def count():
sort = load_data(sort_path, "cpp")
tree = load_data(tree_path, "cpp")
dp = load_data(dp_path, "cpp")
print(sort.__len__())
print(tree.__len__())
print(dp.__len__())
def count():
# array = load_data(array_path, "java")
# math = load_data(math_path, "java")
# search = load_data(search_path, "java")
sort = load_data(sort_path, "java")
# string = load_data(string_path, "java")
tree = load_data(tree_path, "java")
dp = load_data(dp_path, "java")
raw = load_data(raw_path, "java")
print(sort.__len__())
print(tree.__len__())
print(dp.__len__())
print(raw.__len__())
def init_tokenizer():
cpp_data = clc.load_data(data_path, "cpp")
tokenizer = Tokenizer(filters='!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\t\n', )
tokenizer.fit_on_texts(cpp_data)
# save
f = open('tokenizer_lcs_cpp.pkl', 'wb')
pickle.dump(tokenizer, f)
f.close()
def get_top_three_ast_sim(sim_list, xml_file):
list = []
for i in range(len(sim_list)):
path = sim_list[i][0]
xml_path = cfc.code_path2xml_path(path)
ans = ast_evaluator.tree_distance_similarities(xml_path, xml_file)
list.append(ans)
print(ans)
return list
def get_func_path(func, language):
return os.path.join(data_path_dict[language], func)
def predict_function(path, language):
return func_model[language].predict(path)
def creat_file(file_path, source_text):
f = open(file_path, 'w+', encoding='UTF-8')
f.write(source_text)
if __name__ == "__main__":
data_path = '../../data/leetcode/raw'
ret = clc.load_data(data_path, "java")
print(ret[54])
ret = recommend_code("")
print(ret)