File size: 1,489 Bytes
a7b3936 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 |
import sys
def write_combined(dirs):
path = "./saved_models/"+dirs+"/final_ensembled/"
f = open(path+'domain_san_test_model_domain_san_data_domain_san_gold.txt','r')
gold = f.readlines()
f.close()
f = open(path+'domain_san_test_model_domain_san_data_domain_san_pred.txt','r')
pred = f.readlines()
f.close()
for i in range(len(gold)):
if gold[i] == '\n':
continue
if gold[i].split('\t')[0] == pred[i].split('\t')[0]:
gold[i] = gold[i].replace('\n','\t')
gold[i] = gold[i]+'\t'.join(pred[i].split('\t')[-2:])
f = open(path+'domain_san_prose_model_domain_san_data_domain_san_gold.txt','r')
prose_gold = f.readlines()
f.close()
f = open(path+'domain_san_prose_model_domain_san_data_domain_san_pred.txt','r')
prose_pred = f.readlines()
f.close()
for i in range(len(prose_gold)):
if prose_gold[i] == '\n':
gold.append('\n')
continue
if prose_gold[i].split('\t')[0] == prose_pred[i].split('\t')[0]:
line = prose_gold[i].replace('\n','\t')
line =line+'\t'.join(prose_pred[i].split('\t')[-2:])
gold.append(line)
gold.insert(0,'word_id\tword\tpostag\tlemma\tgold_head\tgold_label\tpred_head\tpred_label\n\n')
f = open(path+'combined_1300_test.txt','w')
for line in gold:
f.write(line)
f.close()
if __name__=="__main__":
dir_path = sys.argv[1]
write_combined(dir_path)
|