forked from gkipkorir/cs465_final_project
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathget_Data_Race.py
125 lines (100 loc) · 3.09 KB
/
get_Data_Race.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
import urllib2
import json
# req = urllib2.Request("http://api.census.gov/data/timeseries/healthins/sahie?get=NIC_PT,NAME,NUI_PT&for=us:*&time=2013&key=e0103f837daffd400e2208bacbf97de2be035383")
# response = urllib2.urlopen(req)
# the_page = response.read()
# print response.json
# #print the_page
startYear = 2006
endYear = 2013
myData = {}
us_state_abbrev = {
'Alabama': 'AL',
'Alaska': 'AK',
'Arizona': 'AZ',
'Arkansas': 'AR',
'California': 'CA',
'Colorado': 'CO',
'Connecticut': 'CT',
'District of Columbia':'DC',
'Delaware': 'DE',
'Florida': 'FL',
'Georgia': 'GA',
'Hawaii': 'HI',
'Idaho': 'ID',
'Illinois': 'IL',
'Indiana': 'IN',
'Iowa': 'IA',
'Kansas': 'KS',
'Kentucky': 'KY',
'Louisiana': 'LA',
'Maine': 'ME',
'Maryland': 'MD',
'Massachusetts': 'MA',
'Michigan': 'MI',
'Minnesota': 'MN',
'Mississippi': 'MS',
'Missouri': 'MO',
'Montana': 'MT',
'Nebraska': 'NE',
'Nevada': 'NV',
'New Hampshire': 'NH',
'New Jersey': 'NJ',
'New Mexico': 'NM',
'New York': 'NY',
'North Carolina': 'NC',
'North Dakota': 'ND',
'Ohio': 'OH',
'Oklahoma': 'OK',
'Oregon': 'OR',
'Pennsylvania': 'PA',
'Rhode Island': 'RI',
'South Carolina': 'SC',
'South Dakota': 'SD',
'Tennessee': 'TN',
'Texas': 'TX',
'Utah': 'UT',
'Vermont': 'VT',
'Virginia': 'VA',
'Washington': 'WA',
'West Virginia': 'WV',
'Wisconsin': 'WI',
'Wyoming': 'WY',
}
for year in range(startYear, endYear+1):
# url = "http://api.census.gov/data/timeseries/healthins/sahie?get=NIC_PT,NAME,NUI_PT&for=STATE:010&time=" + str(year)
# url = "http://api.census.gov/data/timeseries/healthins/sahie?get=NIC_PT,NAME,NUI_PT&for=us:*&time=2013"
#url = "http://api.census.gov/data/timeseries/healthins/sahie?get=IPR_DESC,IPRCAT,PCTIC_PT,NAME&for=state:024,025&time=" + str(year)
url = "http://api.census.gov/data/timeseries/healthins/sahie?get=NAME,RACE_DESC,RACECAT,PCTUI_PT&for=state:*&time=" + str(year)
yearData = json.load(urllib2.urlopen(url))
print "yearData", yearData[1][1]
states = []
for i in range(1, len(yearData)):
state_info = {}
for j in range(len(yearData[0])):
state_info[yearData[0][j]] = yearData[i][j]
#Add state abbreviation
state_abrev = us_state_abbrev[state_info["NAME"]]
state_info["abrev"] = state_abrev
#print state_abrev
#add perent unInusred
numInsured = int(state_info["NIC_PT"])
numUnInsured = int(state_info["NUI_PT"])
percUnInsured = str((numUnInsured*1.0/(numInsured+numUnInsured)) * 100)
#print percUnInsured
state_info["PUI"] = percUnInsured
states.append(state_info)
str_year = str(year)
#loop through all the data
# for year in yearData:
# print ()
#myData.append({year: yearData})
newYearData = {"year": year, "states": states}
myData[str_year] = newYearData
# for year in range(startYear, endYear+1):
# str_year = str(year)
# yearData = myData[str_year]
#print myData[str_year][1]
output_name = "newDataPerc.json" #"race_data.txt"
with open(output_name, 'w') as outfile:
json.dump(myData, outfile)