parser.add_argument('-t', '--threshold', type=float, default=0.0)
args = parser.parse_args()
for key in vars(args).keys():
print(key, ":", vars(args)[key])
print("--- Result ---")
if (args.build == True):
model = Lecture2Vec()
model.build(vocab=args.vocab, corpus=args.corpus, name=args.name)
if (args.pred == True):
pred = Predictor(name=args.name)
lecture_file = open(args.lecture, 'r')
lecture_list = lecture_file.read().splitlines()
lectures = []
for l in lecture_list:
tokens = l.split()
vector = pred.get_vector(words=tokens)
lectures.append((l, vector))
most_similars = {}
for lecture in lectures:
most_similars[lecture[0]] = pred.most_similar(
target=lecture, lectures=lectures, threshold=args.threshold)
for k in most_similars.keys():
print(k)
print(most_similars[k])
print("-" * 10)
