In [19]:

    

import numpy as np
import pandas as pd
from pandas import Series, DataFrame


    

In [2]:

    

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


    

In [3]:

    

obj


    

    
Out[3]:





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

In [4]:

    

obj.values


    

    
Out[4]:





array([ 4,  7, -5,  3])

In [5]:

    

obj.index


    

    
Out[5]:





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

In [6]:

    

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


    

In [7]:

    

obj2


    

    
Out[7]:





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

In [8]:

    

obj2.index


    

    
Out[8]:





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

In [9]:

    

obj2["a"]


    

    
Out[9]:





-5

In [10]:

    

obj[2]


    

    
Out[10]:





-5

In [11]:

    

obj2["d"] = 6


    

In [12]:

    

obj2


    

    
Out[12]:





d    6
b    7
a   -5
c    3
dtype: int64

In [14]:

    

obj2[["c", "a", "d"]]


    

    
Out[14]:





c    3
a   -5
d    6
dtype: int64

In [15]:

    

obj2


    

    
Out[15]:





d    6
b    7
a   -5
c    3
dtype: int64

In [16]:

    

obj2[obj2 > 0]


    

    
Out[16]:





d    6
b    7
c    3
dtype: int64

In [17]:

    

obj2 * 2


    

    
Out[17]:





d    12
b    14
a   -10
c     6
dtype: int64

In [20]:

    

np.exp(obj2)


    

    
Out[20]:





d     403.428793
b    1096.633158
a       0.006738
c      20.085537
dtype: float64

In [21]:

    

"b" in obj2


    

    
Out[21]:





True

In [22]:

    

"e" in obj2


    

    
Out[22]:





False

In [23]:

    

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


    

In [24]:

    

obj3 = Series(sdata)


    

In [25]:

    

obj3


    

    
Out[25]:





Ohio      35000
Oregon    16000
Texas     71000
Utah       5000
dtype: int64

In [26]:

    

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


    

In [27]:

    

obj4 = Series(sdata, index=states)


    

In [28]:

    

obj4


    

    
Out[28]:





California      NaN
Ohio          35000
Oregon        16000
Texas         71000
dtype: float64

In [29]:

    

pd.isnull(obj4)


    

    
Out[29]:





California     True
Ohio          False
Oregon        False
Texas         False
dtype: bool

In [30]:

    

pd.notnull(obj4)


    

    
Out[30]:





California    False
Ohio           True
Oregon         True
Texas          True
dtype: bool

In [31]:

    

obj4.isnull()


    

    
Out[31]:





California     True
Ohio          False
Oregon        False
Texas         False
dtype: bool

In [32]:

    

obj3


    

    
Out[32]:





Ohio      35000
Oregon    16000
Texas     71000
Utah       5000
dtype: int64

In [33]:

    

obj4


    

    
Out[33]:





California      NaN
Ohio          35000
Oregon        16000
Texas         71000
dtype: float64

In [37]:

    

obj3 + obj4


    

    
Out[37]:





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

In [40]:

    

obj4.name = "population"


    

In [41]:

    

obj4.index.name = "state"


    

In [42]:

    

obj4


    

    
Out[42]:





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

In [43]:

    

obj.index = ["Bob", "Steve", "Jeff", "Ryan"]


    

In [44]:

    

obj


    

    
Out[44]:





Bob      4
Steve    7
Jeff    -5
Ryan     3
dtype: int64

In [45]:

    

data = {"state": ["Ohio", "Ohio", "Ohio", "Nevada", "Nevada"],
        "year": [2000, 2001, 2002, 2001, 2002],
        "pop": [1.5, 1.7, 3.6, 2.4, 2.9]}
frame = DataFrame(data)


    

In [46]:

    

frame


    

    
Out[46]:






  

    

      

      
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
    
  

5 rows × 3 columns

In [47]:

    

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


    

    
Out[47]:






  

    

      

      
year
      
state
      
pop
    
  
  

    

      
0
      
 2000
      
   Ohio
      
 1.5
    
    

      
1
      
 2001
      
   Ohio
      
 1.7
    
    

      
2
      
 2002
      
   Ohio
      
 3.6
    
    

      
3
      
 2001
      
 Nevada
      
 2.4
    
    

      
4
      
 2002
      
 Nevada
      
 2.9
    
  

5 rows × 3 columns

In [48]:

    

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


    

In [49]:

    

frame2


    

    
Out[49]:






  

    

      

      
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
    
  

5 rows × 4 columns

In [50]:

    

frame2.columns


    

    
Out[50]:





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

In [51]:

    

frame2["state"]


    

    
Out[51]:





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

In [53]:

    

frame2.year


    

    
Out[53]:





one      2000
two      2001
three    2002
four     2001
five     2002
Name: year, dtype: int64

In [54]:

    

frame2.ix["three"]


    

    
Out[54]:





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

In [56]:

    

frame2["debt"] = 16.5


    

In [57]:

    

frame2


    

    
Out[57]:






  

    

      

      
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
    
  

5 rows × 4 columns

In [58]:

    

frame2.debt = np.arange(5.)


