|
|
import time
|
|
|
from md_discovery.functions.multi_process_infer_by_pairs import inference_from_record_pairs
|
|
|
from md_discovery.functions.multi_process_infer_by_pairs import get_mds_metadata
|
|
|
from settings import *
|
|
|
|
|
|
# # 若不输出support和confidence，使用以下两块代码
|
|
|
# # 将列表1写入本地，路径需自己修改
|
|
|
# md_path = '/home/w/A-New Folder/8.14/Paper Dataset/TP_md_list.txt'
|
|
|
# with open(md_path, 'w') as f:
|
|
|
# for _ in mds:
|
|
|
# f.write(str(_) + '\n')
|
|
|
#
|
|
|
# # 将列表2写入本地，路径需自己修改
|
|
|
# vio_path = '/home/w/A-New Folder/8.14/Paper Dataset/TP_vio_list.txt'
|
|
|
# with open(vio_path, 'w') as f:
|
|
|
# for _ in vio:
|
|
|
# f.write(str(_) + '\n')
|
|
|
|
|
|
|
|
|
def md_discover():
|
|
|
# 目前可以仿照这个main函数写
|
|
|
tp_single_tuple_path = "ml_er/output/tp_single_tuple.csv"
|
|
|
fn_single_tuple_path = "ml_er/output/fn_single_tuple.csv"
|
|
|
# 输入：csv文件路径，md左侧相似度阈值，md右侧目标字段
|
|
|
# 输出：2个md列表，列表1中md无violation,列表2中md有violation但confidence满足阈值(0.8)
|
|
|
# 例如此处输入参数要求md左侧相似度字段至少为0.7，右侧指向'id'字段
|
|
|
tp_mds, tp_vio = inference_from_record_pairs(tp_single_tuple_path, similarity_threshold, target_attr)
|
|
|
fn_mds, fn_vio = inference_from_record_pairs(fn_single_tuple_path, similarity_threshold, target_attr)
|
|
|
|
|
|
# 如果不需要输出support和confidence，去掉下面两行
|
|
|
tp_mds_meta = get_mds_metadata(tp_mds, tp_single_tuple_path, target_attr)
|
|
|
tp_vio_meta = get_mds_metadata(tp_vio, tp_single_tuple_path, target_attr)
|
|
|
|
|
|
fn_mds_meta = get_mds_metadata(fn_mds, fn_single_tuple_path, target_attr)
|
|
|
fn_vio_meta = get_mds_metadata(fn_vio, fn_single_tuple_path, target_attr)
|
|
|
|
|
|
# 若输出support和confidence，使用以下两块代码
|
|
|
# 将列表1写入本地，路径需自己修改
|
|
|
tp_mds_path = "md_discovery/output/tp_mds.txt"
|
|
|
tp_vio_path = "md_discovery/output/tp_vio.txt"
|
|
|
|
|
|
with open(tp_mds_path, 'w') as f:
|
|
|
for _ in tp_mds_meta:
|
|
|
for i in _.keys():
|
|
|
f.write(i + ':' + str(_[i]) + '\t')
|
|
|
f.write('\n')
|
|
|
|
|
|
with open(tp_vio_path, 'w') as f:
|
|
|
for _ in tp_vio_meta:
|
|
|
for i in _.keys():
|
|
|
f.write(i + ':' + str(_[i]) + '\t')
|
|
|
f.write('\n')
|
|
|
|
|
|
fn_mds_path = "md_discovery/output/fn_mds.txt"
|
|
|
fn_vio_path = "md_discovery/output/fn_vio.txt"
|
|
|
|
|
|
with open(fn_mds_path, 'w') as f:
|
|
|
for _ in fn_mds_meta:
|
|
|
for i in _.keys():
|
|
|
f.write(i + ':' + str(_[i]) + '\t')
|
|
|
f.write('\n')
|
|
|
|
|
|
with open(fn_vio_path, 'w') as f:
|
|
|
for _ in fn_vio_meta:
|
|
|
for i in _.keys():
|
|
|
f.write(i + ':' + str(_[i]) + '\t')
|
|
|
f.write('\n')
|
