GeoInfluence of Governors

In [1]:

    

cd ../


    

    




C:\Users\Talha\Documents\WinPython3\projects\GeoInfluence

In [3]:

    

import pandas as pd
import json
#from tw import *
import twitter
from utilities.geocoder import Geocoder
from collections import Counter


    

In [4]:

    

# read the IDs of the followers of the governor of North Dakota
# this file is retrieved from dd-css.com
filename = '5522fdf6bd90594f049c4aef.json'
followers_file = open('data/'+filename)
followers = json.load(followers_file)
fids = followers['data']['followers']
followers['parameters']['screen_name']


    

    
Out[4]:





'NDGovDalrymple'

In [ ]:

    

# Connect to twitter and retrieve followers' information
# https://dev.twitter.com/rest/reference/get/users/lookup
resp = []
twitter_api = oauth_login()
for i in range(1+len(fids)//100):
    resp.extend(twitter_api.users.lookup(user_id=fids[100*i:100*(i+1)]))


    

In [5]:

    

# let's save this response
with open('data/resp_'+filename, 'w') as outfile:
    json.dump(resp, outfile)


    

    




---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-5-0f68fc4df566> in <module>()
      1 # let's save this response
      2 with open('data/resp_'+filename, 'w') as outfile:
----> 3     json.dump(resp, outfile)

NameError: name 'resp' is not defined

In [ ]:

    

# let's get the locations out of this JSON response
i = 0
locations = []
for r in resp:
    if r['location'] != '':
        locations.append(r['location'])
        print(r['location'],end='; ')
        i=i+1
print("\nNumber of non-empty location info in user profiles: ",i)
print('Rate of non-empty user-profile location fields: {0:.2f} %'.format(i*100/len(resp)))


    

In [ ]:

    

# let's save the locations to a file
governor = {'name':followers['parameters']['screen_name'], 'locs':locations}
with open('data/loc_'+filename, 'w') as outfile:
    json.dump(governor, outfile)


    

In [6]:

    

# read in the locations back
filename = 'loc_5522fdf6bd90594f049c4aef.json'
followers_file = open('data/'+filename)
followers = json.load(followers_file)
followers.keys()


    

    
Out[6]:





dict_keys(['locs', 'name'])

In [7]:

    

gc = Geocoder('utilities/geodata/state_abbr_file', 'utilities/geodata/city_file')
latlon = []
for f in followers['locs']:
    point = gc.geocode(f.strip())
    if point != None:
        latlon.append((point[0], point[1]))
cnt = Counter(latlon)
print('Number of locations geocoded:',sum(cnt.values()))
cnt.most_common()


    

    




Number of locations geocoded: 115






    
Out[7]:





[(('46.813343', '-100.779004'), 35),
 (('46.871414', '-96.808658'), 19),
 (('38.913611', '-77.013222'), 18),
 (('44.964465', '-93.268198'), 5),
 (('48.233190', '-101.292229'), 3),
 (('46.864563', '-96.758707'), 3),
 (('46.828893', '-100.891138'), 2),
 (('44.367966', '-100.336378'), 2),
 (('38.880344', '-77.108260'), 2),
 (('48.156477', '-103.628064'), 2),
 (('46.883575', '-102.788811'), 2),
 (('40.352206', '-74.657071'), 1),
 (('48.961469', '-101.631889'), 1),
 (('46.780373', '-92.117079'), 1),
 (('31.056125', '-95.129322'), 1),
 (('30.451800', '-84.272770'), 1),
 (('46.595805', '-112.027031'), 1),
 (('40.123496', '-82.921432'), 1),
 (('46.333108', '-113.296564'), 1),
 (('39.896280', '-75.035908'), 1),
 (('41.684200', '-71.268669'), 1),
 (('48.795416', '-97.623259'), 1),
 (('39.726287', '-104.965486'), 1),
 (('47.673341', '-117.410271'), 1),
 (('38.816242', '-77.071282'), 1),
 (('33.050374', '-96.745935'), 1),
 (('42.516564', '-89.029964'), 1),
 (('44.410322', '-103.518486'), 1),
 (('35.357276', '-119.031661'), 1),
 (('47.268088', '-101.777229'), 1),
 (('40.441419', '-79.977292'), 1),
 (('33.590709', '-111.895985'), 1),
 (('33.528370', '-112.076300'), 1)]

In [8]:

    

from IPython.display import HTML
HTML('<iframe width="1000" height="600" scrolling="no" frameborder="no" src="https://www.google.com/fusiontables/embedviz?q=select+col0+from+1mGLpmSCTW6wK07tL0xkd-nmvY7uLJzsl4hd0sRHD+limit+1000&amp;viz=HEATMAP&amp;h=true&amp;lat=40.33704203649286&amp;lng=-95.15016500000002&amp;t=1&amp;z=5&amp;l=col0&amp;y=2&amp;tmplt=2&amp;hmd=true&amp;hmg=%2366ff0000%2C%2393ff00ff%2C%23c1ff00ff%2C%23eeff00ff%2C%23f4e300ff%2C%23f4e300ff%2C%23f9c600ff%2C%23ffaa00ff%2C%23ff7100ff%2C%23ff3900ff%2C%23ff0000ff&amp;hmo=0.6&amp;hmr=25&amp;hmw=0&amp;hml=ONE_COL_LAT_LNG"></iframe>')


    

    
Out[8]: