test_sample.py File Reference

Namespaces
namespace	test_sample

Variables
	test_sample.file = Path(__file__).resolve()
	test_sample.parent
	test_sample.root
str	test_sample.dir_path = "../datasets/tables/megallen/amazon-google-structured"
str	test_sample.path_tableA = "/".join([dir_path, "table_a.csv"])
str	test_sample.path_tableB = "/".join([dir_path, "table_b.csv"])
str	test_sample.path_gold = "/".join([dir_path, "gold.csv"])
	test_sample.gold_graph = nx.Graph()
	test_sample.tableA = read_csv_table(path_tableA)
	test_sample.tableB = read_csv_table(path_tableB)
	test_sample.gold = read_csv_golds(path_gold, gold_graph)
	test_sample.sample_strategy
	test_sample.blocking_attr
	test_sample.cluster_tau
	test_sample.sample_tau
	test_sample.step2_tau
	test_sample.num_data
	test_sample.ob = OverlapBlocker()
	test_sample.C
int	test_sample.cur_golds = 0
	test_sample.row_index = list(C.index)
str	test_sample.id1 = str(C.loc[index, 'ltable_id']) + 'A'
str	test_sample.id2 = str(C.loc[index, 'rtable_id']) + 'B'
int	test_sample.recall = cur_golds / len(gold) * 1.0
int	test_sample.density = cur_golds / len(C) * 1.0