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.
matching_dependency/settings.py

13 lines
633 B

ltable_path = 'datasets\\Amazon.csv'
rtable_path = 'datasets\\GoogleProducts.csv'
mapping_path = 'datasets\\Amzon_GoogleProducts_perfectMapping.csv'
mapping_lid = 'idAmazon' # mapping表中左表id名
mapping_rid = 'idGoogleBase' # mapping表中右表id名
ltable_id = 'id' # 左表id字段名称
rtable_id = 'id' # 右表id字段名称
target_attr = 'id' # 进行md挖掘时的目标字段
lr_attrs_map = {'title': 'name'} # 如果两个表中存在对应字段名称不一样的情况,将名称加入列表便于调整一致
similarity_threshold = 0.7
confidence_threshold = 0.8
interpre_weight = 0.3 # 可解释性权重