You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
|
|
|
|
|
# this is the entrance of the auto-ER procedure
|
|
|
|
|
|
from md_discovery.script.md_discover import md_discover
|
|
|
|
|
|
from ml_er.ml_entity_resolver import ml_er
|
|
|
|
|
|
from hpo.er_model_hpo import ml_er_hpo
|
|
|
|
|
|
from settings import *
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def run(rounds: int):
|
|
|
|
|
|
hp_config = None
|
|
|
|
|
|
# while The termination condition is not met
|
|
|
|
|
|
iter_round = 1
|
|
|
|
|
|
for i in range(0, rounds):
|
|
|
|
|
|
ml_er(iter_round, hp_config)
|
|
|
|
|
|
md_discover()
|
|
|
|
|
|
hp_config = ml_er_hpo()
|
|
|
|
|
|
iter_round += 1
|
|
|
|
|
|
ml_er(iter_round, hp_config)
|
|
|
|
|
|
return
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if __name__ == '__main__':
|
|
|
|
|
|
path = 'md_discovery/output'
|
|
|
|
|
|
# todo
|
|
|
|
|
|
# 距离度量用户可设置?
|
|
|
|
|
|
# 使用drop删除特征向量中的列？(如删除id相关特征)
|
|
|
|
|
|
run(1) # 迭代3轮
|
|
|
|
|
|
# ml_er(1)
|
|
|
|
|
|
# todo 将优化结果与参数输出到文件中
|
|
|
|
|
|
# 通过ml_entity_resolver.ml_er()输出,同时输出参数配置信息
|
|
|
|
|
|
print(ltable_path)
|
