Add names binary search tree implementation

names/binary_search_tree.py

@@ -0,0 +1,53 @@
+class BinarySearchTree:
+    def __init__(self, value):
+        self.value = value
+        self.left = None
+        self.right = None
+
+    # Insert the given value into the tree
+    def insert(self, value):
+        parent = self
+        node = BinarySearchTree(value)
+        while True:
+            if value < parent.value:
+                if parent.left:
+                    parent = parent.left  # traverse down left
+                else:
+                    parent.left = node
+                    break
+            else:
+                if parent.right:
+                    parent = parent.right  # traverse down right
+                else:
+                    parent.right = node
+                    break
+
+    # Return True if the tree contains the value
+    # False if it does not
+    def contains(self, target):
+        node = self
+        while node.value != target:
+            if target < node.value and node.left:
+                node = node.left
+            elif target >= node.value and node.right:
+                node = node.right
+            else:
+                break
+        return node.value == target
+
+    # Return the maximum value found in the tree
+    def get_max(self):
+        node = self
+        while node.right:
+            node = node.right
+        return node.value
+
+    # Call the function `cb` on the value of each node
+    # You may use a recursive or iterative approach
+    def for_each(self, cb):
+        node = self
+        cb(node.value)
+        if node.left:
+            node.left.for_each(cb)
+        if node.right:
+            node.right.for_each(cb)

names/names.py

@@ -1,22 +1,34 @@
 import time
+from binary_search_tree import BinarySearchTree
 
 start_time = time.time()
 
-f = open('names_1.txt', 'r')
+f = open("names_1.txt", "r")
 names_1 = f.read().split("\n")  # List containing 10000 names
 f.close()
 
-f = open('names_2.txt', 'r')
+f = open("names_2.txt", "r")
 names_2 = f.read().split("\n")  # List containing 10000 names
 f.close()
 
+###########
+
+bst = BinarySearchTree(names_1[0])
+for name_1 in names_1[1:]:
+    bst.insert(name_1)
+
 duplicates = []
-for name_1 in names_1:
-    for name_2 in names_2:
-        if name_1 == name_2:
-            duplicates.append(name_1)
+for name_2 in names_2:
+    if bst.contains(name_2):
+        duplicates.append(name_2)
+
+# duplicates = []
+# for name_1 in names_1:
+#     for name_2 in names_2:
+#         if name_1 == name_2:
+#             duplicates.append(name_1)
 
 end_time = time.time()
-print (f"{len(duplicates)} duplicates:\n\n{', '.join(duplicates)}\n\n")
-print (f"runtime: {end_time - start_time} seconds")
+print(f"{len(duplicates)} duplicates:\n\n{', '.join(duplicates)}\n\n")
+print(f"runtime: {end_time - start_time} seconds")