from sentence_transformers import SentenceTransformer

ltable_path = r'E:\Data\Research\Projects\md_bayesian_er_magellan\datasets\Abt-Buy\tableA.csv'
rtable_path = r'E:\Data\Research\Projects\md_bayesian_er_magellan\datasets\Abt-Buy\tableB.csv'
mapping_path = r'E:\Data\Research\Projects\md_bayesian_er_magellan\datasets\Abt-Buy\matches.csv'
mapping_lid = 'idAbt'  # mapping表中左表id名
mapping_rid = 'idBuy'  # mapping表中右表id名
ltable_block_attr = 'name'
rtable_block_attr = 'name'
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 = {}  # 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

model = SentenceTransformer('E:\\Data\\Research\\Models\\all-MiniLM-L6-v2')
interpre_weight = 0  # 可解释性权重
similarity_threshold = 0.1
support_threshold = 1
confidence_threshold = 0.75

er_output_dir = 'E:\\Data\\Research\\Projects\\md_bayesian_er_magellan\\ml_er\\output\\'
md_output_dir = 'E:\\Data\\Research\\Projects\\md_bayesian_er_magellan\\md_discovery\\output\\'
hpo_output_dir = 'E:\\Data\\Research\\Projects\\md_bayesian_er_magellan\\hpo\\output\\'