fasde'))
print (s)
s1=s.drop('s')
s2=s.drop(['f','d'])
print (s1)
print (s2)
print (s)

#删除元素之后返回副本（inplace=False）,默认是false，即不代替，也就是不改变原值

f    0.294838
a    0.367201
s    0.785893
d    0.395416
e    0.998229
dtype: float64
f    0.294838
a    0.367201
d    0.395416
e    0.998229
dtype: float64
a    0.367201
s    0.785893
e    0.998229
dtype: float64
f    0.294838
a    0.367201
s    0.785893
d    0.395416
e    0.998229
dtype: float64

#添加
s1=pd.Series(np.random.rand(5))
s2=pd.Series(np.random.rand(5),index=list('abcde'))
s1[5]=100
s2['f']=100
print (s1)
print (s2)
s3=s1.append(s2)

print (s3)

0      0.596044
1      0.038958
2      0.415344
3      0.412761
4      0.535289
5    100.000000
dtype: float64
a      0.830547
b      0.439642
c      0.867376
d      0.611164
e      0.452300
f    100.000000
dtype: float64
0      0.596044
1      0.038958
2      0.415344
3      0.412761
4      0.535289
5    100.000000
a      0.830547
b      0.439642
c      0.867376
d      0.611164
e      0.452300
f    100.000000
dtype: float64