-
Notifications
You must be signed in to change notification settings - Fork 4
/
Copy pathutils.py
253 lines (228 loc) · 7.52 KB
/
utils.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
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
import os
import requests
import json
import logging
from datetime import date, datetime, timedelta
from google.cloud import storage
from google.oauth2 import service_account
from cairosvg import svg2png
import numpy as np
# source: https://data.cityofchicago.org/Health-Human-Services/COVID-19-Vaccine-Doses-by-ZIP-Code-Series-Complete/8u6c-48j3
vax_url = "https://data.cityofchicago.org/api/views/553k-3xzc/rows.json?accessType=DOWNLOAD"
# source: https://data.cityofchicago.org/Health-Human-Services/COVID-19-Cases-Tests-and-Deaths-by-ZIP-Code/yhhz-zm2v
deaths_url= "https://data.cityofchicago.org/api/views/yhhz-zm2v/rows.json?accessType=DOWNLOAD"
def get_json(url):
res = requests.get(url)
return json.loads(res.text)
def get_vax_perc_by_date(vax_json, date, save_totals=False):
# loop over city data and return a dictionary of zipcodes and their vax rates
# also, a sum of all vaccinations
vax_perc = {}
vax_sum = 0
population_sum = 0
for row in vax_json["data"]:
# we only want dose cumulatives from the latest date
# res date should be in the format 2021-01-18T00:00:00
if date == datetime.strptime(row[9], '%Y-%m-%dT00:00:00') and (row[8] in chicago_zips):
vax_perc[row[8]] = float(row[17])
# display values > 100% as 100%
if vax_perc[row[8]] > 1:
vax_perc[row[8]] = 1
vax_sum += int(row[16])
population_sum += int(row[30])
if save_totals:
return {
"vax_perc": vax_perc,
"vax_sum": vax_sum,
"population_sum": population_sum,
}
else:
return vax_perc
def get_colors_dict(values_dict, colorscale, data_type):
colors_dict = {}
arr = [value for name, value in values_dict.items() if name in chicago_zips]
# alert us if there are unexpected zip values
bad_zips_arr = [name for name, value in values_dict.items() if name not in chicago_zips + ["Unknown", "60666", "60707", "60827"]]
if len(bad_zips_arr) > 0:
logging.error("Unexpected zip values for {data_type} data: {bad_zips}".format(
data_type=data_type,
bad_zips=", ".join(bad_zips_arr)),
)
colors_dict["key_color1"] = colorscale[0]
colors_dict["key_color2"] = colorscale[1]
colors_dict["key_color3"] = colorscale[2]
colors_dict["key_color4"] = colorscale[3]
colors_dict["key_color5"] = colorscale[4]
key_label0_raw = np.percentile(arr, 0, interpolation="nearest")
key_label1_raw = np.percentile(arr, 20, interpolation="nearest")
key_label2_raw = np.percentile(arr, 40, interpolation="nearest")
key_label3_raw = np.percentile(arr, 60, interpolation="nearest")
key_label4_raw = np.percentile(arr, 80, interpolation="nearest")
key_label5_raw = np.percentile(arr, 100, interpolation="nearest")
if data_type == "deaths":
colors_dict["key_label0"] = round(key_label0_raw, 1)
colors_dict["key_label1"] = round(key_label1_raw, 1)
colors_dict["key_label2"] = round(key_label2_raw, 1)
colors_dict["key_label3"] = round(key_label3_raw, 1)
colors_dict["key_label4"] = round(key_label4_raw, 1)
colors_dict["key_label5"] = round(key_label5_raw, 1)
elif data_type == "vax":
colors_dict["key_label0"] = "{}%".format(round(key_label0_raw * 100, 1))
colors_dict["key_label1"] = "{}%".format(round(key_label1_raw * 100, 1))
colors_dict["key_label2"] = "{}%".format(round(key_label2_raw * 100, 1))
colors_dict["key_label3"] = "{}%".format(round(key_label3_raw * 100, 1))
colors_dict["key_label4"] = "{}%".format(round(key_label4_raw * 100, 1))
colors_dict["key_label5"] = "{}%".format(round(key_label5_raw * 100, 1))
else:
raise Exception("Unexpected key passed to function. Choose 'vax' or 'deaths'")
for name, value in values_dict.items():
# prepend "zip" to make these names less confusing
# when they appear in the SVG
svg_name = "zip{}".format(name)
