In [1]:

    

import matplotlib
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import sklearn


    

In [2]:

    

gdp_per_capita = pd.read_csv("https://raw.githubusercontent.com/ageron/handson-ml/master/datasets/lifesat/gdp_per_capita.csv",thousands=',',delimiter='\t',
                             encoding='latin1', na_values="n/a")


    

In [3]:

    

gdp_per_capita.rename(columns={"2015": "GDP per capita"}, inplace=True)
gdp_per_capita.set_index("Country", inplace=True)
gdp_per_capita = gdp_per_capita[['GDP per capita','Estimates Start After']]
gdp_per_capita.head(2)


    

    
Out[3]:







  

    

      

      
GDP per capita
      
Estimates Start After
    
    

      
Country
      

      

    
  
  

    

      
Afghanistan
      
599.994
      
2013.0
    
    

      
Albania
      
3995.383
      
2010.0
    
  

In [4]:

    

gdp_per_capita.sort_values(by='GDP per capita', ascending=False).head(3)


    

    
Out[4]:







  

    

      

      
GDP per capita
      
Estimates Start After
    
    

      
Country
      

      

    
  
  

    

      
Luxembourg
      
101994.093
      
2014.0
    
    

      
Switzerland
      
80675.308
      
2015.0
    
    

      
Qatar
      
76576.080
      
2014.0
    
  

In [5]:

    

# remove extra line
gdp_per_capita = gdp_per_capita.drop('International Monetary Fund, World Economic Outlook Database, April 2016')


    

In [6]:

    

gdp_per_capita.sort_values(by='GDP per capita', ascending=False).tail(5)


    

    
Out[6]:







  

    

      

      
GDP per capita
      
Estimates Start After
    
    

      
Country
      

      

    
  
  

    

      
Central African Republic
      
334.870
      
2004.0
    
    

      
Burundi
      
305.783
      
0.0
    
    

      
South Sudan
      
220.860
      
2008.0
    
    

      
Kosovo
      
NaN
      
NaN
    
    

      
Syria
      
NaN
      
2010.0