First try with names.py

I am getting a little stumped on this one. I am pretty sure this is O(log n), but
the time complexity is 32 seconds. I tried to check the names as they were being inserted
to make it faster, but that fails because their is duplicates inside their own names file.
Need to keep thinking about it.

Author: Lnleite

names/names.py

@@ -1,5 +1,6 @@
 import time
 
+
 start_time = time.time()
 
 f = open('names_1.txt', 'r')
@@ -10,13 +11,75 @@
 names_2 = f.read().split("\n")  # List containing 10000 names
 f.close()
 
+# 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")
+
+
+class BinarySearchTree:
+    def __init__(self, value):
+        self.value = value
+        self.left = None
+        self.right = None
+        self.duplicates = []
+
+    def insert(self, value):
+        new_tree = BinarySearchTree(value)
+        if (value < self.value):
+            if not self.left:
+                self.left = new_tree
+            else:
+                self.left.insert(value)
+        elif value >= self.value:
+            if not self.right:
+                self.right = new_tree
+            else:
+                self.right.insert(value)
+
+    def contains(self, target):
+        if self.value == target:
+            return True
+        if self.left:
+            if self.left.contains(target):
+                return True
+        if self.right:
+            if self.right.contains(target):
+                return True
+        return False
+
+    def get_max(self):
+        if not self:
+            return None
+        max_value = self.value
+        current = self
+        while current:
+            if current.value > max_value:
+                max_value = current.value
+            current = current.right
+        return max_value
+
+
 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")
+firstName = names_1.pop(0)
+
+bst = BinarySearchTree(firstName)
+for name in names_1:
+    bst.insert(name)
+
+for name in names_2:
+    if bst.contains(name):
+        duplicates.append(name)
 
+
+print(bst.duplicates)
+
+end_time = time.time()
+print(f"{len(duplicates)} duplicates:\n\n{', '.join(duplicates)}\n\n")
+print(f"runtime: {end_time - start_time} seconds")