Pandas Series数据结构基本操作

>>> import pandas
>>> import numpy as np
>>> from pandas import Series,DataFrame
#define a series without assigned index
>>> obj = Series([1,-5,7,3])
>>> print obj
0    1
1   -5
2    7
3    3
dtype: int64
>>> print obj.index
RangeIndex(start=0, stop=4, step=1)
>>> print obj.values
[ 1 -5  7  3]
>>> print obj[3]
3

#explicitly assigned index dbac
>>> obj1 = Series([1,2,3,4],index=[‘d‘,‘b‘,‘a‘,‘c‘])
>>> print obj1
d    1
b    2
a    3
c    4
dtype: int64
>>> print obj1.values
[1 2 3 4]
>>> print obj1.index
Index([u‘d‘, u‘b‘, u‘a‘, u‘c‘], dtype=‘object‘)
>>> print obj1[‘c‘]
4
>>> obj1[‘a‘]=-4
>>> print obj1.values
[ 1  2 -4  4]

#basic operation, index will not be changed
>>> obj1[obj1>0]
d    1
b    2
c    4
dtype: int64
>>> print obj1
d    1
b    2
a   -4
c    4
dtype: int64
>>> obj2 = obj1[obj1>0]
>>> obj2
d    1
b    2
c    4
dtype: int64
>>> obj2*2
d    2
b    4
c    8
dtype: int64
>>> obj2
d    1
b    2
c    4
dtype: int64
>>> obj2 = obj2*2
>>> obj2
d    2
b    4
c    8
dtype: int64
>>> obj2=np.exp(obj2)
>>> obj2
d       7.389056
b      54.598150
c    2980.957987
dtype: float64
>>> ‘b‘ in obj2
True
>>> ‘e‘ in obj2
False

#define a Series with indexes and values
>>> sdata={‘beijing‘:‘010‘,‘shanghai‘:‘021‘,‘guangdong‘:‘020‘}
>>> obj3 = Series(sdata)
>>> print obj3
beijing      010
guangdong    020
shanghai     021
dtype: object
>>> index1 = [‘tianjin‘,‘shanghai‘,‘guangdong‘,‘beijing‘]
>>> obj3 = Series(sdata,index=index1)
>>> print obj3
tianjin      NaN
shanghai     021
guangdong    020
beijing      010
dtype: object

#isnull or notnull
>>> import pandas as pd
>>> print pd.isnull(obj3)
tianjin       True
shanghai     False
guangdong    False
beijing      False
dtype: bool
>>> print pd.notnull(obj3)
tianjin      False
shanghai      True
guangdong     True
beijing       True
dtype: bool

>>> obj3 = Series(sdata)
>>> print obj3
beijing      010
guangdong    020
shanghai     021
dtype: object
>>> index1 = [‘tianjin‘,‘shanghai‘,‘guangdong‘,‘beijing‘]
>>> obj4 = Series(sdata,index=index1)
>>> print obj4
tianjin      NaN
shanghai     021
guangdong    020
beijing      010
dtype: object
>>> print obj3+obj4
beijing      010010
guangdong    020020
shanghai     021021
tianjin         NaN
dtype: object

>>> obj4.name=‘postcode‘
>>> obj4.index.name=‘city‘
>>> print obj4
city
tianjin      NaN
shanghai     021
guangdong    020
beijing      010
Name: postcode, dtype: object