test_block.py File Reference

Namespaces
namespace	test_block

Variables
	test_block.file = Path(__file__).resolve()
	test_block.parent
	test_block.root
str	test_block.dir_path = "../datasets/tables/megallen/amazon-google-structured"
str	test_block.path_tableA = "/".join([dir_path, "table_a.csv"])
str	test_block.path_tableB = "/".join([dir_path, "table_b.csv"])
str	test_block.path_gold = "/".join([dir_path, "gold.csv"])
str	test_block.path_rule = "simjoin_entitymatching/blocker/rules/rules_amazon_google_structured1.txt"
	test_block.gold_graph = nx.Graph()
	test_block.tableA = read_csv_table(path_tableA)
	test_block.tableB = read_csv_table(path_tableB)
	test_block.gold = read_csv_golds(path_gold, gold_graph)
	test_block.sample_res = Path("output/buffer/sample_res.csv")
	test_block.sample_abs_path = sample_res.resolve(strict=True)
	test_block.sample_strategy
	test_block.blocking_attr
	test_block.cluster_tau
	test_block.sample_tau
	test_block.step2_tau
	test_block.num_data
	test_block.sample_tab = pd.read_csv(sample_abs_path)
str	test_block.id1 = str(sample_tab.loc[index, 'ltable_id']) + 'A'
str	test_block.id2 = str(sample_tab.loc[index, 'rtable_id']) + 'B'
	test_block.index
	test_block.blocking_attr_type
	test_block.blocking_top_k
	test_block.table_size
	test_block.is_join_topk
	test_block.is_idf_weighted