In [1]:

    

%matplotlib inline

from pandas import Series, DataFrame
import pandas as pd
import numpy as np
import matplotlib
from matplotlib import pyplot as plt
import seaborn as sns


    

    




---------------------------------------------------------------------------
ImportError                               Traceback (most recent call last)
<ipython-input-1-a41dc1103790> in <module>()
      6 import matplotlib
      7 from matplotlib import pyplot as plt
----> 8 import seaborn as sns

ImportError: No module named seaborn

In [44]:

    

url = 'https://en.wikipedia.org/wiki/List_of_countries_and_dependencies_by_population'
#countries = pd.read_html(url,skiprows=0,index_col=0,header=0,match='China')
countries = pd.read_html(url,header=0,index_col=1,match='China')
print len(countries)  
countries=countries[0]
countries[0:5]


    

    




1






    
Out[44]:






  

    

      

      
Rank
      
Population
      
Date
      
% of world population
      
Source
    
    

      
Country (or dependent territory)
      

      

      

      

      

    
  
  

    

      
China[Note 2]
      
1
      
1372780000
      
October 23, 2015
      
18.9%
      
Official population clock
    
    

      
India
      
2
      
1278980000
      
October 23, 2015
      
17.6%
      
Official population clock
    
    

      
United States[Note 3]
      
3
      
322082000
      
October 23, 2015
      
4.43%
      
Official population clock
    
    

      
Indonesia
      
4
      
257080000
      
October 11, 2015
      
3.53%
      
Official projection
    
    

      
Brazil
      
5
      
205084000
      
October 23, 2015
      
2.82%
      
Official population clock
    
  

In [45]:

    

countries.columns


    

    
Out[45]:





Index([u'Rank', u'Population', u'Date', u'% of world population', u'Source'], dtype='object')

In [46]:

    

type(countries)


    

    
Out[46]:





pandas.core.frame.DataFrame

In [54]:

    

df_toptten = DataFrame(countries[0:10],columns=['Population'])
df_toptten


    

    
Out[54]:






  

    

      

      
Population
    
    

      
Country (or dependent territory)
      

    
  
  

    

      
China[Note 2]
      
1372780000
    
    

      
India
      
1278980000
    
    

      
United States[Note 3]
      
322082000
    
    

      
Indonesia
      
257080000
    
    

      
Brazil
      
205084000
    
    

      
Pakistan
      
191165000
    
    

      
Nigeria
      
183541000
    
    

      
Bangladesh
      
159241000
    
    

      
Russia[Note 4]
      
146412580
    
    

      
Japan
      
126832000
    
  

In [55]:

    

df_toptten[0:10].plot(kind='bar')


    

    
Out[55]:





<matplotlib.axes._subplots.AxesSubplot at 0xda31198>






    

In [86]:

    

df = pd.DataFrame(countries[0:20],columns=[ '% of world population'],)
df['% of world population']=df['% of world population'].str.replace('%', '')
df['PercentNum'] = df['% of world population'].astype(float)
df['PercentNum'][0:10]


    

    
Out[86]:





Country (or dependent territory)
China[Note 2]            18.90
India                    17.60
United States[Note 3]     4.43
Indonesia                 3.53
Brazil                    2.82
Pakistan                  2.63
Nigeria                   2.50
Bangladesh                2.19
Russia[Note 4]            2.01
Japan                     1.74
Name: PercentNum, dtype: float64

In [85]:

    

plt.pie(df['PercentNum'][0:10])


    

    
Out[85]:





([<matplotlib.patches.Wedge at 0x22abf1d0>,
  <matplotlib.patches.Wedge at 0x22abfa90>,
  <matplotlib.patches.Wedge at 0x22b11320>,
  <matplotlib.patches.Wedge at 0x22b11b70>,
  <matplotlib.patches.Wedge at 0x22b1f400>,
  <matplotlib.patches.Wedge at 0x22b1fc50>,
  <matplotlib.patches.Wedge at 0x22b2c4e0>,
  <matplotlib.patches.Wedge at 0x22b2cd30>,
  <matplotlib.patches.Wedge at 0x22b3b5c0>,
  <matplotlib.patches.Wedge at 0x22b3be10>],
 [<matplotlib.text.Text at 0x22abf6d8>,
  <matplotlib.text.Text at 0x22abff60>,
  <matplotlib.text.Text at 0x22b117f0>,
  <matplotlib.text.Text at 0x22b11f98>,
  <matplotlib.text.Text at 0x22b1f8d0>,
  <matplotlib.text.Text at 0x22b2c160>,
  <matplotlib.text.Text at 0x22b2c9b0>,
  <matplotlib.text.Text at 0x22b3b240>,
  <matplotlib.text.Text at 0x22b3ba90>,
  <matplotlib.text.Text at 0x22c3f320>])






    

In [ ]: