test_sample 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"])
	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_strategy
	blocking_attr
	cluster_tau
	sample_tau
	step2_tau
	num_data
	ob = OverlapBlocker()
	C
int	cur_golds = 0
	row_index = list(C.index)
str	id1 = str(C.loc[index, 'ltable_id']) + 'A'
str	id2 = str(C.loc[index, 'rtable_id']) + 'B'
int	recall = cur_golds / len(gold) * 1.0
int	density = cur_golds / len(C) * 1.0

Variable Documentation

blocking_attr

test_sample.blocking_attr

C

test_sample.C

Initial value:

=  ob.block_tables(tableA, tableB, "title", "title", 
                    word_level=True, overlap_size=4, 
                    l_output_attrs=["id"], 
                    r_output_attrs=["id"], 
                    allow_missing=False,
                    show_progress=False)

cluster_tau

test_sample.cluster_tau

cur_golds

int test_sample.cur_golds = 0

density

int test_sample.density = cur_golds / len(C) * 1.0

dir_path

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

file

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

gold

test_sample.gold = read_csv_golds(path_gold, gold_graph)

gold_graph

test_sample.gold_graph = nx.Graph()

id1

str test_sample.id1 = str(C.loc[index, 'ltable_id']) + 'A'

id2

str test_sample.id2 = str(C.loc[index, 'rtable_id']) + 'B'

num_data

test_sample.num_data

ob

test_sample.ob = OverlapBlocker()

parent

test_sample.parent

path_gold

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

path_tableA

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

path_tableB

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

recall

int test_sample.recall = cur_golds / len(gold) * 1.0

root

test_sample.root

row_index

test_sample.row_index = list(C.index)

sample_strategy

test_sample.sample_strategy

sample_tau

test_sample.sample_tau

step2_tau

test_sample.step2_tau

tableA

test_sample.tableA = read_csv_table(path_tableA)

tableB

test_sample.tableB = read_csv_table(path_tableB)