Entity Matching by Similarity Join
 
Loading...
Searching...
No Matches
test_block_all 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 = "test/tmp/rules_amazon_google_structured1.txt"
 
str path_range = "test/tmp/ranges_amazon_google_structured.txt"
 
str path_tree = "test/tmp/trees_amazon_google_structured.txt"
 
str path_rf = "test/tmp/rf_amazon_google_structured.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)
 
 attr_types_ltable = au.get_attr_types(tableA)
 
 attr_types_rtable = au.get_attr_types(tableB)
 
 sample_strategy
 
 blocking_attr
 
 cluster_tau
 
 sample_tau
 
 step2_tau
 
 num_data
 
 random_forest
 
 trigraph
 
 model_path
 
 tree_path
 
 range_path
 
 num_tree
 
 sample_size
 
 ground_truth_label
 
 True
 
 training_strategy
 
 inmemory
 
 at_ltable
 
 at_rtable
 
 rule_path
 
 move_strategy
 
 additional_rule_path
 
 None
 
 optimal_rule_path
 
 blocking_attr_type
 
 blocking_top_k
 
 table_size
 
 is_join_topk
 
 is_idf_weighted
 

Variable Documentation

◆ additional_rule_path

test_block_all.additional_rule_path

◆ at_ltable

test_block_all.at_ltable

◆ at_rtable

test_block_all.at_rtable

◆ attr_types_ltable

test_block_all.attr_types_ltable = au.get_attr_types(tableA)

◆ attr_types_rtable

test_block_all.attr_types_rtable = au.get_attr_types(tableB)

◆ blocking_attr

test_block_all.blocking_attr

◆ blocking_attr_type

test_block_all.blocking_attr_type

◆ blocking_top_k

test_block_all.blocking_top_k

◆ cluster_tau

test_block_all.cluster_tau

◆ dir_path

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

◆ file

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

◆ gold

test_block_all.gold = read_csv_golds(path_gold, gold_graph)

◆ gold_graph

test_block_all.gold_graph = nx.Graph()

◆ ground_truth_label

test_block_all.ground_truth_label

◆ inmemory

test_block_all.inmemory

◆ is_idf_weighted

test_block_all.is_idf_weighted

◆ is_join_topk

test_block_all.is_join_topk

◆ model_path

test_block_all.model_path

◆ move_strategy

test_block_all.move_strategy

◆ None

test_block_all.None

◆ num_data

test_block_all.num_data

◆ num_tree

test_block_all.num_tree

◆ optimal_rule_path

test_block_all.optimal_rule_path

◆ parent

test_block_all.parent

◆ path_gold

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

◆ path_range

str test_block_all.path_range = "test/tmp/ranges_amazon_google_structured.txt"

◆ path_rf

test_block_all.path_rf = "test/tmp/rf_amazon_google_structured.joblib"

◆ path_rule

test_block_all.path_rule = "test/tmp/rules_amazon_google_structured1.txt"

◆ path_tableA

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

◆ path_tableB

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

◆ path_tree

test_block_all.path_tree = "test/tmp/trees_amazon_google_structured.txt"

◆ random_forest

test_block_all.random_forest

◆ range_path

test_block_all.range_path

◆ root

test_block_all.root

◆ rule_path

test_block_all.rule_path

◆ sample_size

test_block_all.sample_size

◆ sample_strategy

test_block_all.sample_strategy

◆ sample_tau

test_block_all.sample_tau

◆ step2_tau

test_block_all.step2_tau

◆ table_size

test_block_all.table_size

◆ tableA

test_block_all.tableA = read_csv_table(path_tableA)

◆ tableB

test_block_all.tableB = read_csv_table(path_tableB)

◆ training_strategy

test_block_all.training_strategy

◆ tree_path

test_block_all.tree_path

◆ trigraph

test_block_all.trigraph

◆ True

test_block_all.True