def test_bktree():
test_passed = True
test_database = pickle.load( open( 'testdatabase.p', 'rb' ) )
test_database = test_database['bktree']
keys = test_database['keys']
result_target = test_database['result']
query = test_database['query']
BKT = BKTree(levenshtein_distance_DP)
for key in keys:
BKT.insert(key)
result = BKT.get(query)
for (word,distance) in result:
encounter = 0
for (word_target,distance_target) in result_target:
if word == word_target:
if not distance == distance_target:
test_passed = False
encounter +=1
if not encounter == 1:
test_passed = False
return test_passed
dataset = Dataset(csv_file, query_processor)
dataset.load()
print("Dataset Loaded!")
#process it into an efficient binary search tree
print("Constructing RB-Tree...", end='', flush=True)
binary_search_tree = RedBlackTree()
temp_dataset = dataset.get_token_bookids()
for i in range(len(temp_dataset)):
binary_search_tree.insert(temp_dataset[i][0], temp_dataset[i][1])
print("RB-Tree constructed!")
#create a BK-tree
print("Constructing BK-Tree...", end='', flush=True)
bk_tree = BKTree(levenshtein_distance_DP)
english_dictionary_list = dataset.get_dictionary()
for i in range(len(english_dictionary_list)):
bk_tree.insert(english_dictionary_list[i])
print("BK-Tree constructed!")
if CONSTRUCT_DEBUG_MODE:
pickle.dump(dataset, open("dataset.p", 'wb'))
pickle.dump(binary_search_tree, open("binary_search_tree.p", 'wb'))
pickle.dump(bk_tree, open("bk_tree.p", 'wb'))
#create a Ranker
ranker = Ranker(dataset, query_processor, binary_search_tree, bk_tree)
#Get the book-titles for “The search engine.”
ranker.evaluate("The search engine.")
