def score(msg):
ret = {}
msg = decode_netstring_fd(cStringIO.StringIO(msg))
#cueset_size, cues = ainodex.expand_cueset(
# map(int, msg['cues'].split()))
cueset_size, cues = ainodex.hits(map(int, msg['cues'].split()), 0)
cueset_size, cues = filter_hits(cueset_size, cues,\
prior_check = True, site_check = True)
ret['cueset_size'] = str(cueset_size)
ok_layers = [
i for i, maxf in enumerate(LAYERS)
if min(maxf, cueset_size) / float(max(maxf, cueset_size)) > MIN_SCORE
]
if len(LAYERS) - 1 in ok_layers:
ok_layers.append(len(LAYERS))
print "OK", ok_layers, "CUES", cueset_size
t = time.time()
for i in ok_layers:
layer = ainodex.new_layer(i, cues)
ret[str(i)] = ainodex.serialize_layer(layer)
erlay.report("Scoring <%s> took %dms" % (msg['cues'],
(time.time() - t) * 1000.0))
return encode_netstring_fd(ret)
def score(msg):
ret = {}
msg = decode_netstring_fd(cStringIO.StringIO(msg))
#cueset_size, cues = ainodex.expand_cueset(
# map(int, msg['cues'].split()))
cueset_size, cues = ainodex.hits(map(int, msg['cues'].split()), 0)
cueset_size, cues = filter_hits(cueset_size, cues,\
prior_check = True, site_check = True)
ret['cueset_size'] = str(cueset_size)
ok_layers = [i for i, maxf in enumerate(LAYERS)
if min(maxf, cueset_size) / float(max(maxf, cueset_size))
> MIN_SCORE]
if len(LAYERS) - 1 in ok_layers:
ok_layers.append(len(LAYERS))
print "OK", ok_layers, "CUES", cueset_size
t = time.time()
for i in ok_layers:
layer = ainodex.new_layer(i, cues)
ret[str(i)] = ainodex.serialize_layer(layer)
erlay.report("Scoring <%s> took %dms" %
(msg['cues'], (time.time() - t) * 1000.0))
return encode_netstring_fd(ret)
ainodex.open()
if len(sys.argv) < 2:
print "Usage: simple [key] [cue]"
sys.exit(1)
keys = ainodex.token2ixeme(sys.argv[1])
cues = ainodex.token2ixeme(sys.argv[2])
print "KEYS", keys, "CUES", cues
hits_len, hitset = ainodex.hits([keys], 0)
cues_len, cueset = ainodex.hits([cues], 0)
print "%s occurs in %d segments" % (sys.argv[1], hits_len)
print "%s occurs in %d segments" % (sys.argv[2], cues_len)
# Word frequencies
normtable = ainodex.normtable_to_judy(ainodex.normtable())
# Compute how many times tokens co-occur with the cueset
layers = [ainodex.new_layer(i, cueset) for i in range(10)]
for layer in layers:
# Compute token scores
ainodex.normalize_layer(layer, normtable, cues_len)
ranked = ainodex.rank(hitset, layers)
doc_keys = array.array("I", ranked)[:20:2]
doc_scores = array.array("f", ranked)[1:20:2]
print zip(doc_keys, doc_scores)
ainodex.open()
if len(sys.argv) < 2:
print "Usage: simple [key] [cue]"
sys.exit(1)
keys = ainodex.token2ixeme(sys.argv[1])
cues = ainodex.token2ixeme(sys.argv[2])
print "KEYS", keys, "CUES", cues
hits_len, hitset = ainodex.hits([keys], 0)
cues_len, cueset = ainodex.hits([cues], 0)
print "%s occurs in %d segments" % (sys.argv[1], hits_len)
print "%s occurs in %d segments" % (sys.argv[2], cues_len)
# Word frequencies
normtable = ainodex.normtable_to_judy(ainodex.normtable())
# Compute how many times tokens co-occur with the cueset
layers = [ainodex.new_layer(i, cueset) for i in range(10)]
for layer in layers:
# Compute token scores
ainodex.normalize_layer(layer, normtable, cues_len)
ranked = ainodex.rank(hitset, layers)
doc_keys = array.array("I", ranked)[:20:2]
doc_scores = array.array("f", ranked)[1:20:2]
print zip(doc_keys, doc_scores)
