test_block Namespace Reference

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

Variable Documentation

blocking_attr

test_block.blocking_attr

blocking_attr_type

test_block.blocking_attr_type

blocking_top_k

test_block.blocking_top_k

cluster_tau

test_block.cluster_tau

dir_path

str test_block.dir_path = "../datasets/tables/megallen/amazon-google-structured"

file

test_block.file = Path(__file__).resolve()

gold

test_block.gold = read_csv_golds(path_gold, gold_graph)

gold_graph

test_block.gold_graph = nx.Graph()

id1

str test_block.id1 = str(sample_tab.loc[index, 'ltable_id']) + 'A'

id2

str test_block.id2 = str(sample_tab.loc[index, 'rtable_id']) + 'B'

index

test_block.index

is_idf_weighted

test_block.is_idf_weighted

is_join_topk

test_block.is_join_topk

num_data

test_block.num_data

parent

test_block.parent

path_gold

test_block.path_gold = "/".join([dir_path, "gold.csv"])

path_rule

test_block.path_rule = "simjoin_entitymatching/blocker/rules/rules_amazon_google_structured1.txt"

path_tableA

test_block.path_tableA = "/".join([dir_path, "table_a.csv"])

path_tableB

test_block.path_tableB = "/".join([dir_path, "table_b.csv"])

root

test_block.root

sample_abs_path

test_block.sample_abs_path = sample_res.resolve(strict=True)

sample_res

test_block.sample_res = Path("output/buffer/sample_res.csv")

sample_strategy

test_block.sample_strategy

sample_tab

test_block.sample_tab = pd.read_csv(sample_abs_path)

sample_tau

test_block.sample_tau

step2_tau

test_block.step2_tau

table_size

test_block.table_size

tableA

test_block.tableA = read_csv_table(path_tableA)

tableB

test_block.tableB = read_csv_table(path_tableB)