name with sprint

names/names.py

@@ -1,25 +1,75 @@
 import time
+from collections import Counter
+
+
+class BinarySearchTree:
+    def __init__(self, value):
+        self.value = value
+        self.left = None
+        self.right = None
+
+    def insert(self, value):
+        if self.value == None:
+            self.value == value
+        elif value < self.value:
+            if self.left == None:
+                self.left = BinarySearchTree(value)
+            else:
+                self.left.insert(value)
+        else:
+            if self.right == None:
+                self.right = BinarySearchTree(value)
+            else:
+                self.right.insert(value)
+
+    def contains(self, target):
+        if self.value == target:
+            return True
+        elif target < self.value:
+            if self.left != None:
+                return self.left.contains(target)
+            else:
+                return False
+        else:
+            if self.right != None:
+                return self.right.contains(target)
+            else:
+                return False
+
+    def get_max(self):
+        if self.right == None:
+            return self.value
+        else:
+            return self.right.get_max()
+
+    def for_each(self, cb):
+        cb(self.value)
+        if self.left != None:
+            self.left.for_each(cb)
+        if self.right != None:
+            self.right.for_each(cb)
+
 
 # original solution
-# start_time = time.time()
+start_time = time.time()
 
-# f = open('names_1.txt', 'r')
-# names_1 = f.read().split("\n")  # List containing 10000 names
-# f.close()
+f = open('names_1.txt', 'r')
+names_1 = f.read().split("\n")  # List containing 10000 names
+f.close()
 
-# f = open('names_2.txt', 'r')
-# names_2 = f.read().split("\n")  # List containing 10000 names
-# f.close()
+f = open('names_2.txt', 'r')
+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)
+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")
+end_time = time.time()
+print(f"{len(duplicates)} duplicates:\n\n{', '.join(duplicates)}\n\n")
+print(f"runtime: {end_time - start_time} seconds")
 
 # first pass solution
 start_time = time.time()
@@ -43,7 +93,88 @@
         counts[elem] = 1
         continue
     counts[elem] += 1
-duplicates = [k for k, v in counts.items() if v > 1]
+duplicates = [key for key, value in counts.items() if value > 1]
+
+end_time = time.time()
+print(f"{len(duplicates)} duplicates:\n\n{', '.join(duplicates)}\n\n")
+print(f"runtime: {end_time - start_time} seconds")
+
+
+# second pass solution with BST
+start_time = time.time()
+
+f = open('names_1.txt', 'r')
+names_1 = f.read().split("\n")  # List containing 10000 names
+f.close()
+
+f = open('names_2.txt', 'r')
+names_2 = f.read().split("\n")  # List containing 10000 names
+f.close()
+
+bts_names_2 = BinarySearchTree(names_2[0])
+
+for name_1 in names_2[1:]:
+    bts_names_2.insert(name_1)
+
+duplicates = []
+
+for name_1 in names_1:
+    if bts_names_2.contains(name_1):
+        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")
+
+# stretch
+start_time = time.time()
+
+f = open('names_1.txt', 'r')
+names_1 = f.read().split("\n")  # List containing 10000 names
+f.close()
+
+f = open('names_2.txt', 'r')
+names_2 = f.read().split("\n")  # List containing 10000 names
+f.close()
+
+names_2.sort()
+
+
+def sub(arr, x):
+    L = 0
+    R = len(arr)
+    m = -1
+    while L < R:
+        m = (L+R)//2
+        if x <= arr[m]:
+            R = m
+        else:
+            L = m + 1
+    return arr[L] == x
+
+
+duplicates = []
+
+for elem in names_1:
+    if sub(names_2, elem):
+        duplicates.append(elem)
+
+end_time = time.time()
+print(f"{len(duplicates)} duplicates:\n\n{', '.join(duplicates)}\n\n")
+print(f"runtime: {end_time - start_time} seconds")
+
+# stretch 2
+start_time = time.time()
+
+f = open('names_1.txt', 'r')
+names_1 = f.read().split("\n")  # List containing 10000 names
+f.close()
+
+f = open('names_2.txt', 'r')
+names_2 = f.read().split("\n")  # List containing 10000 names
+f.close()
+
+duplicates = list((Counter(names_1) & Counter(names_2)))
 
 end_time = time.time()
 print(f"{len(duplicates)} duplicates:\n\n{', '.join(duplicates)}\n\n")