def test_test_thread(path: str,
thread_num: int,
is_save_intermediate_file: bool = False) -> None:
# 有bug，废弃
Log(time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()))
Log("开始测试", path, "的数据")
exe = ExecuteCode(is_save_intermediate_file=is_save_intermediate_file)
exe_res, compile_succ = [], 0
for root, dirs, files in os.walk(path):
exe_res, compile_succ = exe.execute_code_thread(
PathFunc.to_linux(path), files, thread_num)
break
Log("编译成功数量：", compile_succ, "/", len(files))
with open("build/execute_info", "wb") as f:
pickle.dump(exe_res, f)
g = GenerateAns.GenerateAns("ans.csvc", "sample_submission.csv")
while True:
t = g.get()
if t is None:
break
g.add(1 if compare_test(exe_res[t[0]], exe_res[t[1]]) else 0)
Log(time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()))
def test_train_in_one_dir(path: str,
test_num: int = -1,
is_save_intermediate_file=False) -> None:
exe_res = []
exe = ExecuteCode(is_save_intermediate_file=is_save_intermediate_file)
Log("开始测试", path, "的数据")
count = 0
for root, dirs, files in os.walk(path):
for name in files:
if count == test_num:
break
count += 1
Log("开始编译", name)
p = PathFunc.join(PathFunc.to_linux(path), name)
exe_res.append({"res": exe.execute_code(p), "name": name})
break
Log("开始比较输出")
length = len(exe_res)
for i in range(length):
for j in range(i + 1, length):
if not compare_test(exe_res[i]["res"], exe_res[j]["res"]):
l1, l2 = exe_res[i], exe_res[j]
print("文件", exe_res[i]["name"], "和", exe_res[j]["name"],
"结果不一致")
continue
def test_test(path: str, is_save_intermediate_file: bool = False) -> None:
Log("开始测试", path, "的数据")
exe_res, compile_succ = dict(), 0
exe = ExecuteCode(is_save_intermediate_file=is_save_intermediate_file)
for root, dirs, files in os.walk(path):
total_num, cur_num = len(files), 1
for name in files:
Log("开始编译", name, "：[", str(cur_num), "/", str(total_num), "]")
cur_num += 1
p = PathFunc.join(PathFunc.to_linux(path), name)
exe_res[name.split(".")[0]], cs = exe.execute_code(p)
compile_succ += cs
break
Log("编译成功数量：", compile_succ, "/", len(files))
with open("../build/execute_info", "wb") as f:
pickle.dump(exe_res, f)
with open("../build/execute_info", "rb") as f:
exe_res = pickle.load(f)
g = GenerateAns.GenerateAns("../ans.csv", "../sample_submission.csv")
while True:
t = g.get()
if t is None:
break
g.add(1 if compare_test(exe_res[t[0]], exe_res[t[1]]) else 0)
def use_exe_save_and_analysis_str_and_csv(
save_path: str, compared_csv_path: str, csv_name: str,
model_path: str, test_dir_path: str,
test_len: int, word_len: int, thresh_num: float
) -> None:
"""
用lstm生成的答案的csv文件来生成
"""
with open(save_path, "rb") as f:
exe_res = pickle.load(f)
predict_by_network = PredictByNetwork(model_path, test_dir_path,
test_len, word_len, thresh_num)
g = GenerateAns(csv_name, "sample_submission.csv")
compared_csv = GenerateAns("", compared_csv_path)
while True:
t = g.get()
compared_csv.get()
if t is None:
break
b1 = compare_test(exe_res[t[0]], exe_res[t[1]])
b2 = analysis_str(t[0], t[1])
b3 = ((judge(exe_res[t[0]][0], exe_res[t[1]][0]) and exe_res[t[0]][0].result != -1)
or (judge(exe_res[t[0]][1], exe_res[t[1]][1]) and exe_res[t[1]][0].result != -1))\
and compared_csv.get_cur_value() == 1
p = 1 if b1 or b2 or b3 else 0
if not b1 and not b2:
print("hehehe")
g.add(p)
