In [1]:

    

import pandas as pd

years = range(1950,2013)

values = []
for year in years:
    names1986 = pd.read_csv('data/yob%s.txt' % year, names=['name','sex','births'])
    values.append(names1986.births[names1986.name=='Dmitri'].sum())


    

In [2]:

    

names1986.plot()


    

    
Out[2]:





<matplotlib.axes.AxesSubplot at 0x10d4fa950>






    

In [3]:

    

Dmitri = pd.Series(values,index=years)


    

In [4]:

    

Dmitri.plot()


    

    
Out[4]:





<matplotlib.axes.AxesSubplot at 0x10e58ad90>






    

In [50]:

    

Dmitri.head(10)


    

    
Out[50]:





1950     0
1951     0
1952     0
1953     0
1954     0
1955     8
1956    10
1957     0
1958     0
1959     9
dtype: int64

In [11]:

    

type(names1986.name[names1986.name == 'Dmitri'])


    

    
Out[11]:





pandas.core.series.Series

In [23]:

    

names1986.head()


    

    
Out[23]:






  

    

      

      
name
      
sex
      
births
    
  
  

    

      
0
      
  Jessica
      
 F
      
 52657
    
    

      
1
      
   Ashley
      
 F
      
 49674
    
    

      
2
      
   Amanda
      
 F
      
 40519
    
    

      
3
      
 Jennifer
      
 F
      
 36173
    
    

      
4
      
    Sarah
      
 F
      
 28134
    
  

In [24]:

    

names1986.ix[10]


    

    
Out[24]:





name      Megan
sex           F
births    18592
Name: 10, dtype: object

In [26]:

    

pieces = []
for year in range(1880,2011):
    path = 'data/yob%s.txt' % year
    frame = pd.read_csv(path, names = ['name','sex','births'])
    frame['year'] = year
    pieces.append(frame)
names = pd.concat(pieces, ignore_index=True)


    

In [27]:

    

names.count()


    

    
Out[27]:





name      1691357
sex       1691357
births    1691357
year      1691357
dtype: int64

In [29]:

    

glory = names[names.name=='Dmitri']


    

In [32]:

    

total_births = names.pivot_table('births',rows = 'year',cols = 'sex',aggfunc = sum)


    

In [33]:

    

total_births


    

    
Out[33]:




<class 'pandas.core.frame.DataFrame'>
Int64Index: 131 entries, 1880 to 2010
Data columns (total 2 columns):
F    131  non-null values
M    131  non-null values
dtypes: int64(2)

In [34]:

    

total_births.head()


    

    
Out[34]:






  

    

      
sex
      
F
      
M
    
    

      
year
      

      

    
  
  

    

      
1880
      
  90993
      
 110491
    
    

      
1881
      
  91955
      
 100746
    
    

      
1882
      
 107850
      
 113687
    
    

      
1883
      
 112322
      
 104630
    
    

      
1884
      
 129022
      
 114445
    
  

In [47]:

    

geo = pd.Series(['Uchaly','Ufa','Moskva','Vancouver','Ottawa'], index = [1986,1986,2003,2005,2014])


    

In [48]:

    

geo


    

    
Out[48]:





1986       Uchaly
1986          Ufa
2003       Moskva
2005    Vancouver
2014       Ottawa
dtype: object

In [43]:

    

geo.values


    

    
Out[43]:





array(['Uchaly', 'Ufa', 'Moskva', 'Vancouver', 'Ottawa'], dtype=object)

In [44]:

    

geo.index


    

    
Out[44]:





Int64Index([1987, 1986, 2003, 2005, 2014], dtype=int64)

In [53]:

    

geo[geo == 'Ufa']


    

    
Out[53]:





1986    Ufa
dtype: object

In [ ]:

    

names.