get_true_pos Namespace Reference

Variables
	gold = pd.read_csv("output/buffer/gold.csv")
	ground_truth = set()
	lid = int(row["id1"])
	rid = int(row["id2"])
	match_res = pd.read_csv("output/match_res/match_res.csv")
	true_positive = pd.DataFrame(columns=match_res.columns)
	false_negative = pd.DataFrame(columns=["_id", "ltable_id", "rtable_id", "ltable_title", "rtable_title"])
	tableA = pd.read_csv("output/buffer/clean_A.csv")
	tableB = pd.read_csv("output/buffer/clean_B.csv")
dict	map_A = {tableA.loc[ridx, "id"] : ridx for ridx in list(tableA.index)}
dict	map_B = {tableB.loc[ridx, "id"] : ridx for ridx in list(tableB.index)}
dict	lridx = map_A[tup[0]]
dict	rridx = map_B[tup[1]]
list	addlist = [idx, tup[0], tup[1], tableA.loc[lridx, "title"], tableB.loc[rridx, "title"]]
	index

Variable Documentation

addlist

list get_true_pos.addlist = [idx, tup[0], tup[1], tableA.loc[lridx, "title"], tableB.loc[rridx, "title"]]

false_negative

get_true_pos.false_negative = pd.DataFrame(columns=["_id", "ltable_id", "rtable_id", "ltable_title", "rtable_title"])

gold

get_true_pos.gold = pd.read_csv("output/buffer/gold.csv")

ground_truth

get_true_pos.ground_truth = set()

index

get_true_pos.index

lid

get_true_pos.lid = int(row["id1"])

lridx

dict get_true_pos.lridx = map_A[tup[0]]

map_A

dict get_true_pos.map_A = {tableA.loc[ridx, "id"] : ridx for ridx in list(tableA.index)}

map_B

dict get_true_pos.map_B = {tableB.loc[ridx, "id"] : ridx for ridx in list(tableB.index)}

match_res

get_true_pos.match_res = pd.read_csv("output/match_res/match_res.csv")

rid

get_true_pos.rid = int(row["id2"])

rridx

dict get_true_pos.rridx = map_B[tup[1]]

tableA

get_true_pos.tableA = pd.read_csv("output/buffer/clean_A.csv")

tableB

get_true_pos.tableB = pd.read_csv("output/buffer/clean_B.csv")

true_positive

get_true_pos.true_positive = pd.DataFrame(columns=match_res.columns)