    

In [59]:

    

frame2


    

    
Out[59]:






  

    

      

      
year
      
state
      
pop
      
debt
    
  
  

    

      
one
      
 2000
      
   Ohio
      
 1.5
      
 0
    
    

      
two
      
 2001
      
   Ohio
      
 1.7
      
 1
    
    

      
three
      
 2002
      
   Ohio
      
 3.6
      
 2
    
    

      
four
      
 2001
      
 Nevada
      
 2.4
      
 3
    
    

      
five
      
 2002
      
 Nevada
      
 2.9
      
 4
    
  

5 rows × 4 columns

In [60]:

    

val = Series([-1.2, -1.5, -1.7], index=["two", "four", "five"])


    

In [66]:

    

frame2["debt"] = val


    

In [67]:

    

frame2


    

    
Out[67]:






  

    

      

      
year
      
state
      
pop
      
debt
    
  
  

    

      
one
      
 2000
      
   Ohio
      
 1.5
      
 NaN
    
    

      
two
      
 2001
      
   Ohio
      
 1.7
      
-1.2
    
    

      
three
      
 2002
      
   Ohio
      
 3.6
      
 NaN
    
    

      
four
      
 2001
      
 Nevada
      
 2.4
      
-1.5
    
    

      
five
      
 2002
      
 Nevada
      
 2.9
      
-1.7
    
  

5 rows × 4 columns

In [68]:

    

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


    

In [69]:

    

frame2


    

    
Out[69]:






  

    

      

      
year
      
state
      
pop
      
debt
      
eastern
    
  
  

    

      
one
      
 2000
      
   Ohio
      
 1.5
      
 NaN
      
  True
    
    

      
two
      
 2001
      
   Ohio
      
 1.7
      
-1.2
      
  True
    
    

      
three
      
 2002
      
   Ohio
      
 3.6
      
 NaN
      
  True
    
    

      
four
      
 2001
      
 Nevada
      
 2.4
      
-1.5
      
 False
    
    

      
five
      
 2002
      
 Nevada
      
 2.9
      
-1.7
      
 False
    
  

5 rows × 5 columns

In [70]:

    

del frame2["eastern"]


    

In [71]:

    

frame2.columns


    

    
Out[71]:





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

In [72]:

    

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


    

In [73]:

    

frame3 = DataFrame(pop)


    

In [75]:

    

frame3


    

    
Out[75]:






  

    

      

      
Nevada
      
Ohio
    
  
  

    

      
2000
      
 NaN
      
 1.5
    
    

      
2001
      
 2.4
      
 1.7
    
    

      
2002
      
 2.9
      
 3.6
    
  

3 rows × 2 columns

In [78]:

    

frame3.T


    

    
Out[78]:






  

    

      

      
2000
      
2001
      
2002
    
  
  

    

      
Nevada
      
 NaN
      
 2.4
      
 2.9
    
    

      
Ohio
      
 1.5
      
 1.7
      
 3.6
    
  

2 rows × 3 columns

In [79]:

    

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


    

    
Out[79]:






  

    

      

      
Nevada
      
Ohio
    
  
  

    

      
2001
      
 2.4
      
 1.7
    
    

      
2002
      
 2.9
      
 3.6
    
    

      
2003
      
 NaN
      
 NaN
    
  

3 rows × 2 columns

In [80]:

    

pdata = {"Ohio": frame3["Ohio"][:-1],
         "Nevada": frame3["Nevada"][:2]}


    

In [82]:

    

DataFrame(pdata)


    

    
Out[82]:






  

    

      

      
Nevada
      
Ohio
    
  
  

    

      
2000
      
 NaN
      
 1.5
    
    

      
2001
      
 2.4
      
 1.7
    
  

2 rows × 2 columns

In [83]:

    

frame3.index.name = "year"
frame3.columns.name = "state"


    

In [84]:

    

frame3


    

    
Out[84]:






  

    

      
state
      
Nevada
      
Ohio
    
    

      
year
      

      

    
  
  

    

      
2000
      
 NaN
      
 1.5
    
    

      
2001
      
 2.4
      
 1.7
    
    

      
2002
      
 2.9
      
 3.6
    
  

3 rows × 2 columns

In [85]:

    

frame3.values


    

    
Out[85]:





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

In [86]:

    

frame2.values


    

    
Out[86]:





array([[2000, 'Ohio', 1.5, nan],
       [2001, 'Ohio', 1.7, -1.2],
       [2002, 'Ohio', 3.6, nan],
       [2001, 'Nevada', 2.4, -1.5],
       [2002, 'Nevada', 2.9, -1.7]], dtype=object)

In [87]:

    

obj = Series(range(3), index=["a", "b", "c"])


    

In [88]:

    

index = obj.index


    

In [89]:

    

index


    

    
Out[89]:





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

In [90]:

    

index[1:]


    

    
Out[90]:





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

In [91]:

    

index[1] = "d"


    

    




---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-91-092906bbf8a9> in <module>()
----> 1 index[1] = "d"

/Users/jlhudd/anaconda/lib/python2.7/site-packages/pandas/core/base.pyc in _disabled(self, *args, **kwargs)
    178         """This method will not function because object is immutable."""
    179         raise TypeError("'%s' does not support mutable operations." %
--> 180                         self.__class__)
    181 
    182     __setitem__ = __setslice__ = __delitem__ = __delslice__ = _disabled

TypeError: '<class 'pandas.core.index.Index'>' does not support mutable operations.

