【python】pandas库Serie

In [1]: import pandas as pd

In [2]: list_a = [2,4,5,6]

In [3]: pd.Series(list_a)
Out[3]:
0    2
1    4
2    5
3    6
dtype: int64

In [4]: pd.Series(1,index = [1,2,3])
Out[4]:
1    1
2    1
3    1
dtype: int64

In [5]: pd.Series({'a':1,'b':3})
Out[5]:
a    1
b    3
dtype: int64
#如果定义的index在原字典中已经存在，那么该索引会一直对应原字典的值，如果index对应不到原字典的值，则会返回NaN
In [11]: pd.Series({'a':1,'b':3},index = ['b','a','c'])
Out[11]:
b    3.0
a    1.0
c    NaN
dtype: float64

In [9]: list_b = np.arange(6)

In [10]: pd.Series(list_b)
Out[10]:
0    0
1    1
2    2
3    3
4    4
5    5
dtype: int32

In [12]: pd.Series(range(3))
Out[12]:
0    0
1    1
2    2
dtype: int32

In [14]: a = pd.Series({'a':1,'b':5})

In [15]: a.index
Out[15]: Index(['a', 'b'], dtype='object')

In [16]: a.values  #返回一个多维数组numpy对象
Out[16]: array([1, 5], dtype=int64)

#自动索引和自定义索引并存，但不能混用
In [17]: a[0]  #自动索引
Out[17]: 1
#自定义索引
In [18]: a['a']
Out[18]: 1
#不能混用
In [20]: a[['a',1]]
Out[20]:
a    1.0
1    NaN
dtype: float64

#通过自定义索引访问
#对索引保留字in操作，值不可以
In [21]: 'a' in a
Out[21]: True

In [22]: 1 in a
Out[22]: False

In [29]: a = pd.Series([1,3,5],index = ['a','b','c'])

In [30]: b = pd.Series([2,4,5,6],index = ['c,','d','e','b'])

In [31]: a+b
Out[31]:
a     NaN
b     9.0
c     NaN
c,    NaN
d     NaN
e     NaN
dtype: float64

In [32]: a.index = ['c','d','e']

In [33]: a
Out[33]:
c    1
d    3
e    5
dtype: int64

In [34]: a+b
Out[34]:
b      NaN
c      NaN
c,     NaN
d      7.0
e     10.0
dtype: float64