pandas is a numpy-based library and a very commonly used library for data processing in python.
- Series
- DataFrame
- Index
1. Series
>>> import pandas as pd
>>> import numpy as np
>>> s = pd.Series([7,'beijing',2.1,2,'happy'])
>>> s
0 7
1 beijing
2 2.1
3 2
4 happy
dtype: object
>>> s = pd.Series([7,'beijing',2.1,2,'happy'],index = ['A','B','C','D','E']) #修改index
>>> s
A 7
B beijing
C 2.1
D 2
E happy
dtype: object
>>> type(s)
<class 'pandas.core.series.Series'>
>>> cities = {'beijing':55000,'shanghai':60000,'shenzhen':40000,'guangzhou':25000}
>>> cities
{'beijing': 55000, 'shanghai': 60000, 'shenzhen': 40000, 'guangzhou': 25000}
>>> apts = pd.Series(cities) #Use dict to define a Series, Series itself is a key value pair
>>> apts
beijing 55000
guangzhou 25000
shanghai 60000
shenzhen 40000
dtype: int64
>>> apts[['beijing','shenzhen']]
beijing 55000
shenzhen 40000
dtype: int64
>>> apts[apts<50000]
guangzhou 25000
shenzhen 40000
dtype: int64
>>> 'beijing' in apts #Check if the element is in the Series
True
>>> apts[apts.isnull()] #View elements whose value is null
Series([], dtype: int64)
>>> apts[apts.notnull()] #View elements whose value is not null
beijing 55000
guangzhou 25000
shanghai 60000
shenzhen 40000
dtype: int64
2. DataFrame
A DataFrame is a table, a Series is a one-dimensional array, and a DataFrame is a two-dimensional array
>>> import pandas as pd
>>> import numpy as np
>>> data = {'cities':['beijing','shanghai','guangzhou','shenzhen'],'years':[2014,2015,2016,2017],'population':[1000,2000,3000,4000]}
>>> type(pd.DataFrame(data))
<class 'pandas.core.frame.DataFrame'>
>>> pd.DataFrame(data) #DataFrame initialization
cities population years
0 beijing 1000 2014
1 shanghai 2000 2015
2 guangzhou 3000 2016
3 shenzhen 4000 2017
>>> pd.DataFrame(data,columns=['years','cities','population'])#Specify the order of columns
years cities population
0 2014 beijing 1000
1 2015 shanghai 2000
2 2016 guangzhou 3000
3 2017 shenzhen 4000
>>> pd.DataFrame(data,columns=['years','cities','population'],index=['one','two','three','foue'])#Modify the name of the row
years cities population
one 2014 beijing 1000
two 2015 shanghai 2000
three 2016 guangzhou 3000
foue 2017 shenzhen 4000
>>> frame2 = pd.DataFrame(data,columns=['years','cities','population'],index=['one','two','three','foue'])
>>> frame2
years cities population
one 2014 beijing 1000
two 2015 shanghai 2000
three 2016 guangzhou 3000
foue 2017 shenzhen 4000
>>> frame2['cities']#Remove a column
one beijing
two shanghai
three guangzhou
foue shenzhen
Name: cities, dtype: object
>>> frame2.cities
one beijing
two shanghai
three guangzhou
foue shenzhen
Name: cities, dtype: object
>>> frame2.ix['three']# Take out a row
years 2016
cities guangzhou
population 3000
Name: three, dtype: object
>>> frame2.ix[2]
years 2016
cities guangzhou
population 3000
Name: three, dtype: object
>>> frame2['cities']['one'] = 'zhuhai'#Modify an element
Warning (from warnings module):
File "__main__", line 1
SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame
See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
>>> frame2
years cities population
one 2014 zhuhai 1000
two 2015 shanghai 2000
three 2016 guangzhou 3000
foue 2017 shenzhen 4000
>>> frame2['population'] = 1#Modify a whole column
>>> frame2
years cities population