In [92]:

    

index = pd.Index(np.arange(3))


    

In [93]:

    

index


    

    
Out[93]:





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

In [94]:

    

obj2 = Series([1.5, -2.5, 0], index=index)


    

In [95]:

    

obj2


    

    
Out[95]:





0    1.5
1   -2.5
2    0.0
dtype: float64

In [96]:

    

obj2.index is index


    

    
Out[96]:





True

In [97]:

    

frame3


    

    
Out[97]:






  

    

      
state
      
Nevada
      
Ohio
    
    

      
year
      

      

    
  
  

    

      
2000
      
 NaN
      
 1.5
    
    

      
2001
      
 2.4
      
 1.7
    
    

      
2002
      
 2.9
      
 3.6
    
  

3 rows × 2 columns

In [98]:

    

"Ohio" in frame3.columns


    

    
Out[98]:





True

In [99]:

    

2003 in frame3.index


    

    
Out[99]:





False

In [107]:

    

obj = Series([4.5, 7.2, -5.3, 3.6], index=["d", "b", "a", "c"])


    

In [108]:

    

obj


    

    
Out[108]:





d    4.5
b    7.2
a   -5.3
c    3.6
dtype: float64

In [109]:

    

obj2 = obj.reindex(["a", "b", "c", "d", "e"])


    

In [110]:

    

obj2


    

    
Out[110]:





a   -5.3
b    7.2
c    3.6
d    4.5
e    NaN
dtype: float64

In [111]:

    

obj.reindex(["a", "b", "c", "d", "e"], fill_value=0)


    

    
Out[111]:





a   -5.3
b    7.2
c    3.6
d    4.5
e    0.0
dtype: float64

In [112]:

    

obj3 = Series(["blue", "purple", "yellow"], index=[0, 2, 4])


    

In [113]:

    

obj3.reindex(range(6), method="ffill")


    

    
Out[113]:





0      blue
1      blue
2    purple
3    purple
4    yellow
5    yellow
dtype: object

In [114]:

    

frame = DataFrame(np.arange(9).reshape((3, 3)), index=["a", "c", "d"], columns=["Ohio", "Texas", "California"])


    

In [115]:

    

frame


    

    
Out[115]:






  

    

      

      
Ohio
      
Texas
      
California
    
  
  

    

      
a
      
 0
      
 1
      
 2
    
    

      
c
      
 3
      
 4
      
 5
    
    

      
d
      
 6
      
 7
      
 8
    
  

3 rows × 3 columns

In [116]:

    

frame2 = frame.reindex(["a", "b", "c", "d"])


    

In [117]:

    

frame2


    

    
Out[117]:






  

    

      

      
Ohio
      
Texas
      
California
    
  
  

    

      
a
      
  0
      
  1
      
  2
    
    

      
b
      
NaN
      
NaN
      
NaN
    
    

      
c
      
  3
      
  4
      
  5
    
    

      
d
      
  6
      
  7
      
  8
    
  

4 rows × 3 columns

In [118]:

    

states = ["Texas", "Utah", "California"]


    

In [119]:

    

frame.reindex(columns=states)


    

    
Out[119]:






  

    

      

      
Texas
      
Utah
      
California
    
  
  

    

      
a
      
 1
      
NaN
      
 2
    
    

      
c
      
 4
      
NaN
      
 5
    
    

      
d
      
 7
      
NaN
      
 8
    
  

3 rows × 3 columns

In [120]:

    

frame.reindex(index=["a", "b", "c", "d"], method="ffill", columns=states)


    

    
Out[120]:






  

    

      

      
Texas
      
Utah
      
California
    
  
  

    

      
a
      
 1
      
NaN
      
 2
    
    

      
b
      
 1
      
NaN
      
 2
    
    

      
c
      
 4
      
NaN
      
 5
    
    

      
d
      
 7
      
NaN
      
 8
    
  

4 rows × 3 columns

In [121]:

    

frame.ix[["a", "b", "c", "d"], states]


    

    
Out[121]:






  

    

      

      
Texas
      
Utah
      
California
    
  
  

    

      
a
      
  1
      
NaN
      
  2
    
    

      
b
      
NaN
      
NaN
      
NaN
    
    

      
c
      
  4
      
NaN
      
  5
    
    

      
d
      
  7
      
NaN
      
  8
    
  

4 rows × 3 columns

In [ ]: