from sentence_transformers import SentenceTransformer

ltable_path = r'E:\Data\Research\Projects\matching_dependency_pyJedAI\datasets\JedAI\ccer\D2\abt.csv'
rtable_path = r'E:\Data\Research\Projects\matching_dependency_pyJedAI\datasets\JedAI\ccer\D2\buy.csv'
mapping_path = r'E:\Data\Research\Projects\matching_dependency_pyJedAI\datasets\JedAI\ccer\D2\gt.csv'
mapping_lid = 'D1'  # mapping表中左表id名
mapping_rid = 'D2'  # 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 = {}  # 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\\roberta-large-nli-stsb-mean-tokens')
interpre_weight = 0.5  # 可解释性权重
similarity_threshold = 0.1
support_threshold = 1
confidence_threshold = 0.25

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