-
Notifications
You must be signed in to change notification settings - Fork 0
/
harvest.py
469 lines (347 loc) · 14.6 KB
/
harvest.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
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
"""
Original created on Dec 16 2020
Edited on Jan 28 2021
Converted GeoJSON into TopoJSON to reduce file size
@author: Yijing Zhou @YijingZhou33
"""
"""
Part 0: Initialization
"""
##### Import necessary modules #######
# Note that mapclassify and topojson aren't built-in modules in Anaconda.
# You may need to install in advance.
# pip install mapclassify
# pip install topojson
####### Set file path #######
# ********** Input Files **********
# Raw data: CSV files
import os
import pandas as pd
import json
import numpy as np
import re
from bs4 import BeautifulSoup, SoupStrainer
import requests
import geopandas as gpd
import folium
import sys
import mapclassify
import topojson as tp
stategeoportals = os.path.join('data', 'allStates.csv')
countygeoportals = os.path.join('data', 'allCounties.csv')
citygeoportals = os.path.join('data', 'allCities.csv')
# Basemap GeoJSON files for states and counties
statejson = os.path.join('data', 'states.json')
countyjson = os.path.join('data', 'counties.json')
# ********** Output Files **********
activestates = os.path.join('json', 'activeStates.topo.json')
activecounties = os.path.join('json', 'activeCounties.topo.json')
activecities = os.path.join('json', 'activeCities.json')
legendjson = os.path.join('json', 'legend.json')
"""
Part 1: State Geoportals TopoJSON
"""
####### Format state name in state geoportals spreadsheet allStates.csv #######
df_csv = pd.read_csv(stategeoportals)
df_csv['btaaURL'] = df_csv['btaaURL'].apply(lambda x: x.split('-')[0])
####### Etract total records number from BTAA Geoportal search page #######
def totalRecords(df):
totalrecords = []
for _, row in df.iterrows():
url = row['btaaURL']
# Start session and get the search page
session = requests.Session()
response = session.get(url)
# Parse only part of the page (<meta> tag) for better performance using SoupStrainer and lxml
strainer = SoupStrainer('meta', attrs={'name': 'totalResults'})
soup = BeautifulSoup(response.content, 'lxml', parse_only=strainer)
# The find() method looks through <meta> tag��s descendants and retrieves one result with attribute 'name'.
meta_tag = soup.find('meta', attrs={'name': 'totalResults'})
# Grab the content inside the <meta> tag that matches the filter
totalrecord = meta_tag.get('content')
totalrecords.append(totalrecord)
return totalrecords
df_csv['totalRecords'] = totalRecords(df_csv)
####### Inspect the numinum number of total records #######
# If it equals to 0, meaning the landing page is 404 Not Found.
# Go back to check if the identifier is still active.
def check_totalRecords(df):
df['totalRecords'] = df['totalRecords'].astype(int)
if df['totalRecords'].min() == 0:
return df[df['totalRecords'] == 0]
else:
print('> State Geoportal Codes all valid!')
check_totalRecords(df_csv)
####### Group dataframe rows into list by geoportal sites #######
def aggregate_to_array(data):
groupItems = ['stateCode', 'Title', 'sourceURL']
for i in range(len(groupItems)):
data[groupItems[i]] = np.tile(
[data[groupItems[i]].values], (data.shape[0], 1)).tolist()
return data
# Group by ['State']
df_group = df_csv.groupby(['State']).apply(
aggregate_to_array).drop_duplicates(subset=['State'])
####### Merge state GeoJSON and geoportal GeoJSON #######
# Load statejson featuer properties
state_geojson = gpd.read_file(statejson)
state_json = json.loads(state_geojson.to_json())
df_allState = pd.json_normalize(state_json['features'])
# Change column names for further operation
df_allState = df_allState[['properties.State', 'geometry.coordinates']].rename(
columns={'properties.State': 'State', 'geometry.coordinates': 'boundingBox'})
# Join on column 'State' from left dataframe df_group
df_merge = pd.merge(df_group, df_allState, on='State', how='left')
####### Return rows with Nan value #######
# Check if there exists any records doesn't include any coordinates information in the boundingBox column
# If so, go back to allCounties.csv and manually change the county name to the one in county.json
def check_nanrows(df):
if df.isnull().values.any():
print(df[df['boundingBox'].isnull()])
sys.exit()
else:
print('> No NULL rows')
check_nanrows(df_merge)
####### Create state GeoJSON features #######
def create_geojson_features(df):
print('> Creating state GeoJSON features...')
