修复了挖掘出重复md的bug；

修改列表遍历方式，避免可能出现的异常

deprecated/inference_from_record_pairs.py

@@ -3,7 +3,6 @@ import time
 import Levenshtein
 import copy
 
-
 def my_Levenshtein_ratio(str1, str2):
     return 1 - Levenshtein.distance(str1, str2) / max(len(str1), len(str2))
 
@@ -131,21 +130,21 @@ def inference_from_record_pairs(path, threshold, target_col):
 
 if __name__ == '__main__':
     # 目前可以仿照这个main函数写
-    path = "/home/w/PycharmProjects/py_entitymatching/py_entitymatching/datasets/end-to-end/DBLP-ACM/output/7.6/TP_single_tuple.csv"
+    path = "input/T_positive_with_id_concat_single_tuple.csv"
     start = time.time()
     # 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
-    mds, mds_vio = inference_from_record_pairs(path, 0.7, 'id')
+    mds, mds_vio = inference_from_record_pairs(path, 0.7, 'id_concat')
 
     # 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'
+    md_path = 'output/md.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'
+    vio_path = 'output/vio.txt'
     with open(vio_path, 'w') as f:
         for _ in mds_vio:
             f.write(str(_) + '\n')

script/get_support_and_confidence.py

@@ -1,19 +1,19 @@
 import time
-from multi_process_infer_by_pairs import inference_from_record_pairs
+from functions.multi_process_infer_by_pairs import inference_from_record_pairs
-from multi_process_infer_by_pairs import get_mds_metadata
+from functions.multi_process_infer_by_pairs import get_mds_metadata
 
 if __name__ == '__main__':
     # 目前可以仿照这个main函数写
-    path = "/home/w/PycharmProjects/py_entitymatching/py_entitymatching/datasets/end-to-end/Amazon-GoogleProducts/output/8.14/TP_single_tuple.csv"
+    path = "/home/w/PycharmProjects/matching_dependency/input/T_positive_with_id_concat_single_tuple.csv"
     start = time.time()
     # 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
-    mds, mds_vio = inference_from_record_pairs(path, 0.7, 'id')
+    mds, mds_vio = inference_from_record_pairs(path, 0.1, 'id_concat')
 
     # 如果不需要输出support和confidence，去掉下面两行
-    mds_meta = get_mds_metadata(mds, path, 'id')
+    mds_meta = get_mds_metadata(mds, path, 'id_concat')
-    mds_vio_meta = get_mds_metadata(mds_vio, path, 'id')
+    mds_vio_meta = get_mds_metadata(mds_vio, path, 'id_concat')
 
     # # 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
@@ -30,7 +30,7 @@ if __name__ == '__main__':
 
     # 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
-    md_path = '/home/w/A-New Folder/8.14/Goods Dataset/TP_md_list.txt'
+    md_path = "output/md.txt"
     with open(md_path, 'w') as f:
         for _ in mds_meta:
             for i in _.keys():
@@ -38,11 +38,11 @@ if __name__ == '__main__':
             f.write('\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/Goods Dataset/TP_vio_list.txt'
+    vio_path = "output/vio.txt"
     with open(vio_path, 'w') as f:
         for _ in mds_vio_meta:
             for i in _.keys():
                 f.write(i + ':' + str(_[i]) + '\t')
             f.write('\n')
 
-    print(time.time() - start)
+    print(time.time() - start)