Optimised runtime w BST

names/binary_search_tree.py

@@ -0,0 +1,37 @@
+class BinarySearchTree:
+    def __init__(self, value):
+        self.value = value
+        self.left = None
+        self.right = None
+        self.count = 1
+
+    # insert the given value into the tree
+    def insert(self, value):
+        if value < self.value:
+            if not self.left:
+                # if node does not exist, insert new node
+                self.left = BinarySearchTree(value)
+            else:
+                # if node exists, recurse
+                self.left.insert(value)
+        else:
+            # value is >= node
+            if not self.right:
+                self.right = BinarySearchTree(value)
+            else:
+                self.right.insert(value)
+
+    # Return True if the tree contains the value
+    # False if it does not
+    def contains(self, target):
+        # recursive solution
+        if target == self.value:
+            return True
+        elif target < self.value:
+            if self.left is None:
+                return False
+            return self.left.contains(target)
+        else:
+            if self.right is None:
+                return False
+            return self.right.contains(target)

names/names.py

@@ -1,27 +1,39 @@
 import time
-<<<<<<< HEAD
-# Will come back to this Sprint (AGAIN)
-=======
-# Will come back to this Sprint
->>>>>>> a4b13b5adcd64c3913edeba6bdeed7e5c67f7b11
+# Import Binary Search
+from binary_search_tree import BinarySearchTree
 
 start_time = time.time()
 
-f = open('names_1.txt', 'r')
+f = open('names/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/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
 
 # Replace the nested for loops below with your improvements
+'''
 for name_1 in names_1:
     for name_2 in names_2:
         if name_1 == name_2:
             duplicates.append(name_1)
+'''
+# Above takes roughly 7 secs - 0(n^2)
+
+# Starting in middle of alphabet
+bst = BinarySearchTree('N')
+
+for name in names_1:
+    bst.insert(name)
+
+for name in names_2:
+    if bst.contains(name):
+        duplicates.append(name)
+
+#BST method runtime: 0.1453089714050293 seconds - 0(n * log(n))
 
 end_time = time.time()
 print (f"{len(duplicates)} duplicates:\n\n{', '.join(duplicates)}\n\n")