Completed names.py + STRETCH

Author: exploratum

names/binary_search_tree.py

@@ -0,0 +1,44 @@
+class BinarySearchTree:
+  def __init__(self, value):
+    self.value = value
+    self.left = None
+    self.right = None
+
+
+  def insert(self, value):
+
+    if value == self.value:
+      return
+
+    if value < self.value:
+      if not self.left:
+        self.left = BinarySearchTree(value)
+      else:
+        self.left.insert(value)
+    
+    elif value > self.value:
+      if not self.right:
+        self.right = BinarySearchTree(value)
+      else:
+        self.right.insert(value)
+    
+
+
+
+  def contains(self, target):
+
+    if self.value == target:
+      return True
+
+    if target < self.value:
+
+      if self.left:
+        return self.left.contains(target)
+      else:
+        return False
+
+    else:
+      if self.right:
+        return self.right.contains(target)
+      else:
+        return False

names/names.py

@@ -1,4 +1,5 @@
 import time
+from binary_search_tree import BinarySearchTree
 
 start_time = time.time()
 
@@ -10,11 +11,38 @@
 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)
+###########################################################################
+# Binary Tree Search solution (insertion complexity: O(h(eight of tree)), 
+# comparison: n * O(h(eight of tree))
+###########################################################################
+
+# Setup binary tree and insert all names of names_1
+bst = BinarySearchTree(names_1[0])
+
+for i in range(1,len(names_1)):
+    bst.insert(names_1[i])
+
+# look up for duplicates
+duplicates=[]
+for name in names_2:
+    if bst.contains(name):
+        duplicates.append(name)
+
+#####################################
+# Original solution (runtime: 5.5 s.)
+# complexity: O(n**2)
+######################################
+# duplicates = []
+# for name_1 in names_1:
+#     for name_2 in names_2:
+#         if name_1 == name_2:
+#             duplicates.append(name_1)
+
+######## ############################## STRETCH ###################################
+# STRETCH - only Python lists - No extra storage for binary tree  (runtime: 1.11 s.)
+####################################################################################
+# 
+# duplicates = [name for name in names_1 if name in names_2]
 
 end_time = time.time()
 print (f"{len(duplicates)} duplicates:\n\n{', '.join(duplicates)}\n\n")