(type, values_of_this_column, lsh_result, folder_path, model)
| 266 | |
| 267 | |
| 268 | def cal_precise_unionablity(type, values_of_this_column, lsh_result, folder_path, model): |
| 269 | #计算values_of_this_column与候选列的精确可并行分数 |
| 270 | #后面加上u_NL的分数 |
| 271 | col_dict = {} |
| 272 | for r in lsh_result: |
| 273 | file_name, column_name = r.split(maxsplit=1) |
| 274 | file_path = os.path.join(folder_path, file_name) |
| 275 | df_query = pd.read_csv(file_path) |
| 276 | if type == 'Uset' or type == 'Usem': |
| 277 | unionablity = u_set_or_sem(type, values_of_this_column, df_query[column_name].to_list()) |
| 278 | else: |
| 279 | unionablity = u_nl(values_of_this_column, df_query[column_name], model) |
| 280 | if file_name in col_dict: |
| 281 | if unionablity > col_dict[file_name]: |
| 282 | col_dict[file_name] = unionablity |
| 283 | else: |
| 284 | col_dict[file_name] = unionablity |
| 285 | |
| 286 | return col_dict |
| 287 | |
| 288 | |
| 289 | #save_dict_to_json(u_set_distribution(u_set_Lsh()), 'result/uset_lsh.json') |
nothing calls this directly
no test coverage detected