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
|
import os
import re
import glob
import simplejson as json
import math
import operator
import click
#import builder
from util import *
@click.command()
def s2_citation_report():
addresses = AddressBook()
megapixels = load_megapixels_queries()
successful_geocodes = {}
papers = []
for row in megapixels:
paper_data = process_paper(row, addresses, successful_geocodes)
if paper_data is not None:
papers.append(paper_data)
write_papers_report('reports/report_index.html', 'All Papers', papers, 'title')
write_papers_report('reports/report_coverage.html', 'Coverage', papers, 'citations_geocoded', reverse=True)
paper_count = 0
geocode_count = 0
for key, value in successful_geocodes.items():
if value:
geocode_count += 1
paper_count += 1
print("citations: {}".format(paper_count))
print("geocoded: {} ({}%)".format(geocode_count, percent(geocode_count, paper_count)))
def write_papers_report(fn, title, papers, key, reverse=False):
sorted_papers = []
for paper in sorted(papers, key=lambda x: x[key], reverse=reverse):
sorted_papers.append([
paper['paperId'],
paper['key'],
paper['name'],
LinkLine(paper['report_link'], paper['title']),
LinkLine(paper['pdf_link'], '[pdf]'),
paper['journal'],
paper['address_type'],
paper['address'],
paper['lat'],
paper['lng'],
str(percent(paper['citations_geocoded'], paper['citation_count'])) + '%',
paper['citation_count'],
paper['citations_geocoded'],
paper['citations_unknown'],
paper['citations_empty'],
paper['citations_pdf'],
paper['citations_doi'],
])
sorted_paper_keys = [
'Paper ID',
'Megapixels Key',
'Megapixels Name',
'Report Link',
'PDF Link',
'Journal',
'Type',
'Address',
'Lat',
'Lng',
'Coverage',
'Total Citations',
'Geocoded Citations',
'Unknown Citations',
'Empty Citations',
'With PDF',
'With DOI',
]
write_report(fn, title=title, keys=sorted_paper_keys, rows=sorted_papers)
def process_paper(row, addresses, success):
res = {
'paperId': '',
'key': '',
'title': '',
'journal': '',
'address': '',
'address_type': '',
'lat': '',
'lng': '',
'pdf_link': '',
'report_link': '',
'citation_count': 0,
'citations_geocoded': 0,
'citations_unknown': 0,
'citations_empty': 0,
'citations_pdf': 0,
'citations_doi': 0,
}
geocoded_citations = []
unknown_citations = []
display_geocoded_citations = []
empty_citations = []
pdf_count = 0
doi_count = 0
address_count = 0
fn = file_path('papers', row['paper_id'], 'paper.json')
with open(fn, 'r') as f:
data = json.load(f)
print('>> {}'.format(data['paperId']))
paper = load_paper(data['paperId'])
if paper is None:
print("Paper missing! {}".format(data['paperId']))
return
res['key'] = row['key']
res['name'] = row['name']
res['paperId'] = paper.paper_id
res['title'] = paper.title
res['journal'] = paper.journal
res['report_link'] = 'papers/{}.html'.format(paper.paper_id)
res['pdf_link'] = paper.pdf_link
# res['authors'] = ', '.join(paper.authors)
# res['citations'] = []
paper_institutions = load_institutions(paper.paper_id)
paper_address = None
for inst in sorted(paper_institutions, key=operator.itemgetter(1)):
# print(inst[1])
institution = inst[1]
if paper_address is None:
paper_address = addresses.find(institution)
if paper_address:
# print(paper_address)
res['address'] = paper_address[0]
res['lat'] = paper_address[3]
res['lng'] = paper_address[4]
res['address_type'] = paper_address[5]
for cite in data['citations']:
citationId = cite['paperId']
citation = load_paper(citationId)
has_pdf = os.path.exists(file_path('pdf', citationId, 'paper.txt'))
has_doi = os.path.exists(file_path('doi', citationId, 'paper.doi'))
if has_pdf:
pdf_count += 1
if has_doi:
doi_count += 1
if citation.data is None:
print("Citation missing! {}".format(cite['paperId']))
continue
institutions = load_institutions(citationId)
geocoded_institutions = []
unknown_institutions = []
institution = ''
address = None
for inst in sorted(institutions, key=operator.itemgetter(1)):
# print(inst[1])
address_count += 1
institution = inst[1]
next_address = addresses.find(institution)
if next_address:
address = next_address
geocoded_institutions.append(institution)
else:
unknown_institutions.append(institution)
if not address:
if has_pdf:
headings, found_abstract = read_headings(file_path('pdf', citationId, 'paper.txt'), citation)
heading_string = '\n'.join(headings[0:20])