one 2014 zhuhai 1
two 2015 shanghai 1
three 2016 guangzhou 1
foue 2017 shenzhen 1
>>> frame2.ix['five'] = 1#Modify a whole line
>>> frame2
years cities population
one 2014 zhuhai 1
two 2015 shanghai 1
three 2016 guangzhou 1
foue 2017 shenzhen 1
five 1 1 1
>>> frame2.ix['one'] = 2
>>> frame2
years cities population
one 2 2 2
two 2015 shanghai 1
three 2016 guangzhou 1
foue 2017 shenzhen 1
five 1 1 1
>>> frame2.years = np.arange(5)#Use a generator to modify a column
>>> frame2
years cities population
one 0 2 2
two 1 shanghai 1
three 2 guangzhou 1
foue 3 shenzhen 1
five 4 1 1
>>> val = pd.Series([200,300,500],index=['two','three','five'])
>>> frame2['population'] = val#Use a Series to modify a column
>>> frame2
years cities population
one 0 2 NaN
two 1 shanghai 200.0
three 2 guangzhou 300.0
foue 3 shenzhen NaN
five 4 1 500.0
>>> frame2.columns
Index(['years', 'cities', 'population'], dtype='object')
>>> frame2.index
Index(['one', 'two', 'three', 'foue', 'five'], dtype='object')
>>> frame2.T#transpose
one two three foue five
years 0 1 2 3 4
cities 2 shanghai guangzhou shenzhen 1
population NaN 200 300 NaN 500
>>> frame2['cities'][1:2]#Use slices to get elements
two shanghai
Name: cities, dtype: object
>>>
3. Index
Some operations on index
>>> import pandas as pd
>>> import numpy as np
>>> obj = pd.Series(range(3))
>>> obj
0 0
1 1
2 2
dtype: int64
>>> obj = pd.Series(range(3),index=['a','b','c'])
>>> obj
a 0
b 1
c 2
dtype: int64
>>> obj[[0,2]]
a 0
c 2
dtype: int64
>>> obj[0:2]
a 0
b 1
dtype: int64
>>> obj['a':'c']
a 0
b 1
c 2
dtype: int64
>>> obj['a':'c'] = 3
>>> obj
a 3
b 3
c 3
dtype: int64
>>> frame = pd.DataFrame(np.arange(9).reshape(3,3),index = ['a','b','c'],columns=['beijing','shanghai','guangzhou'])
>>> frame
beijing shanghai guangzhou
a 0 1 2
b 3 4 5
c 6 7 8
>>> frame.ix['a':'c']
beijing shanghai guangzhou
a 0 1 2
b 3 4 5
c 6 7 8
>>> frame.ix[['a','c'],['beijing','guangzhou']]
beijing guangzhou
a 0 2
c 6 8
>>> frame.ix[:,'beijing':'guangzhou']
beijing shanghai guangzhou
a 0 1 2
b 3 4 5
c 6 7 8
>>> frame.reindex(['e','f','g','h'])
beijing shanghai guangzhou
e NaN NaN NaN
f NaN NaN NaN
g NaN NaN NaN
h NaN NaN NaN
>>> frame
beijing shanghai guangzhou
a 0 1 2
b 3 4 5
c 6 7 8
>>> frame.drop('a')
beijing shanghai guangzhou
b 3 4 5
c 6 7 8
>>> frame
beijing shanghai guangzhou
a 0 1 2
b 3 4 5
c 6 7 8
>>> frame = frame.drop('a')
>>> frame
beijing shanghai guangzhou
b 3 4 5
c 6 7 8
>>> data = pd.Series(np.random.randn(10),index=[['a','a','a','b','b','c','c','c','d','d'],[1,2,3,1,2,1,2,3,1,2]])
>>> data
a 1 -0.060544
2 -1.680403
3 0.408582
b 1 1.001766
2 1.320155
c 1 -1.125726
2 1.508404
3 0.640139
d 1 0.824988
2 0.148888
dtype: float64
>>> data.index
MultiIndex(levels=[['a', 'b', 'c', 'd'], [1, 2, 3]],
labels=[[0, 0, 0, 1, 1, 2, 2, 2, 3, 3], [0, 1, 2, 0, 1, 0, 1, 2, 0, 1]])
>>> data['b':'d']
b 1 1.001766
2 1.320155
c 1 -1.125726
2 1.508404
3 0.640139
d 1 0.824988
2 0.148888
dtype: float64
>>> data[1:4]
a 2 -1.680403
3 0.408582
b 1 1.001766
dtype: float64
>>> data.unstack()
1 2 3
a -0.060544 -1.680403 0.408582
b 1.001766 1.320155 NaN
c -1.125726 1.508404 0.640139
d 0.824988 0.148888 NaN
>>> data.unstack().stack()
a 1 -0.060544
2 -1.680403
3 0.408582
b 1 1.001766
2 1.320155
c 1 -1.125726
2 1.508404
3 0.640139
d 1 0.824988
2 0.148888
dtype: float64
>>>