Work in Progress



In [1]:

    
# read population in
import json
import requests
from pandas import DataFrame

# pop_json_url holds a 
pop_json_url = "https://gist.github.com/rdhyee/8511607/raw/f16257434352916574473e63612fcea55a0c1b1c/population_of_countries.json"
pop_list= requests.get(pop_json_url).json()

df = DataFrame(pop_list)
df[:5]









    Out[1]:






  
    
      
      0
      1
      2
    
  
  
    
      0
       1
               China
       1385566537
    
    
      1
       2
               India
       1252139596
    
    
      2
       3
       United States
        320050716
    
    
      3
       4
           Indonesia
        249865631
    
    
      4
       5
              Brazil
        200361925
    
  

5 rows × 3 columns

Q: What is the relationship between s and the population of China?

s = sum(df[df[1].str.startswith('C')][2])

s is greater than the population of China
s is the same as the population of China
s is less than the population of China
s is not a number.



In [2]:

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

s1 = Series(np.arange(1,4))
s1









    Out[2]:





0    1
1    2
2    3
dtype: int64

Q: What is

s1.apply(lambda k: 2*k).sum()

Q: What is s1.cumsum()[1]?



In [2]:

	0	1	2
0	1	China	1385566537
1	2	India	1252139596
2	3	United States	320050716
3	4	Indonesia	249865631
4	5	Brazil	200361925