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
|
|
|
|
|
import numpy as np
|
|
|
|
|
|
|
|
|
|
ltable_path = 'E:\\Data\\Research\\Projects\\matching_dependency\\datasets\\Amazon.csv'
|
|
|
|
|
rtable_path = 'E:\\Data\\Research\\Projects\\matching_dependency\\datasets\\GoogleProducts.csv'
|
|
|
|
|
mapping_path = 'E:\\Data\\Research\\Projects\\matching_dependency\\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
|
|
|
|
|
support_threshold = 1
|
|
|
|
|
confidence_threshold = 0.8
|
|
|
|
|
interpre_weight = 0.3 # 可解释性权重
|
|
|
|
|
er_output_dir = 'E:\\Data\\Research\\Projects\\matching_dependency\\ml_er\\output\\'
|
|
|
|
|
md_output_dir = 'E:\\Data\\Research\\Projects\\matching_dependency\\md_discovery\\output\\'
|
|
|
|
|
model = SentenceTransformer('E:\\Data\\Research\\Models\\paraphrase-MiniLM-L6-v2')
|
|
|
|
|
embedding_dict = np.load('E:\\Data\\Research\\Projects\\matching_dependency\\md_discovery\\embedding_dic.npy',
|
|
|
|
|
allow_pickle=True).item()
|