features = []
geometry_type = ''
geojson = {
'type': 'FeatureCollection',
'features': features
}
for _, row in df.iterrows():
if type(row['boundingBox'][0][0][0]) is float:
geometry_type = 'Polygon'
else:
geometry_type = 'MultiPolygon'
feature = {
'type': 'Feature',
'geometry': {
'type': geometry_type,
'coordinates': row['boundingBox']
},
'properties': {
'State': row['State'],
'Title': '|'.join([str(elem) for elem in row['Title']]),
'sourceURL': '|'.join([str(elem) for elem in row['sourceURL']]),
'btaaURL': row['btaaURL'],
'totalRecords': row['totalRecords']
}
}
features.append(feature)
return geojson
data_geojson = create_geojson_features(df_merge)
####### Write to state TopoJSON file activeStates.topo.json #######
state_geojson = gpd.GeoDataFrame.from_features(data_geojson["features"])
# TopoJSON is an extension of GeoJSON to compress geometry information
topo = tp.Topology(state_geojson)
topo.to_json(activestates)
print('> Creating state TopoJSON file...')
"""
Part 2: County Geoportals GeoJSON
"""
####### Format county name in county geoportals spreadsheet allCounties.csv #######
df_csv = pd.read_csv(countygeoportals)
# Replace 'Saint' and 'St' with 'St.'
df_csv['County'] = df_csv['County'].apply(
lambda x: re.sub(r'(Saint\s|^St\s|^St\.\s)', 'St. ', x))
# Replace 'Baltimore County' and 'Baltimore' with 'Baltimore County County'
df_csv['County'] = df_csv['County'].apply(lambda x: re.sub(
r'(^(Baltimore|Baltimore\sCounty)$)', 'Baltimore County County', x))
####### Etract total records number from BTAA Geoportal search page #######
df_csv['totalRecords'] = totalRecords(df_csv)
####### Inspect the numinum number of total records #######
check_totalRecords(df_csv)
####### Group dataframe rows into list by geoportal sites #######
def aggregate_to_array(data):
groupItems = ['Title', 'sourceURL', 'totalRecords']
for i in range(len(groupItems)):
data[groupItems[i]] = np.tile(
[data[groupItems[i]].values], (data.shape[0], 1)).tolist()
return data
# Group by ['County', 'State']
df_group = df_csv.groupby(['County', 'State']).apply(
aggregate_to_array).drop_duplicates(subset=['County', 'State'])
# Sum up the total records if there're multiple geoportals in one county
df_group['totalRecords'] = df_group['totalRecords'].apply(
lambda x: sum(int(item)for item in x))
####### Classify the geoportal by total number #######
# You may want to adjust the classification method NaturalBreaks and class number k.
df_excludeOne = df_group[df_group['totalRecords'] != 1]
n4 = mapclassify.NaturalBreaks(df_excludeOne.totalRecords, k=4)
countyInterval = [1.0] + [i for i in list(n4.bins)]
####### Assign different color to each geoportal based on total records class #######
# Select the gradient color palette
palette = ['#b3cde0', '#6497b1', '#005b96', '#03396c ', '#011f4b']
def totalRecords_color(row):
if row['totalRecords'] <= countyInterval[0]:
return palette[0]
elif row['totalRecords'] > countyInterval[0] and row['totalRecords'] <= countyInterval[1]:
return palette[1]
elif row['totalRecords'] > countyInterval[1] and row['totalRecords'] <= countyInterval[2]:
return palette[2]
elif row['totalRecords'] > countyInterval[2] and row['totalRecords'] <= countyInterval[3]:
return palette[3]
else:
return palette[4]
# Append a new column with color generated above
df_group['Color'] = df_group.apply(totalRecords_color, axis=1)
####### Merge county GeoJSON and geoportal GeoJSON #######
# Load countyjson featuer properties
county_geojson = gpd.read_file(countyjson)
county_json = json.loads(county_geojson.to_json())
df_allCounty = pd.json_normalize(county_json['features'])
# Change column names for further operation
df_allCounty = df_allCounty[['properties.County', 'properties.State', 'geometry.coordinates']].rename(
columns={'properties.County': 'County', 'properties.State': 'State', 'geometry.coordinates': 'boundingBox'})
# Join on column 'County' and 'State' from left dataframe df_group
df_merge = pd.merge(df_group, df_allCounty, on=['County', 'State'], how='left')
####### Return rows with Nan value #######
# Check if there exists any records doesn't include any coordinates information in the boundingBox column
# If so, go back to allCounties.csv and manually change the county name to the one in county.json
def check_nanrows(df):
if df.isnull().values.any():
print(df[df['boundingBox'].isnull()])
sys.exit()
else:
print('> No NULL rows')
check_nanrows(df_merge)
####### Create county GeoJSON features #######
def create_geojson_features(df):
print('> Creating county GeoJSON features...')
