def testContains(self):
# Set up tree
tree = BinarySearchTree()
tree.add('B')
tree.add('A')
tree.add('C')
# Try looking for an element which doesn't exist
self.assertFalse(tree.contains('D'))
# Try looking for an element which exists in the root
self.assertTrue(tree.contains('B'))
# Try looking for an element which exists as the left child of the root
self.assertTrue(tree.contains('A'))
# Try looking for an element which exists as the right child of the root
self.assertTrue(tree.contains('C'))
def randomRemoveTests(self):
for i in range(self.LOOPS):
size = i
tree = BinarySearchTree()
lst = self.genRandList(size)
for idx, value in enumerate(lst):
tree.add(value)
self.assertEqual(len(tree), idx + 1)
random.shuffle(lst)
for j in range(size):
value = lst[j]
self.assertTrue(tree.contains(value))
# Remove all the elements we just placed in the tree
for j in range(size):
value = lst[j]
tree.remove(value)
self.assertFalse(tree.contains(value))
self.assertEqual(len(tree), size - j - 1)
self.assertFalse(tree)
def randomRemoveTests(self):
for i in range(0, self.LOOPS):
sz = i
tree = BinarySearchTree()
lst = self.genRandList(sz)
for value in lst:
tree.add(value)
random.shuffle(lst)
# Remove all the elements we just placed in the tree
for j in range(0, sz):
value = lst[j]
self.assertTrue(tree.remove(value))
self.assertFalse(tree.contains(value))
self.assertEqual(tree.size(), sz - j - 1)
self.assertTrue(tree.isEmpty())
f = open('names_2.txt', 'r')
names_2 = f.read().split("\n") # List containing 10000 names
f.close()
duplicates = [] # Return the list of duplicates in this data structure
# grab the first name to start tree
bst = BinarySearchTree(names_1[0])
# insert the rest from first file into the tree
for name in names_1[1:]:
bst.insert(name)
for name in names_2:
if bst.contains(name):
duplicates.append(name)
end_time = time.time()
print(
f"*******MVP TIME******{len(duplicates)} duplicates:\n\n{', '.join(duplicates)}\n\n")
print(f"runtime: {end_time - start_time} seconds*******MVP TIME******")
# --------------BAD TIME-----------------
start_time = time.time()
# Replace the nested for loops below with your improvements
bad_duplicates = []
for name_1 in names_1:
for name_2 in names_2:
if name_1 == name_2:
f = open('names/names_1.txt', 'r')
names_1 = f.read().split("\n") # List containing 10000 names
f.close()
f = open('names/names_2.txt', 'r')
names_2 = f.read().split("\n") # List containing 10000 names
f.close()
duplicates = []
bst = BinarySearchTree(names_1[0])
for i in range(1, len(names_1)-1):
bst.insert(names_1[i])
for name in names_2:
if (bst.contains(name)):
duplicates.append(name)
end_time = time.time()
print (f"{len(duplicates)} duplicates:\n\n{', '.join(duplicates)}\n\n")
print (f"runtime: {end_time - start_time} seconds")
for name_1 in names_1:
# for name_2 in names_2:
# By commenting out this line, runtime went from 13 secs to 2 secs
# Original runtime of O(n^2) and I made it O(n).
if name_1 in names_2:
duplicates.append(name_1)