# divide results into 5 even percentiles
if (value < key_label1_raw):
colors_dict[svg_name] = colors_dict["key_color1"]
elif (value < key_label2_raw):
colors_dict[svg_name] = colors_dict["key_color2"]
elif (value < key_label3_raw):
colors_dict[svg_name] = colors_dict["key_color3"]
elif (value < key_label4_raw):
colors_dict[svg_name] = colors_dict["key_color4"]
elif (value <= key_label5_raw):
colors_dict[svg_name] = colors_dict["key_color5"]
else:
colors_dict[svg_name] = "white"
return colors_dict
def get_colors_dict_absolute(values_dict, colorscale, date, data_type):
colors_dict = {}
colors_dict["date"] = date.strftime("%B %-d")
colors_dict["year"] = date.strftime("%Y")
# alert us if there are unexpected zip values
arr = [value for name, value in values_dict.items() if name in chicago_zips]
bad_zips_arr = [name for name, value in values_dict.items() if name not in chicago_zips + ["Unknown", "60666", "60707", "60827"]]
if len(bad_zips_arr) > 0:
logging.error("Unexpected zip values for {data_type} data: {bad_zips}".format(
data_type=data_type,
bad_zips=", ".join(bad_zips_arr)),
)
for index, value in enumerate(colorscale):
colors_dict["key_color{}".format(index + 1)] = value
for name, value in values_dict.items():
# prepend "zip" to make these names less confusing
# when they appear in the SVG
svg_name = "zip{}".format(name)
# divide results into 10 absolute buckets
if (value < .1):
colors_dict[svg_name] = colors_dict["key_color1"]
elif (value < .2):
colors_dict[svg_name] = colors_dict["key_color2"]
elif (value < .3):
colors_dict[svg_name] = colors_dict["key_color3"]
elif (value < .4):
colors_dict[svg_name] = colors_dict["key_color4"]
elif (value <= .5):
colors_dict[svg_name] = colors_dict["key_color5"]
elif (value <= .6):
colors_dict[svg_name] = colors_dict["key_color6"]
elif (value <= .7):
colors_dict[svg_name] = colors_dict["key_color7"]
elif (value <= .8):
colors_dict[svg_name] = colors_dict["key_color8"]
elif (value <= .9):
colors_dict[svg_name] = colors_dict["key_color9"]
elif (value <= 1):
colors_dict[svg_name] = colors_dict["key_color10"]
else:
colors_dict[svg_name] = "white"
return colors_dict
def write_svg(svg_path, output_paths, colors_dict, dpi=150):
# write colors into the SVG file and export
with open(svg_path, "r") as svg_file:
svg_string = svg_file.read().format(**colors_dict)
for output_path in output_paths:
svg2png(
bytestring=svg_string,
write_to=output_path,
dpi=dpi,
background_color="white",
)
print("Saved image file {}".format(output_path))
# gcloud utils
def get_bucket(bucket_name, cred_str):
json_data = json.loads(cred_str, strict=False)
json_data['private_key'] = json_data['private_key'].replace('\\n', '\n')
credentials = service_account.Credentials.from_service_account_info(
json_data)
storage_client = storage.Client(
project=bucket_name, credentials=credentials)
return storage_client.bucket(bucket_name)
def upload_to_gcloud(bucket, source_file_name):
destination_name = os.path.basename(source_file_name)
blob = bucket.blob(destination_name)
blob.upload_from_filename(source_file_name)
print(
"File {} uploaded to {} on Google Cloud.".format(
source_file_name, destination_name
)
)
chicago_zips = [
"60638",
"60601",
"60606",
"60611",
# "60666", low pop
"60645",
"60625",
"60640",
"60626",
"60657",
"60615",
"60621",
"60651",
# "60707", low pop
"60631",
"60602",
"60607",
"60630",
"60641",
"60622",
"60636",
"60610",
"60659",
"60614",
"60644",
"60603",
"60634",
"60637",
"60649",
"60618",
"60623",
"60647",
"60629",
"60613",
"60660",
"60654",
"60608",
"60642",
"60604",
"60653",
"60619",
"60655",
"60617",
"60633",
"60612",
"60646",
"60643",
"60628",
"60661",
"60624",
"60609",
# "60827", low pop
"60639",
"60632",
"60656",
"60620",
"60605",
"60652",
"60616"
]