Entity Matching by Similarity Join
 
Loading...
Searching...
No Matches
test_match.py File Reference

Namespaces

namespace  test_match
 

Variables

 test_match.file = Path(__file__).resolve()
 
 test_match.parent
 
 test_match.root
 
str test_match.dir_path = "../datasets/tables/megallen/amazon-google-structured"
 
str test_match.path_tableA = "/".join([dir_path, "table_a.csv"])
 
str test_match.path_tableB = "/".join([dir_path, "table_b.csv"])
 
str test_match.path_gold = "/".join([dir_path, "gold.csv"])
 
str test_match.path_rule = "test/tmp/rules_amazon_google_structured1.txt"
 
str test_match.path_range = "test/tmp/ranges_amazon_google_structured.txt"
 
str test_match.path_tree = "test/tmp/trees_amazon_google_structured.txt"
 
str test_match.path_rf = "test/tmp/rf_amazon_google_structured.joblib"
 
 test_match.gold_graph = nx.Graph()
 
 test_match.tableA = read_csv_table(path_tableA)
 
 test_match.tableB = read_csv_table(path_tableB)
 
 test_match.gold = read_csv_golds(path_gold, gold_graph)
 
list test_match.numeric_attr = ["price", "year"]
 
 test_match.schemas = list(tableA)[1:]
 
 test_match.attr_types_ltable = au.get_attr_types(tableA)
 
 test_match.attr_types_rtable = au.get_attr_types(tableB)
 
 test_match.random_forest
 
 test_match.trigraph
 
 test_match.blocking_attr
 
 test_match.model_path
 
 test_match.tree_path
 
 test_match.range_path
 
 test_match.num_tree
 
 test_match.sample_size
 
 test_match.ground_truth_label
 
 test_match.True
 
 test_match.training_strategy
 
 test_match.inmemory
 
 test_match.num_data
 
 test_match.at_ltable
 
 test_match.at_rtable
 
 test_match.is_interchangeable
 
 test_match.flag_consistent