async def main():
judger = Judger()
judger.addLocalPlayer(0, aiArgs)
judger.addLocalPlayer(1, aiArgs)
returnCode = await judger.startJudge(logicArgs, "", 'replay',
(int)(sys.argv[1]))
print(returnCode)
def __init__(self, **kwargs):
self.train_path = kwargs["train_path"]
self.valid_path = kwargs["valid_path"]
self.test_path = kwargs["test_path"]
self.accusation_path = kwargs["accusation_path"]
self.law_path = kwargs["law_path"]
self.judger = Judger(accusation_path=self.accusation_path, law_path=self.law_path)
self.train(train_path=train_path)
print("\nValid F-score......")
self.calculate_metrics(path=self.valid_path)
print("\nTest F-score......")
self.calculate_metrics(path=self.test_path)
def perform_create(self, serializer):
#submission = serializer.save(user=self.request.user)
from account.models import User
submission = serializer.save(user=User.objects.get(username='******'))
# TODO 已完成：调用评测函数
Judger(submission_id=submission.id,
on_finished=Submission.update_all_statistic_info,
args=get_dict(id=submission.id))\
.judge_async()
class Metrics(object):
"""
Metrics
"""
def __init__(self, **kwargs):
self.train_path = kwargs["train_path"]
self.valid_path = kwargs["valid_path"]
self.test_path = kwargs["test_path"]
self.accusation_path = kwargs["accusation_path"]
self.law_path = kwargs["law_path"]
self.judger = Judger(accusation_path=self.accusation_path,
law_path=self.law_path)
self.train(train_path=train_path)
print("\nValid F-score......")
self.calculate_metrics(path=self.valid_path)
print("\nTest F-score......")
self.calculate_metrics(path=self.test_path)
def train(self, train_path):
"""
:param train_path:
:return:
"""
print("reading...")
alltext, accu_label, law_label, time_label = read_trainData(train_path)
print("cut text...")
train_data = cut_text(alltext)
print("train tfidf...")
tfidf = train_tfidf(train_data)
vec = tfidf.transform(train_data)
print('accu SVC')
accu = train_SVC(vec, accu_label)
print('law SVC')
law = train_SVC(vec, law_label)
print('time SVC')
time = train_SVC(vec, time_label)
print('saving model to ./predictor/model/*.model')
joblib.dump(tfidf, './predictor/model/tfidf.model')
joblib.dump(accu, './predictor/model/accu.model')
joblib.dump(law, './predictor/model/law.model')
joblib.dump(time, './predictor/model/time.model')
def calculate_metrics(self, path):
"""
:param path:
:return:
"""
predictor = Predictor()
cnt = 0
result = [[], [], {}]
for a in range(0, self.judger.task1_cnt):
result[0].append({"TP": 0, "FP": 0, "TN": 0, "FN": 0})
for a in range(0, self.judger.task2_cnt):
result[1].append({"TP": 0, "FP": 0, "TN": 0, "FN": 0})
result[2] = {"cnt": 0, "score": 0}
with open(path, encoding="UTF-8") as f:
for line in f.readlines():
line = json.loads(line)
ground_truth = line["meta"]
fact = line["fact"]
ans = predictor.predict(fact)
cnt += 1
result = self.judger.gen_new_result(result, ground_truth,
ans[0])
scores = self.judger.get_score(result)
# print(result)
print(scores)
return result
for file_name in os.listdir(data_path):
inf = open(os.path.join(data_path, file_name), "r")
ouf = open(os.path.join(output_path, file_name), "w")
fact = []
for line in inf:
fact.append(json.loads(line)["fact"])
if len(fact) == get_batch():
result = solve(fact)
cnt += len(result)
for x in result:
print(json.dumps(x), file=ouf)
fact = []
if len(fact) != 0:
result = solve(fact)
cnt += len(result)
for x in result:
print(json.dumps(x), file=ouf)
fact = []
inf.close()
ouf.close()
jud = Judger(accusation_path='/home/wshong/Downloads/cail_0518/accu.txt',
law_path='/home/wshong/Downloads/cail_0518/law.txt')
res = jud.test(truth_path=data_path, output_path=output_path)
jud.get_score(result=res)
test_filename = 'data_test.json'
pred = PredictorLocal(tfidf, law, accu, time)
all_test_predicts = []
all_test_metas = []
test_f = open(test_filename)
for line in test_f:
js = json.loads(line)
text = js["fact"]
meta = js["meta"]
ans = pred.predict(text)
all_test_predicts.append(ans)
all_test_metas.append(meta)
#metrics
judge = Judger("../baseline/accu.txt", "../baseline/law.txt")
result = judge.test2(all_test_metas, all_test_predicts)
rst = judge.get_score(result)
print(rst)
rstr = "ACCU:(%.4f, %.4f, %.4f); LAW:(%.4f, %.4f, %.4f) TIME: %.4f"% \
(rst[0][0], rst[0][1], rst[0][2], rst[1][0], rst[1][1], rst[1][2], rst[2])
sinfo = 'Seg:%s DIM:%s NGRAM:%d RESULT: %s' % (seg_method, dim, ngram,
rstr)
logger.info(sinfo)
'''
print('begin test model:')
print('saving model')
joblib.dump(tfidf, 'predictor/model/tfidf.model')
joblib.dump(accu, 'predictor/model/accu.model')
from judger.judger import Judger
INPUT = 'input/small/'
OUTPUT = 'output/'
jud = Judger('accu.txt', 'law.txt')
res = jud.test(INPUT, OUTPUT)
print(res)
scor = jud.get_score(res)
print(scor)
print('FIN')
#accu = train_SVC(vec, accu_label)
print('law SVC')
sys.stdout.flush()
#law = train_SVC(vec, law_label)
print('time SVC')
sys.stdout.flush()
#time = train_SVC(vec, time_label)
#test
print('predict')
sys.stdout.flush()
predictor = PredictorLocal(tfidf, accu, law, time)
test_label, test_predict = predictor.predict_file(test_filename)
#metrics
judge = Judger("../baseline/accu.txt", "../baseline/law.txt")
result = judge.test2(test_label, test_predict)
print(result)
rst = judge.get_score(result)
print(rst)
rstr = "ACCU:(%.4f, %.4f, %.4f); LAW:(%.4f, %.4f, %.4f) TIME: %.4f"% \
(rst[0][0], rst[0][1], rst[0][2], rst[1][0], rst[1][1], rst[1][2], rst[2])
sinfo = 'Prog: %s TrainFile: %s Seg:%s DIM:%s NGRAM:%d RESULT: %s' % \
(sys.argv[0], train_fname, seg_method, dim, ngram, rstr)
logger.info(sinfo)
print('begin test model:')
print('saving model')
joblib.dump(tfidf, 'predictor/model/tfidf.model')