args.pairStartIndex) + "." + str(args.pairEndIndex) + ".txt" #
print("loading dictionary/embedding")
dictionary = helper.load_object(args.save_path + 'gene_dictionary.p')
embeddings_index = helper.load_word_embeddings(args.word_vectors_directory,
args.word_vectors_file,
dictionary.word2idx)
print("loading model")
# print (args)
model = SentenceClassifier(dictionary,
embeddings_index,
args,
select_method='max')
if args.cuda:
model = model.cuda()
helper.load_model_states_from_checkpoint(
model, args.save_path + 'model_best.pth.tar', 'state_dict', args.cuda)
print('vocabulary size = ', len(dictionary))
annotationBP = pickle.load(
open(args.goAnnotationFile + "goBP.cPickle", "rb"))
annotationCC = pickle.load(
open(args.goAnnotationFile + "goCC.cPickle", "rb"))
annotationMF = pickle.load(
open(args.goAnnotationFile + "goMF.cPickle", "rb"))
annotationAll3 = pickle.load(
open(args.goAnnotationFile + "go3ontology.cPickle", "rb"))
f = open(args.pairs2test,
'r') ## load genes to be tested. [[gene1,gene2],...]
pairs = []
for line in f:
0, di + 1].data].data.cpu().numpy()[0]
return gen_prob
if __name__ == "__main__":
dictionary = helper.load_object(args.save_path + 'dictionary.p')
embeddings_index = helper.load_word_embeddings(args.word_vectors_directory,
args.word_vectors_file,
dictionary.word2idx)
model = Seq2Seq(dictionary, embeddings_index, args)
print(model)
if args.cuda:
model = model.cuda()
helper.load_model_states_from_checkpoint(
model, os.path.join(args.save_path, 'model_best.pth.tar'),
'state_dict', args.cuda)
print('model, embedding index and dictionary loaded.')
model.eval()
# load the test dataset
test_corpus = data.Corpus(args.tokenize, args.max_query_length)
test_corpus.parse(args.data + 'dev.txt', args.max_example, False)
print('test set size = ', len(test_corpus.data))
candidate_map = dict()
with open('../data/anchor_candidates.txt', 'r') as f:
for line in f:
tokens = line.strip().split(':::')
candidate_map[tokens[0]] = []
for i in range(1, len(tokens)):