def test_train_random_from_same_dir(dir_path: str,
test_num: int,
is_save_intermediate_file: bool = False):
dir_list = os.listdir(dir_path)
dir_list_len = len(dir_list)
dir_file = []
for name in dir_list:
dir_file_list = os.listdir(os.path.join(dir_path, name))
dir_file.append([name, len(dir_file_list), dir_file_list])
exe = ExecuteCode(is_save_intermediate_file=is_save_intermediate_file)
is_same_num, succ_num = 0, 0
for _ in range(test_num):
i = random.randint(0, dir_list_len - 1)
j1 = random.randint(0, dir_file[i][1] - 1)
j2 = random.randint(0, dir_file[i][1] - 1)
Log("开始比较 ", dir_file[i][0], " 的 ", dir_file[i][2][j1], " 和 ",
dir_file[i][2][j2])
p1 = PathFunc.join(dir_path, dir_file[i][0], dir_file[i][2][j1])
p2 = PathFunc.join(dir_path, dir_file[i][0], dir_file[i][2][j2])
ret_list1, _ = exe.execute_code(p1)
ret_list2, _ = exe.execute_code(p2)
if not compare_test(ret_list1, ret_list2):
GLog("文件不相同")
for r1, r2 in zip(ret_list1, ret_list2):
GLog(r1, r2)
if sum([1 if x.result == 0 else 0 for x in ret_list1]) != len(ret_list1) \
or sum([1 if x.result == 0 else 0 for x in ret_list2]) != len(ret_list2):
print("diff")
else:
succ_num += 1
else:
is_same_num += 1
succ_num += 1
return is_same_num, succ_num
def use_exe_save(save_path: str, csv_name: str) -> None:
with open(save_path, "rb") as f:
exe_res = pickle.load(f)
g = GenerateAns(csv_name, "sample_submission.csv")
while True:
t = g.get()
if t is None:
break
g.add(1 if compare_test(exe_res[t[0]], exe_res[t[1]]) else 0)
def use_exe_save_and_analysis_str(save_path: str, csv_name: str) -> None:
"""
有点点效果，提升到了0.74
"""
with open(save_path, "rb") as f:
exe_res = pickle.load(f)
g = GenerateAns(csv_name, "sample_submission.csv")
while True:
t = g.get()
if t is None:
break
g.add(1 if compare_test(exe_res[t[0]], exe_res[t[1]]) or analysis_str(t[0], t[1]) else 0)
def use_exe_save_and_analysis_str_and_xgboost(save_path: str, csv_name: str,
test_index_map: str, network_result_path: str) -> None:
with open(save_path, "rb") as f:
exe_res = pickle.load(f)
gcr = GetCompareResult(test_index_map, network_result_path)
g = GenerateAns(csv_name, "sample_submission.csv")
while True:
t = g.get()
if t is None:
break
xgboost_bool = gcr.get(t[0], t[1])
# xgboost_bool = False
g.add(1 if compare_test(exe_res[t[0]], exe_res[t[1]]) or analysis_str(t[0], t[1]) or xgboost_bool else 0)
def use_exe_save_and_analysis_str_input_output_loop(save_path: str, csv_name: str) -> None:
"""
效果不佳，调出的最好成绩为0.70
"""
with open(save_path, "rb") as f:
exe_res = pickle.load(f)
g = GenerateAns(csv_name, "sample_submission.csv")
while True:
t = g.get()
if t is None:
break
g.add(1 if compare_test(exe_res[t[0]], exe_res[t[1]])
or analysis_str(t[0], t[1])
or analysis_input_output_loop_num(t[0], t[1])
else 0)
def use_exe_save_and_analysis_str_and_network(
save_path: str, csv_name: str,
model_path: str, test_dir_path: str,
test_len: int, word_len: int, thresh_num: float
) -> None:
"""
辅助以lstm
"""
with open(save_path, "rb") as f:
exe_res = pickle.load(f)
predict_by_network = PredictByNetwork(model_path, test_dir_path,
test_len, word_len, thresh_num)
g = GenerateAns(csv_name, "sample_submission.csv")
while True:
t = g.get()
if t is None:
break
g.add(1 if compare_test(exe_res[t[0]], exe_res[t[1]])
or analysis_str(t[0], t[1])
or predict_by_network.predict(t[0], t[1])
else 0)