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.
|
|
|
|
from sentence_transformers import SentenceTransformer
|
|
|
|
|
|
|
|
|
|
ltable_path = r'E:\Data\Research\Projects\matching_dependency\datasets\Walmart-Amazon_dirty\tableA.csv'
|
|
|
|
|
rtable_path = r'E:\Data\Research\Projects\matching_dependency\datasets\Walmart-Amazon_dirty\tableB.csv'
|
|
|
|
|
mapping_path = r'E:\Data\Research\Projects\matching_dependency\datasets\Walmart-Amazon_dirty\matches.csv'
|
|
|
|
|
mapping_lid = 'ltable_id' # mapping表中左表id名
|
|
|
|
|
mapping_rid = 'rtable_id' # 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 = 1 # 可解释性权重
|
|
|
|
|
similarity_threshold = 0.1
|
|
|
|
|
support_threshold = 1
|
|
|
|
|
confidence_threshold = 0.25
|
|
|
|
|
|
|
|
|
|
er_output_dir = 'E:\\Data\\Research\\Projects\\matching_dependency\\ml_er\\output\\'
|
|
|
|
|
md_output_dir = 'E:\\Data\\Research\\Projects\\matching_dependency\\md_discovery\\output\\'
|
|
|
|
|
hpo_output_dir = 'E:\\Data\\Research\\Projects\\matching_dependency\\hpo\\output\\'
|
|
|
|
|
|