found_addresses = []
if len(headings):
for heading in headings:
l = heading.lower().strip()
if l:
next_address = addresses.find(l)
if next_address:
address = next_address
geocoded_institutions.append(heading)
else:
unknown_institutions.append(heading)
else:
empty_citations.append([
citationId,
citation.title,
])
# res['citations'].append({
# 'title': citation.title,
# 'journal': citation.journal,
# 'authors': citation.authors,
# 'institutions': [inst[1] for inst in institutions],
# 'geocoded': geocoded_institutions,
# })
if address:
success[citationId] = True
geocoded_citations.append([
citation.title,
institution,
] + address)
display_geocoded_citations.append([
citationId,
LinkLine(citation.pdf_link, '[pdf]'),
citation.title,
] + address[0:5])
else:
success[citationId] = False
unknown_citations.append([
citationId,
LinkLine(citation.pdf_link, '[pdf]'),
citation.title,
'<br>'.join(unknown_institutions),
])
res['citation_count'] = len(data['citations'])
res['citations_geocoded'] = len(geocoded_citations)
res['citations_unknown'] = len(unknown_citations)
res['citations_empty'] = len(empty_citations)
res['citations_pdf'] = pdf_count
res['citations_doi'] = doi_count
total_citations = len(geocoded_citations) + len(unknown_citations)
os.makedirs('reports/papers/', exist_ok=True)
with open('reports/papers/{}.html'.format(paper.paper_id), 'w') as f:
f.write("<!doctype html>")
f.write("<html>")
f.write("<head>")
f.write('<meta charset="utf-8">')
f.write("<title>{}</title>".format(paper.title))
f.write("<link rel='stylesheet' href='../reports.css'>")
f.write('<link rel="stylesheet" href="https://unpkg.com/leaflet@1.3.4/dist/leaflet.css" integrity="sha512-puBpdR0798OZvTTbP4A8Ix/l+A4dHDD0DGqYW6RQ+9jxkRFclaxxQb/SJAWZfWAkuyeQUytO7+7N4QKrDh+drA==" crossorigin=""/>')
f.write("</head>")
f.write("<body>")
f.write("<div id='mapid'></div>")
f.write("<h2>{}</h2>".format(paper.title))
f.write('<ul>')
if paper.journal:
f.write('<li>Journal: {}</li>'.format(paper.journal))
if paper_address:
f.write('<li>Research institution: {}</li>'.format(paper_address[0]))
f.write('<li>Address: {}</li>'.format(paper_address[2]))
f.write('<li>Lat/Lng: {}, {}</li>'.format(paper_address[3], paper_address[4]))
f.write('<li>Year: {}</li>'.format(paper.year))
if total_citations == 0:
f.write('<li>Coverage: No citations found!</li>')
else:
f.write('<li>Coverage: {} / {} citations were located ({} %).</li>'.format(len(geocoded_citations), total_citations, math.floor(len(geocoded_citations) / total_citations * 100)))
f.write('</ul>')
f.write('<h3>{}</h3>'.format('Geocoded Citations'))
write_table(f, keys=None, rows=sorted(display_geocoded_citations, key=operator.itemgetter(0)))
f.write('<h3>{}</h3>'.format('Other Citations'))
write_table(f, keys=None, rows=sorted(unknown_citations, key=operator.itemgetter(0)))
f.write("</body>")
f.write('<script src="../snap.svg-min.js"></script>')
f.write('<script src="https://unpkg.com/leaflet@1.3.4/dist/leaflet.js" integrity="sha512-nMMmRyTVoLYqjP9hrbed9S+FzjZHW5gY1TWCHA5ckwXZBadntCNs8kEqAWdrb9O7rxbCaA4lKTIWjDXZxflOcA==" crossorigin=""></script>')
f.write('<script src="../leaflet.arc.js"></script>')
f.write('<script src="../leaflet.bezier.js"></script>')
f.write('<script type="text/json" id="address">')
json.dump(paper_address, f)
f.write('</script>')
f.write('<script type="text/json" id="citations">')
json.dump(geocoded_citations, f)
f.write('</script>')
f.write('<script src="../map.js"></script>')
f.write("</html>")
# template = env.get_template('paper.html')
return res
def load_megapixels_queries():
keys, rows = read_csv('datasets/citation_lookup.csv')
recs = []
for row in rows:
rec = {}
for index, key in enumerate(keys):
rec[key] = row[index]
recs.append(rec)
return recs
def load_institutions(paperId):
if os.path.exists(file_path('pdf', paperId, 'institutions.json')):
return read_json(file_path('pdf', paperId, 'institutions.json'))['institutions']
elif os.path.exists(file_path('doi', paperId, 'institutions.json')):
return read_json(file_path('doi', paperId, 'institutions.json'))['institutions']
else:
return []
def data_path(key, paper_id):
return 'datasets/s2/{}/{}/{}'.format(key, paper_id[0:2], paper_id)
def file_path(key, paper_id, fn):
return os.path.join(data_path(key, paper_id), fn)
if __name__ == '__main__':
s2_citation_report()
|