features = []
geometry_type = ''
geojson = {
'type': 'FeatureCollection',
'features': features
}
for _, row in df.iterrows():
if type(row['boundingBox'][0][0][0]) is float:
geometry_type = 'Polygon'
else:
geometry_type = 'MultiPolygon'
feature = {
'type': 'Feature',
'geometry': {
'type': geometry_type,
'coordinates': row['boundingBox']
},
'properties': {
'County': row['County'],
'State': row['State'],
'countyCode': row['countyCode'],
'Title': '|'.join([str(elem) for elem in row['Title']]),
'sourceURL': '|'.join([str(elem) for elem in row['sourceURL']]),
'btaaURL': row['btaaURL'],
'totalRecords': row['totalRecords'],
'Color': row['Color']
}
}
features.append(feature)
return geojson
data_geojson = create_geojson_features(df_merge)
####### Write to county TopoJSON file activeCounties.topo.json #######
county_geojson = gpd.GeoDataFrame.from_features(data_geojson["features"])
# TopoJSON is an extension of GeoJSON to compress geometry information
topo = tp.Topology(county_geojson)
topo.to_json(activecounties)
print('> Creating county TopoJSON file...')
"""
Part 3: City Geoportals GeoJSON
"""
####### Format city name in city geoportals spreadsheet allCities.csv #######
df = pd.read_csv(citygeoportals)
# Calculate city coordinates and round to 2 decimal places
df = pd.concat([df, df['Bounding Box'].str.split(',', expand=True).astype(float)], axis=1).rename(
columns={0: 'minX', 1: 'minY', 2: 'maxX', 3: 'maxY'})
df['centerX'] = round((df['minX'] + df['maxX']) / 2, 2)
df['centerY'] = round((df['minY'] + df['maxY']) / 2, 2)
df_clean = df.drop(columns=['minX', 'minY', 'maxX', 'maxY', 'Bounding Box'])
####### Etract total records number from BTAA Geoportal search page #######
df_clean['totalRecords'] = totalRecords(df_clean)
####### Inspect the numinum number of total records #######
check_totalRecords(df_clean)
####### Group dataframe rows into list by geoportal sites #######
def aggregate_to_array(data):
groupItems = ['Title', 'sourceURL', 'totalRecords']
for i in range(len(groupItems)):
data[groupItems[i]] = np.tile(
[data[groupItems[i]].values], (data.shape[0], 1)).tolist()
return data
# Group by ['City', 'State']
df_group = df_clean.groupby(['centerX']).apply(
aggregate_to_array).drop_duplicates(subset=['City', 'State'])
# sum up the total records if there're multiple geoportals in one city
df_group['totalRecords'] = df_group['totalRecords'].apply(
lambda x: sum(int(item)for item in x))
####### Classify the geoportal by total number #######
# You may want to adjust the classification method Quantiles and class number k.
n3 = mapclassify.Quantiles(df_group.totalRecords, k=3)
cityInterval = list(n3.bins)
####### Assign different circle radius to each geoportal based on total records class #######
# Size of symbols on map in meters
size = [12000, 16000, 22000]
# Size of symbols inside legend in pixels
legendSize = [12, 18, 28]
def totalRecords_size(row):
if row['totalRecords'] <= cityInterval[0]:
return size[0]
elif row['totalRecords'] > cityInterval[0] and row['totalRecords'] <= cityInterval[1]:
return size[1]
else:
return size[2]
# Append a new column with color generated above
df_group['Size'] = df_group.apply(totalRecords_size, axis=1)
####### Create city GeoJSON features #######
def create_geojson_features(df):
print('> Creating city GeoJSON features...')
features = []
geojson = {
'type': 'FeatureCollection',
'features': features
}
for _, row in df.iterrows():
feature = {
'type': 'Feature',
'geometry': {
'type': 'Point',
'coordinates': [row['centerX'], row['centerY']]
},
'properties': {
'City': row['City'],
'State': row['State'],
'Title': '|'.join([str(elem) for elem in row['Title']]),
'sourceURL': '|'.join([str(elem) for elem in row['sourceURL']]),
'btaaURL': row['btaaURL'],
'totalRecords': row['totalRecords'],
'Size': row['Size']
}
}
features.append(feature)
return geojson
data_geojson = create_geojson_features(df_group)
####### Write to city GeoJSON file activecities.json #######
with open(activecities, 'w') as txtfile:
json.dump(data_geojson, txtfile)
print('> Creating city GeoJSON file...')
"""
Part 4: Legend JSON
"""
####### Create legend JSON features #######
def create_legend_json(countyinterval, palette, cityinterval, size):
print('> Creating legend JSON featuers...')
countystyle = dict(zip(countyinterval, palette))
citystyle = dict(zip(cityinterval, size))
dic = {
'county': countystyle,
'city': citystyle
}
return dic
data_json = create_legend_json(
countyInterval, palette, cityInterval, legendSize)
####### Write to legend JSON file legend.json #######
with open(legendjson, 'w') as txtfile:
json.dump(data_json, txtfile)
print('> Creating legend JSON file...')