import urllib2
import xmltodict
from string import split
from secrets import wolfram_key

states = ['Alabama', 'Alaska', 'Arizona', 'Arkansas', 'California', 'Colorado', 'Connecticut', 'Delaware', 'Florida', 'Georgia', 'Hawaii', 'Idaho', 'Illinois', 'Indiana', 'Iowa', 'Kansas', 'Kentucky', 'Louisiana', 'Maine', 'Maryland', 'Massachusetts', 'Michigan', 'Minnesota', 'Mississippi', 'Missouri', 'Montana', 'Nebraska', 'Nevada', 'New Hampshire', 'New Jersey', 'New Mexico', 'New York', 'North Carolina', 'North Dakota', 'Ohio', 'Oklahoma', 'Oregon', 'Pennsylvania', 'Rhode Island', 'South Carolina', 'South Dakota', 'Tennessee', 'Texas', 'Utah', 'Vermont', 'Virginia', 'Washington State', 'West Virginia', 'Wisconsin', 'Wyoming', 'Washington DC']
def query(q, key=wolfram_key):
    return urllib2.urlopen('http://api.wolframalpha.com/v2/query?appid=%s&input=%s&format=plaintext' % (key,urllib2.quote(q))).read()

def state_query(group_name, states=states):
    results = {s: xmltodict.parse(query('number of %s in %s?' % (group_name, s))) for s in states}
    results = {s: [p for p in v['queryresult']['pod'] if p['@title'] == 'Result'][0]['subpod']['plaintext'] for s,v in results.items()}
    results = {s: float(split(v)[0])*(1000000 if 'million' in v else 1) for s,v in results.items()}
    return results
    



adults = state_query('adults')

for group in ['phds', 'college graduates']:
    group_data = state_query(group)
    print '-'*100
    print group
    print '\n'.join('#%d: %s: %2.2f%%' % (i+1,r[0],r[1]) for i,r in enumerate(sorted({s: (group_data[s]/adults[s])*100 for s in states}.items(), key = lambda x: x[1], reverse=True)))