vis_rf_path 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_structured_1.txt"
str	path_range = "simjoin_entitymatching/matcher/model/ranges/ranges_amazon_google_structured_1.txt"
str	path_tree = "simjoin_entitymatching/matcher/model/trees/trees_amazon_google_structured_1.txt"
str	path_rf = "simjoin_entitymatching/matcher/model/rf_amazon_google_structured_1.joblib"
	gold_graph = nx.Graph()
	tableA = read_csv_table(path_tableA)
	tableB = read_csv_table(path_tableB)
	gold = read_csv_golds(path_gold, gold_graph)
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)}
	attr_types_ltable = au.get_attr_types(tableA)
	attr_types_rtable = au.get_attr_types(tableB)
	rf = randf.RandomForest()
	graph
	at_ltable
	at_rtable
	wrtie_fea_names
	blk_res_cand
	H
	false_neg = pd.read_csv("test/debug/false_neg.csv")
	lid = int(row["ltable_id"])
	rid = int(row["rtable_id"])
	exclude_attrs

Variable Documentation

at_ltable

vis_rf_path.at_ltable

at_rtable

vis_rf_path.at_rtable

attr_types_ltable

vis_rf_path.attr_types_ltable = au.get_attr_types(tableA)

attr_types_rtable

vis_rf_path.attr_types_rtable = au.get_attr_types(tableB)

blk_res_cand

vis_rf_path.blk_res_cand

Initial value:

=  em.read_csv_metadata("test/debug/false_neg.csv", key="_id", 
                                    ltable=tableA, rtable=tableB, 
                                    fk_ltable="ltable_id", 
                                    fk_rtable="rtable_id")

dir_path

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

exclude_attrs

vis_rf_path.exclude_attrs

false_neg

vis_rf_path.false_neg = pd.read_csv("test/debug/false_neg.csv")

file

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

gold

vis_rf_path.gold = read_csv_golds(path_gold, gold_graph)

gold_graph

vis_rf_path.gold_graph = nx.Graph()

graph

vis_rf_path.graph

H

vis_rf_path.H

Initial value:

=  em.extract_feature_vecs(blk_res_cand, 
                            feature_table=rf.features, 
                            show_progress=False)

lid

vis_rf_path.lid = int(row["ltable_id"])

map_A

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

map_B

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

parent

vis_rf_path.parent

path_gold

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

path_range

str vis_rf_path.path_range = "simjoin_entitymatching/matcher/model/ranges/ranges_amazon_google_structured_1.txt"

path_rf

str vis_rf_path.path_rf = "simjoin_entitymatching/matcher/model/rf_amazon_google_structured_1.joblib"

path_rule

str vis_rf_path.path_rule = "simjoin_entitymatching/blocker/rules/rules_amazon_google_structured_1.txt"

path_tableA

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

path_tableB

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

path_tree

str vis_rf_path.path_tree = "simjoin_entitymatching/matcher/model/trees/trees_amazon_google_structured_1.txt"

rf

vis_rf_path.rf = randf.RandomForest()

rid

vis_rf_path.rid = int(row["rtable_id"])

root

vis_rf_path.root

tableA

vis_rf_path.tableA = read_csv_table(path_tableA)

tableB

vis_rf_path.tableB = read_csv_table(path_tableB)

wrtie_fea_names

vis_rf_path.wrtie_fea_names