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
|
#!/usr/bin/env python
'''
This benchmark will produce graph digests for all of the
downloadable ontologies available in Bioportal.
'''
from rdflib import *
from rdflib.compare import to_isomorphic
import sys, csv
from urllib import *
from io import StringIO
from collections import defaultdict
from urllib2 import urlopen
from multiprocessing import *
from Queue import Empty
bioportal_query = '''
PREFIX metadata: <http://data.bioontology.org/metadata/>
select distinct ?ontology ?title ?download where {
?ontology a metadata:Ontology;
metadata:omvname ?title;
metadata:links ?links.
?links metadata:Ontology ?download.
filter(regex(?download, "/download"))
}
'''
stat_cols = [
'id',
'ontology',
'download_url',
'tree_depth',
'color_count',
'individuations',
'prunings',
'initial_color_count',
'adjacent_nodes',
'initial_coloring_runtime',
'triple_count',
'graph_digest',
'to_hash_runtime',
'canonicalize_triples_runtime',
'error',
]
def files_benchmark(ontologies, output_file, threads):
w = open(output_file, 'w')
writer = csv.DictWriter(w, stat_cols)
writer.writeheader()
tasks = Queue()
finished_tasks = Queue()
dl_lock = Semaphore(4)
task_count = len(ontologies)
def worker(q, finished_tasks, dl_lock):
try:
while True:
stats = q.get()
og = Graph()
try:
og.load(stats['download_url'])
print stats['ontology'], stats['id']
ig = to_isomorphic(og)
graph_digest = ig.graph_digest(stats)
finished_tasks.put(stats)
except Exception as e:
print 'ERROR', stats['id'], e
stats['error'] = str(e)
finished_tasks.put(stats)
except Empty:
pass
for i in range(int(threads)):
print "Starting worker", i
t = Process(target=worker, args=[tasks, finished_tasks, dl_lock])
t.daemon = True
t.start()
for download in ontologies:
stats = defaultdict(str)
stats.update({
"id": download.split("/")[-1].split(".")[0],
"ontology": download.split("/")[-1].split(".")[0],
"download_url": download
})
tasks.put(stats)
tasks.close()
written_tasks = 0
while written_tasks < task_count:
stats = finished_tasks.get()
# print "Writing", stats['ontology']
writer.writerow(stats)
w.flush()
written_tasks += 1
def bioportal_benchmark(apikey, output_file, threads):
metadata = Namespace("http://data.bioontology.org/metadata/")
url = 'http://data.bioontology.org/ontologies?apikey=%s' % apikey
ontology_graph = Graph()
print url
ontology_list_json = urlopen(url).read()
ontology_graph.parse(StringIO(unicode(ontology_list_json)), format="json-ld")
ontologies = ontology_graph.query(bioportal_query)
w = open(output_file, 'w')
writer = csv.DictWriter(w, stat_cols)
writer.writeheader()
tasks = Queue()
finished_tasks = Queue()
dl_lock = Semaphore(4)
task_count = len(ontologies)
def worker(q, finished_tasks, dl_lock):
try:
while True:
stats = q.get()
og = Graph()
try:
try:
dl_lock.acquire()
og.load(stats['download_url'] + "?apikey=%s" % apikey)
finally:
dl_lock.release()
print stats['ontology'], stats['id']
ig = to_isomorphic(og)
graph_digest = ig.graph_digest(stats)
finished_tasks.put(stats)
except Exception as e:
print 'ERROR', stats['id'], e
stats['error'] = str(e)
finished_tasks.put(stats)
except Empty:
pass
for i in range(int(threads)):
print "Starting worker", i
t = Process(target=worker, args=[tasks, finished_tasks, dl_lock])
t.daemon = True
t.start()
for ontology, title, download in ontologies:
stats = defaultdict(str)
stats.update({
"id": ontology,
"ontology": title,
"download_url": download
})
tasks.put(stats)
tasks.close()
written_tasks = 0
while written_tasks < task_count:
stats = finished_tasks.get()
# print "Writing", stats['ontology']
writer.writerow(stats)
w.flush()
written_tasks += 1
if __name__ == '__main__':
if len(sys.argv) > 4:
files_benchmark(sys.argv[1:-2], sys.argv[-2], sys.argv[-1])
else:
bioportal_benchmark(sys.argv[1], sys.argv[2], sys.argv[3])
|
