notebook.community

Edit and run



In [1]:

    
from pandas import Series, DataFrame



In [42]:

    
import pandas as pd
import numpy as np



In [3]:

    
obj = Series([4, 7, -5, 3])



In [4]:

    
obj









    Out[4]:





0    4
1    7
2   -5
3    3
dtype: int64



In [5]:

    
obj.values









    Out[5]:





array([ 4,  7, -5,  3], dtype=int64)



In [6]:

    
obj.index









    Out[6]:





Int64Index([0, 1, 2, 3], dtype='int64')



In [7]:

    
obj2 = Series([4, 7, -5, 3], index=['d', 'b', 'a', 'c'])



In [8]:

    
obj2









    Out[8]:





d    4
b    7
a   -5
c    3
dtype: int64



In [9]:

    
obj2.index









    Out[9]:





Index([u'd', u'b', u'a', u'c'], dtype='object')



In [10]:

    
obj2['a']









    Out[10]:





-5



In [11]:

    
obj2









    Out[11]:





d    4
b    7
a   -5
c    3
dtype: int64



In [12]:

    
obj2[obj2 > 0]









    Out[12]:





d    4
b    7
c    3
dtype: int64



In [13]:

    
obj2 * 2









    Out[13]:





d     8
b    14
a   -10
c     6
dtype: int64



In [14]:

    
sdata = {'Ohio': 35000, 'Texas': 71000, 'Oregon': 16000, 'Utah': 5000}



In [15]:

    
obj3 = Series(sdata)



In [16]:

    
obj3









    Out[16]:





Ohio      35000
Oregon    16000
Texas     71000
Utah       5000
dtype: int64



In [17]:

    
states = ['California', 'Ohio', 'Oregon', 'Texas']



In [18]:

    
obj4 = Series(sdata, index=states)



In [19]:

    
obj4









    Out[19]:





California      NaN
Ohio          35000
Oregon        16000
Texas         71000
dtype: float64



In [20]:

    
pd.isnull(obj4)









    Out[20]:





California     True
Ohio          False
Oregon        False
Texas         False
dtype: bool



In [21]:

    
pd.notnull(obj4)









    Out[21]:





California    False
Ohio           True
Oregon         True
Texas          True
dtype: bool



In [22]:

    
obj4.isnull()









    Out[22]:





California     True
Ohio          False
Oregon        False
Texas         False
dtype: bool



In [23]:

    
obj3 + obj4









    Out[23]:





California       NaN
Ohio           70000
Oregon         32000
Texas         142000
Utah             NaN
dtype: float64



In [24]:

    
obj4.name = 'population'



In [25]:

    
obj4.index.name = 'state'



In [26]:

    
obj4









    Out[26]:





state
California      NaN
Ohio          35000
Oregon        16000
Texas         71000
Name: population, dtype: float64



In [27]:

    
data = {'state': ['Ohio', 'Ohio', 'Ohio', 'Nevada', 'Nevada'],
'year': [2000, 2001, 2002, 2001, 2002],
'pop': [1.5, 1.7, 3.6, 2.4, 2.9]}



In [28]:

    
frame = DataFrame(data)



In [29]:

    
frame



In [30]:

    
DataFrame(data, columns=['year', 'state', 'pop'])



In [31]:

    
frame2 = DataFrame(data, columns=['year', 'state', 'pop', 'debt'],
              index=['one', 'two', 'three', 'four', 'five'])



In [32]:

    
frame2









    Out[32]:






  
    
      
      year
      state
      pop
      debt
    
  
  
    
      one
      2000
      Ohio
      1.5
      NaN
    
    
      two
      2001
      Ohio
      1.7
      NaN
    
    
      three
      2002
      Ohio
      3.6
      NaN
    
    
      four
      2001
      Nevada
      2.4
      NaN
    
    
      five
      2002
      Nevada
      2.9
      NaN



In [33]:

    
frame2.columns









    Out[33]:





Index([u'year', u'state', u'pop', u'debt'], dtype='object')



In [34]:

    
frame2['state']









    Out[34]:





one        Ohio
two        Ohio
three      Ohio
four     Nevada
five     Nevada
Name: state, dtype: object



In [36]:

    
frame2.state









    Out[36]:





one        Ohio
two        Ohio
three      Ohio
four     Nevada
five     Nevada
Name: state, dtype: object



In [37]:

    
frame2.ix['three']









    Out[37]:





year     2002
state    Ohio
pop       3.6
debt      NaN
Name: three, dtype: object



In [38]:

    
frame2['debt'] = 16.5



In [39]:

    
frame2



In [43]:

    
frame2['debt'] = np.arange(5.)



In [44]:

    
frame2



In [45]:

    
frame2['eastern'] = frame2.state == 'Ohio'



In [46]:

    
frame2









    Out[46]:






  
    
      
      year
      state
      pop
      debt
      eastern
    
  
  
    
      one
      2000
      Ohio
      1.5
      0
      True
    
    
      two
      2001
      Ohio
      1.7
      1
      True
    
    
      three
      2002
      Ohio
      3.6
      2
      True
    
    
      four
      2001
      Nevada
      2.4
      3
      False
    
    
      five
      2002
      Nevada
      2.9
      4
      False



In [47]:

    
del frame2['eastern']



In [48]:

    
frame2.columns









    Out[48]:





Index([u'year', u'state', u'pop', u'debt'], dtype='object')



In [49]:

    
pop = {'Nevada': {2001: 2.4, 2002: 2.9}, 'Ohio': {2000: 1.5, 2001: 1.7, 2002: 3.6}}



In [50]:

    
frame3 = DataFrame(pop)



In [51]:

    
pop









    Out[51]:





{'Nevada': {2001: 2.4, 2002: 2.9}, 'Ohio': {2000: 1.5, 2001: 1.7, 2002: 3.6}}



In [52]:

    
frame3



In [53]:

    
frame3.T



In [54]:

    
DataFrame(pop, index=[2001, 2002, 2003])



In [55]:

    
frame3.values









    Out[55]:





array([[ nan,  1.5],
       [ 2.4,  1.7],
       [ 2.9,  3.6]])



In [56]:

    
frame2.values









    Out[56]:





array([[2000L, 'Ohio', 1.5, 0.0],
       [2001L, 'Ohio', 1.7, 1.0],
       [2002L, 'Ohio', 3.6, 2.0],
       [2001L, 'Nevada', 2.4, 3.0],
       [2002L, 'Nevada', 2.9, 4.0]], dtype=object)



In [ ]:

	pop	state	year
0	1.5	Ohio	2000
1	1.7	Ohio	2001
2	3.6	Ohio	2002
3	2.4	Nevada	2001
4	2.9	Nevada	2002

	year	state	pop	debt
one	2000	Ohio	1.5	16.5
two	2001	Ohio	1.7	16.5
three	2002	Ohio	3.6	16.5
four	2001	Nevada	2.4	16.5
five	2002	Nevada	2.9	16.5

	year	state	pop	debt	eastern
one	2000	Ohio	1.5	0	True
two	2001	Ohio	1.7	1	True
three	2002	Ohio	3.6	2	True
four	2001	Nevada	2.4	3	False
five	2002	Nevada	2.9	4	False