In [1]:

    

import pandas as pd
from pandas import DataFrame

import census
import settings
import us
import numpy as np
from itertools import islice

# instantiate the census object

c=census.Census(settings.CENSUS_KEY)


    

In [2]:

    

states_fips = np.array([state.fips for state in us.states.STATES])


    

In [3]:

    

11 in states_fips


    

    
Out[3]:





False

In [4]:

    

all_places=c.sf1.get('NAME,P0010001', 
                         geo={'for': 'place:*', 
                              'in': 'state:*'})


    

In [5]:

    

## EXERCISE
## FILL in with your generator for all census places in the 2010 census

def places(variables="NAME"):
#     global all_places
#     if process == 'by_state':
    for state in states_fips:
        p=c.sf1.get('NAME,P0010001', 
                         geo={'for': 'place:*', 
                              'in': 'state:%s' % state})
        for k in p:
            yield k

#     else:
#         print"using all_places"
#         for k in all_places:
#             yield k


    

In [6]:

    

#for testing the generator
place_gen=places()


    

In [7]:

    

#for testing the generator
place_gen.next()


    

    
Out[7]:





{u'NAME': u'Abanda CDP',
 u'P0010001': u'192',
 u'place': u'00100',
 u'state': u'01'}

In [8]:

    

# use this code to run your code
# I recommend replacing the None in islice to a small number to make sure you're on 
# the right track

r = list(islice(places("NAME,P0010001"), None))
places_df = DataFrame(r)
places_df.P0010001 = places_df.P0010001.astype('int')

places_df['FIPS'] = places_df.apply(lambda s: s['state']+s['place'], axis=1)

print "number of places", len(places_df)
print "total pop", places_df.P0010001.sum()
places_df.head()


    

    




number of places 29261
total pop 228457238






    
Out[8]:






  

    

      

      
NAME
      
P0010001
      
place
      
state
      
FIPS
    
  
  

    

      
0
      
      Abanda CDP
      
  192
      
 00100
      
 01
      
 0100100
    
    

      
1
      
  Abbeville city
      
 2688
      
 00124
      
 01
      
 0100124
    
    

      
2
      
 Adamsville city
      
 4522
      
 00460
      
 01
      
 0100460
    
    

      
3
      
    Addison town
      
  758
      
 00484
      
 01
      
 0100484
    
    

      
4
      
      Akron town
      
  356
      
 00676
      
 01
      
 0100676
    
  

5 rows × 5 columns

In [100]:

    

# if you've done this correctly, the following asserts should stop complaining

assert places_df.P0010001.sum() == 228457238
# number of places in 2010 Census
assert len(places_df) == 29261


    

In [ ]: