parser.add_argument("--maxN", dest="maxn", type=int, help="")
parser.set_defaults(thread=cpu_count())
parser.add_argument("-t", "--thread", dest="thread", type=int, help="the number of threads")
parser.set_defaults(knn=1)
parser.add_argument("-k", "--knn", dest="knn", type=int, help="use k of the nearest neighbors (default 1)")
args = parser.parse_args()
test_file = args.test
topK = args.knn
maxN = args.maxn
if not args.modelfile1 or not args.modelfile2:
print "Specify modelfile1 and modelfile2"
quit(-1)
logging.info("load trained model file")
modelfile1 = args.modelfile1
model1 = Sentence2Vec.load(modelfile1)
modelfile2 = args.modelfile2
model2 = Sentence2Vec.load(modelfile2)
sent_cat = readSentence(CatSentence(args.train, cont_col=3, split=args.split))
test_sentences = CatSentence(test_file)
confusion_mtx = {}
def prepare_sentences():
count = 0
for sent_tuple in test_sentences:
yield sent_tuple
count += 1
if count > maxN:
break
if __name__ == "__main__":
logging.basicConfig(format='%(asctime)s : %(threadName)s : %(levelname)s : %(message)s', level=logging.INFO)
current_dir = os.path.dirname(os.path.realpath(__file__))
wikip_data = current_dir+"/"+wiki_name
s2v_model_name = current_dir+"/"+model_dir+"/"+ wiki_name + "_sent.model"
if not os.path.exists(current_dir+"/"+model_dir):
os.mkdir(current_dir+"/"+model_dir)
if not os.path.isfile(wikip_data):
logger.info("downloading Wikipedia data")
urllib.urlretrieve(wiki_url, wikip_data)
logger.info("downloaded in %s" % wikip_data)
sentences = WikiSentence(wikip_data)
if not os.path.isfile(s2v_model_name):
model = Sentence2Vec(sentences,iteration=10, model="cb", hs = 1, negative = 0, size=300, update_mode = 0)
model.save(s2v_model_name)
else:
model = Sentence2Vec.load(s2v_model_name)
print "Input an article title (type EXIT to exit)"
sys.stdout.write("Name: ")
line = sys.stdin.readline()
while line:
line = utils.to_unicode(line.rstrip())
if line == "EXIT":
break
try:
if model.sent_no_hash.has_key(line):
sent_no = model.sent_no_hash[line]
sent_vec = model.sents[sent_no]
sent_cat[sent_id] = cat_id
return sent_cat
if __name__ == "__main__":
logging.basicConfig(
format=
'%(asctime)s %(relativeCreated)d : %(threadName)s : %(levelname)s : %(message)s',
level=logging.INFO)
logging.info("running %s" % " ".join(sys.argv))
program = os.path.basename(sys.argv[0])
if len(sys.argv) < 2:
print(globals()['__doc__'] % locals())
sys.exit(1)
parser = Sentence2Vec.arg_parser()
parser.add_argument("--split",
dest="split",
action="store_true",
help="use this option for split training data",
default=False)
parser.add_argument("--modelfile",
dest="modelfile",
type=str,
help="trained model file")
parser.add_argument("--test", dest="test", type=str, help="test file")
parser.set_defaults(maxn=sys.maxint)
parser.add_argument("--maxN", dest="maxn", type=int, help="")
parser.set_defaults(knn=1)
parser.add_argument("-k",
"--knn",
sent_cat = {}
for tpl in sent:
sent_id = tpl[1]
cat_id = tpl[2]
sent_cat[sent_id] = cat_id
return sent_cat
if __name__ == "__main__":
logging.basicConfig(format='%(asctime)s %(relativeCreated)d : %(threadName)s : %(levelname)s : %(message)s', level=logging.INFO)
logging.info("running %s" % " ".join(sys.argv))
program = os.path.basename(sys.argv[0])
if len(sys.argv) < 2:
print(globals()['__doc__'] % locals())
sys.exit(1)
parser = Sentence2Vec.arg_parser()
parser.add_argument("--split", dest="split", action="store_true", help="use this option for split training data", default=False)
parser.add_argument("--modelfile", dest="modelfile", type=str, help="trained model file")
parser.add_argument("--test", dest="test", type=str, help="test file")
parser.set_defaults(maxn=sys.maxint)
parser.add_argument("--maxN", dest="maxn", type=int, help="")
parser.set_defaults(knn=1)
parser.add_argument("-k","--knn", dest="knn", type=int, help="use k of the nearest neighbors (default 1)")
args = parser.parse_args()
test_file = args.test
topK = args.knn
maxN = args.maxn
if not args.train:
print "ERROR: specify training set"
quit()
parser.add_argument("-k",
"--knn",
dest="knn",
type=int,
help="use k of the nearest neighbors (default 1)")
args = parser.parse_args()
test_file = args.test
topK = args.knn
maxN = args.maxn
if not args.modelfile1 or not args.modelfile2:
print "Specify modelfile1 and modelfile2"
quit(-1)
logging.info("load trained model file")
modelfile1 = args.modelfile1
model1 = Sentence2Vec.load(modelfile1)
modelfile2 = args.modelfile2
model2 = Sentence2Vec.load(modelfile2)
sent_cat = readSentence(
CatSentence(args.train, cont_col=3, split=args.split))
test_sentences = CatSentence(test_file)
confusion_mtx = {}
def prepare_sentences():
count = 0
for sent_tuple in test_sentences:
yield sent_tuple
count += 1
if count > maxN: break
