pred_numpy = (y_pred.data).cpu().numpy()
y_pred_labels = [ix_to_label[ix] for ix in pred_numpy]
assert len(y_pred_labels) == len(
features), 'y_pred_labels and features have different lengths'
for i, pred_label in enumerate(y_pred_labels):
features[i][5] = pred_label
instances.append(features[i])
acc = 100.0 * correct / total
return acc, instances
if __name__ == "__main__":
traindocuments = parserNcbiTxtFile_simple(opt.train_file)
devdocuments = parserNcbiTxtFile_simple(opt.dev_file)
testdocuments = parserNcbiTxtFile_simple(opt.test_file)
entityAbbres = loadAbbreviations(opt.abbre_file)
preprocessMentions(traindocuments, devdocuments, testdocuments,
entityAbbres)
dict = load_dict(opt.dict_file)
meshlabels, meshlabel_to_ix, dict_words = utils.parser_dict(dict)
corpus_words = utils.parser_corpus(traindocuments, devdocuments,
testdocuments)
word_to_ix, all_words, char_to_ix = utils.generate_word_alphabet(
corpus_words, dict_words)
if opt.random_emb:
return entity_docs
if __name__ == '__main__':
ner_path = "/home/lyx/workspace/Dnorm_ncbi/ncbi_test_plain_ner"
output_path_doc = "./sample_data/ncbi_test_ner_evalNorm"
output_path_entity = "/home/lyx/workspace/Dnorm_ncbi/ncbi_test_plain_ner_entities"
ncbi_ner_path = "/home/lyx/workspace/Dnorm_ncbi/output/analysis_ncbi.txt"
# entity_docs = load_entity_doc(ner_path)
entity_docs = load_entity_doc(ncbi_ner_path)
test_documents = parserNcbiTxtFile_simple(opt.test_file)
for i in range(len(entity_docs)):
isfind = False
for test_doc in test_documents:
if entity_docs[i].doc_name == test_doc.doc_name:
isfind =True
entity_docs[i].title = test_doc.title
entity_docs[i].abstractt = test_doc.abstractt
break
if not isfind:
print(entity_docs[i].doc_name)
outputDocuments_title_abstract_entity(output_path_doc, entity_docs)
# outputDocuments_ner_entities(output_path_entity, entity_docs)
print('end')