def testSVMTK(sentence, pairs, pairs_list, model="svm_tk_classifier.model", tag=""):
if os.path.isfile(basedir + tag + "svm_test_data.txt"):
os.remove(basedir + tag + "svm_test_data.txt")
if os.path.isfile(basedir + tag + "svm_test_output.txt"):
os.remove(basedir + tag + "svm_test_output.txt")
#docs = use_external_data(docs, excludesentences, dditype)
#pidlist = pairs.keys()
total = 0
with open(temp_dir + tag + "svm_test_data.txt", 'w') as test:
for pid in pairs:
sid = pairs[pid].sid
tree = sentence.parsetree
#if len(docs[sid][ddi.SENTENCE_ENTITIES]) > 30:
#print line
#line = reparse_tree(line)
# line = "1 |BT| (ROOT (NP (NN candidatedrug) (, ,) (NN candidatedrug))) |ET|\n"
# xerrors += 1
#else:
line = get_svm_train_line(tree, pairs[pid], sid)
line = '-' + line
test.write(line)
total += 1
#print "tree errors:", xerrors, "total:", total
svmtklightargs = ["./bin/svm-light-TK-1.2/svm-light-TK-1.2.1/svm_classify",
temp_dir + tag + "svm_test_data.txt", basedir + model,
temp_dir + tag + "svm_test_output.txt"]
svmlightcall = Popen(svmtklightargs, stdout=PIPE, stderr=PIPE)
res = svmlightcall.communicate()
# logging.debug(res[0].split('\n')[-3:])
#os.system(' '.join(svmtklightargs))
if not os.path.isfile(temp_dir + tag + "svm_test_output.txt"):
print "something went wrong with SVM-light-TK"
print res
sys.exit()
with open(temp_dir + tag + "svm_test_output.txt", 'r') as out:
lines = out.readlines()
if len(lines) != len(pairs_list):
print "check " + tag + "svm_test_output.txt! something is wrong"
print res
sys.exit()
for p, pid in enumerate(pairs):
score = float(lines[p])
if float(score) < 0:
pairs[pid].recognized_by[relations.SST_PRED] = -1
else:
pairs[pid].recognized_by[relations.SST_PRED] = 1
logging.info("{} - {} SST: {}".format(pairs[pid].entities[0], pairs[pid].entities[0], score))
return pairs
评论列表
文章目录
