def test_singletons(self):
tr = TreeFile(SINGLETONS)
for recs in make_expert_rec(tr):
raise "This shouldn't ever happen"
tr = TreeFile(SINGLETONS)
for recs in make_classic_recs(tr):
raise "This shouldn't ever happen"
def test_singletons(self):
tr = TreeFile(SINGLETONS)
for recs in make_expert_rec(tr):
raise "This shouldn't ever happen"
tr = TreeFile(SINGLETONS)
for recs in make_classic_recs(tr):
raise "This shouldn't ever happen"
def make_classic(args, b, t):
with t.get_batch_put_context() as batch:
args.tree.seek(0)
parser = TreeFile(args.tree)
for classic_rec in process_record_stream(make_classic_recs(parser)):
if args.verbose:
print(classic_rec)
if not args.dryrun:
batch.put_item(classic_rec)
b.increment()
def make_classic(args, b, t):
with t.get_batch_put_context() as batch:
args.tree.seek(0)
parser = TreeFile(args.tree)
for classic_rec in process_record_stream(make_classic_recs(parser)):
if args.verbose:
print(classic_rec)
if not args.dryrun:
batch.put_item(classic_rec)
b.increment()
tf = TreeFile(args.infile)
if args.batch_size:
writer = leveldb.WriteBatch()
else:
writer = db
for recs in make_expert_rec(tf, args.limit):
recd = [r.pid for r in recs]
key = recs[0].target_pid + "|expert"
writer.Put(key.encode(), msgpack.packb(recd))
b.increment()
if args.batch_size and b.count % args.batch_size == 0:
db.Write(writer)
args.infile.seek(0)
tf = TreeFile(args.infile)
for recs in make_classic_recs(tf, args.limit):
recd = [r.pid for r in recs]
key = recs[0].target_pid + "|classic"
writer.Put(key.encode(), msgpack.packb(recd))
b.increment()
if args.batch_size and b.count % args.batch_size == 0:
db.Write(writer)
if args.batch_size:
db.Write(writer, sync=True)
b.print_freq()
print(db.GetStats())
def test_classic_limit(self):
for recs in make_classic_recs(self.tr, 5):
recd = [r.pid for r in recs]
answer = make_answer(CLASSIC, recs[0].target_pid)[:5]
self.assertListEqual(recd, answer)
def test_classic(self):
for recs in make_classic_recs(self.tr):
recd = [r.pid for r in recs]
self.assertListEqual(recd, make_answer(CLASSIC, recs[0].target_pid))
if args.verbose:
print(expert_rec)
if not args.dryrun:
batch.put_item(expert_rec)
entries += 1
if entries % 50000 == 0:
current_time = time.time()
current_rate = entries/(current_time - start)
print("\nProcessed {0:,} entries in {1:.0f} seconds: {2:.2f} entries/sec".format(entries, time.time()-start, entries/(time.time()-start)))
sys.stdout.flush()
# Reset for the second pass
print("Generating classic recommendations...")
args.tree.seek(0)
parser = TreeFile(args.tree)
for classic_rec in process_record_stream(make_classic_recs(parser)):
if args.verbose:
print(classic_rec)
if not args.dryrun:
batch.put_item(classic_rec)
entries += 1
if entries % 50000 == 0:
current_time = time.time()
current_rate = entries/(current_time - start)
print("\nProcessed {0:,} entries in {1:.0f} seconds: {2:.2f} entries/sec".format(entries, time.time()-start, entries/(time.time()-start)))
sys.stdout.flush()
end = time.time()
print("\nProcessed {0:,} entries in {1:.0f} seconds: {2:.2f} entries/sec".format(entries, end-start, entries/(end-start)))
if not args.dryrun:
t.update_throughput()
def test_classic_limit(self):
for recs in make_classic_recs(self.tr, 5):
recd = [r.pid for r in recs]
answer = make_answer(CLASSIC, recs[0].target_pid)[:5]
self.assertListEqual(recd, answer)
def test_classic(self):
for recs in make_classic_recs(self.tr):
recd = [r.pid for r in recs]
self.assertListEqual(recd, make_answer(CLASSIC,
recs[0].target_pid))
from recommenders.ef import make_classic_recs, make_expert_rec
from util.misc import Benchmark
if __name__ == "__main__":
import argparse
import sys
parser = argparse.ArgumentParser(description="Creates EF recommendations and store them in a DBM")
parser.add_argument('infile', nargs='?', type=argparse.FileType('r'), default=sys.stdin)
parser.add_argument('shelf')
parser.add_argument('--benchmark-freq', default=10000, type=int)
parser.add_argument('--toint', help="Convert scores to integers, larger is better", action='store_true', default=False)
parser.add_argument('-l', '--limit', type=int, help="Max number of recommendations to generate per-paper", default=10)
args = parser.parse_args()
tf = TreeFile(args.infile)
b = Benchmark(args.benchmark_freq)
with shelve.open(args.shelf, flag='n', protocol=pickle.HIGHEST_PROTOCOL) as s:
for recs in make_expert_rec(tf, args.limit):
recd = [r.pid for r in recs]
s['expert|'+recs[0].target_pid] = recd
b.increment()
args.infile.seek(0)
tf = TreeFile(args.infile)
for recs in make_classic_recs(tf, args.limit):
recd = [r.pid for r in recs]
s['classic|'+recs[0].target_pid] = recd
b.increment()
b.print_freq()
