diff options
| author | Joern Hees <dev@joernhees.de> | 2014-12-08 17:01:02 +0100 |
|---|---|---|
| committer | Joern Hees <dev@joernhees.de> | 2014-12-08 17:08:19 +0100 |
| commit | 8e78708e0dd3a36d8e54796f78fd27957255b47a (patch) | |
| tree | 0e3bcbab69765e2e3a2f3646fd5f81ebc818d0e7 /examples | |
| parent | b29e0b08b8171e33a9da25a5b7287fdce5ce229b (diff) | |
| download | rdflib-8e78708e0dd3a36d8e54796f78fd27957255b47a.tar.gz | |
minor: code style guides
Diffstat (limited to 'examples')
| -rw-r--r-- | examples/graph_digest_benchmark.py | 50 |
1 files changed, 27 insertions, 23 deletions
diff --git a/examples/graph_digest_benchmark.py b/examples/graph_digest_benchmark.py index c7c374f8..d987cf18 100644 --- a/examples/graph_digest_benchmark.py +++ b/examples/graph_digest_benchmark.py @@ -1,7 +1,7 @@ #!/usr/bin/env python ''' -This benchmark will produce graph digests for all of the +This benchmark will produce graph digests for all of the downloadable ontologies available in Bioportal. ''' @@ -25,36 +25,38 @@ select distinct ?ontology ?title ?download where { metadata:links ?links. ?links metadata:Ontology ?download. filter(regex(?download, "/download")) -} +} ''' stat_cols = [ 'id', 'ontology', 'download_url', - 'tree_depth', - 'color_count', - 'individuations', + 'tree_depth', + 'color_count', + 'individuations', 'prunings', - 'initial_color_count', - 'adjacent_nodes', - 'initial_coloring_runtime', - 'triple_count', + '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 = 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): + + def worker(q, finished_tasks, dl_lock): try: while True: stats = q.get() @@ -73,13 +75,13 @@ def files_benchmark(ontologies, output_file, threads): pass for i in range(int(threads)): print "Starting worker", i - t = Process(target=worker, args=[tasks,finished_tasks, dl_lock]) + 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], + "id": download.split("/")[-1].split(".")[0], "ontology": download.split("/")[-1].split(".")[0], "download_url": download }) @@ -88,27 +90,29 @@ def files_benchmark(ontologies, output_file, threads): written_tasks = 0 while written_tasks < task_count: stats = finished_tasks.get() - #print "Writing", stats['ontology'] + # 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 + 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 = 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): + + def worker(q, finished_tasks, dl_lock): try: while True: stats = q.get() @@ -116,7 +120,7 @@ def bioportal_benchmark(apikey, output_file, threads): try: try: dl_lock.acquire() - og.load(stats['download_url']+"?apikey=%s"%apikey) + og.load(stats['download_url'] + "?apikey=%s" % apikey) finally: dl_lock.release() print stats['ontology'], stats['id'] @@ -131,13 +135,13 @@ def bioportal_benchmark(apikey, output_file, threads): pass for i in range(int(threads)): print "Starting worker", i - t = Process(target=worker, args=[tasks,finished_tasks, dl_lock]) + 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, + "id": ontology, "ontology": title, "download_url": download }) @@ -146,13 +150,13 @@ def bioportal_benchmark(apikey, output_file, threads): written_tasks = 0 while written_tasks < task_count: stats = finished_tasks.get() - #print "Writing", stats['ontology'] + # 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]) + files_benchmark(sys.argv[1:-2], sys.argv[-2], sys.argv[-1]) else: bioportal_benchmark(sys.argv[1], sys.argv[2], sys.argv[3]) |
