In [8]:

    

import pandas as pd


    

    




/usr/local/lib/python2.7/dist-packages/pandas-0.13.1-py2.7-linux-i686.egg/pandas/io/gbq.py:10: UserWarning: Module PIL was already imported from /usr/lib/python2.7/dist-packages/PIL/__init__.pyc, but /usr/local/lib/python2.7/dist-packages is being added to sys.path
  import pkg_resources

In [5]:

    

cd "/home/bakuda/pandas-book/"


    

    




/home/bakuda/pandas-book

In [6]:

    

ls


    

    




ch02/  ch03/  ch06/  ch07/  ch08/  ch09/  ch11/  ch13/  flights.csv

In [9]:

    

df = pd.read_csv('ch06/ex1.csv')


    

In [10]:

    

df.shape


    

    
Out[10]:





(3, 5)

In [11]:

    

df


    

    
Out[11]:






  

    

      

      
a
      
b
      
c
      
d
      
message
    
  
  

    

      
0
      
 1
      
  2
      
  3
      
  4
      
 hello
    
    

      
1
      
 5
      
  6
      
  7
      
  8
      
 world
    
    

      
2
      
 9
      
 10
      
 11
      
 12
      
   foo
    
  

3 rows × 5 columns

In [15]:

    

#OR 
#df = pd.read_table('ch06/ex1.csv', sep=',')


    

In [17]:

    

pd.read_csv('ch06/ex2.csv', header=None)


    

    
Out[17]:






  

    

      

      
0
      
1
      
2
      
3
      
4
    
  
  

    

      
0
      
 1
      
  2
      
  3
      
  4
      
 hello
    
    

      
1
      
 5
      
  6
      
  7
      
  8
      
 world
    
    

      
2
      
 9
      
 10
      
 11
      
 12
      
   foo
    
  

3 rows × 5 columns

In [18]:

    

!cat ch06/ex2.csv


    

    




1,2,3,4,hello
5,6,7,8,world
9,10,11,12,foo

In [19]:

    

pd.read_csv('ch06/ex2.csv', names=['a', 'b', 'c', 'd', 'message'])


    

    
Out[19]:






  

    

      

      
a
      
b
      
c
      
d
      
message
    
  
  

    

      
0
      
 1
      
  2
      
  3
      
  4
      
 hello
    
    

      
1
      
 5
      
  6
      
  7
      
  8
      
 world
    
    

      
2
      
 9
      
 10
      
 11
      
 12
      
   foo
    
  

3 rows × 5 columns

In [20]:

    

names = ['a', 'b', 'c', 'd', 'message']


    

In [24]:

    

pd.read_csv('ch06/ex2.csv', names=names, index_col=4)
# OR
#pd.read_csv('ch06/ex2.csv', names=names, index_col='message')


    

    
Out[24]:






  

    

      

      
a
      
b
      
c
      
d
    
    

      
message
      

      

      

      

    
  
  

    

      
hello
      
 1
      
  2
      
  3
      
  4
    
    

      
world
      
 5
      
  6
      
  7
      
  8
    
    

      
foo
      
 9
      
 10
      
 11
      
 12
    
  

3 rows × 4 columns

In [25]:

    

parsed = pd.read_csv('ch06/csv_mindex.csv', index_col=['key1', 'key2'])


    

In [26]:

    

parsed


    

    
Out[26]:






  

    

      

      

      
value1
      
value2
    
    

      
key1
      
key2
      

      

    
  
  

    

      
one
      
a
      
  1
      
  2
    
    

      
b
      
  3
      
  4
    
    

      
c
      
  5
      
  6
    
    

      
d
      
  7
      
  8
    
    

      
two
      
a
      
  9
      
 10
    
    

      
b
      
 11
      
 12
    
    

      
c
      
 13
      
 14
    
    

      
d
      
 15
      
 16
    
  

8 rows × 2 columns

In [27]:

    

!cat ch06/csv_mindex.csv


    

    




key1,key2,value1,value2
one,a,1,2
one,b,3,4
one,c,5,6
one,d,7,8
two,a,9,10
two,b,11,12
two,c,13,14
two,d,15,16

In [28]:

    

list(open('ch06/ex3.txt'))


    

    
Out[28]:





['            A         B         C\n',
 'aaa -0.264438 -1.026059 -0.619500\n',
 'bbb  0.927272  0.302904 -0.032399\n',
 'ccc -0.264273 -0.386314 -0.217601\n',
 'ddd -0.871858 -0.348382  1.100491\n']

In [30]:

    

!cat ch06/ex3.txt


    

    




            A         B         C
aaa -0.264438 -1.026059 -0.619500
bbb  0.927272  0.302904 -0.032399
ccc -0.264273 -0.386314 -0.217601
ddd -0.871858 -0.348382  1.100491

In [35]:

    

pd.read_csv('ch06/ex3.txt', sep='\s+')


    

    
Out[35]:






  

    

      

      
A
      
B
      
C
    
  
  

    

      
aaa
      
-0.264438
      
-1.026059
      
-0.619500
    
    

      
bbb
      
 0.927272
      
 0.302904
      
-0.032399
    
    

      
ccc
      
-0.264273
      
-0.386314
      
-0.217601
    
    

      
ddd
      
-0.871858
      
-0.348382
      
 1.100491
    
  

4 rows × 3 columns

In [39]:

    

#reading nrows number of nows at a time
pd.read_csv('ch06/ex6.csv', nrows=4)


    

    
Out[39]:






  

    

      

      
one
      
two
      
three
      
four
      
key
    
  
  

    

      
0
      
 0.467976
      
-0.038649
      
-0.295344
      
-1.824726
      
 L
    
    

      
1
      
-0.358893
      
 1.404453
      
 0.704965
      
-0.200638
      
 B
    
    

      
2
      
-0.501840
      
 0.659254
      
-0.421691
      
-0.057688
      
 G
    
    

      
3
      
 0.204886
      
 1.074134
      
 1.388361
      
-0.982404
      
 R
    
  

4 rows × 5 columns

In [50]:

    

chunker = pd.read_csv('ch06/ex6.csv', chunksize=1000)
tot = pd.Series([])
for i, piece in enumerate(chunker):
    #print 'chunker %d' %(i)
    tot = tot.add(piece['key'].value_counts(), fill_value=0)
    #print piece['key'].value_counts()
tot = tot.order(ascending=False)


    

In [51]:

    

#tot


    

In [ ]: