Refactor benchmark to use randomized vectors instead of sets

- Replaced std::set with std::vector for sequence handling.
- Added randomization of sequences to avoid ordered input bias.
- Removed unused balance function and related code in bst.cpp and bst.h.
- Fixed bugs in list insertion and search logic.
- Updated plot.py to allow custom y-axis labels and enable log scale for build plots.

Lab2/benchmark.cpp

@@ -2,6 +2,7 @@
 #include "bst/bst.h"
 #include "list/list.h"
 
+#include <algorithm>
 #include <chrono>
 #include <cstdio>
 #include <iostream>
@@ -9,7 +10,7 @@
 #include <random>
 #include <set>
 
-void measureList(std::set<int> *sequence, FILE *file) {
+void measureList(std::vector<int> *sequence, FILE *file) {
   float buildTime = 0, searchTime = 0, deleteTime = 0;
 
   for (int i = 0; i < 10; i++) {
@@ -55,7 +56,7 @@ void measureList(std::set<int> *sequence, FILE *file) {
   fprintf(file, "List,%f,%f,%f\n", buildTime, searchTime, deleteTime);
 }
 
-void measureBST(std::set<int> *sequence, FILE *file) {
+void measureBST(std::vector<int> *sequence, FILE *file) {
   float buildTime = 0, searchTime = 0, deleteTime = 0;
 
   for (int i = 0; i < 10; i++) {
@@ -68,7 +69,7 @@ void measureBST(std::set<int> *sequence, FILE *file) {
     for (int value : *sequence) {
       root = insert(root, value);
     }
-    root = balance(root);
+    // root = balance(root);
     auto end = std::chrono::high_resolution_clock::now();
     std::chrono::duration<double> elapsed_seconds = end - start;
     buildTime += elapsed_seconds.count() * 1000; // Convert to milliseconds
@@ -100,7 +101,7 @@ void measureBST(std::set<int> *sequence, FILE *file) {
   fprintf(file, "BST,%f,%f,%f\n", buildTime, searchTime, deleteTime);
 }
 
-void benchmarkAVL(std::set<int> *sequence, FILE *file) {
+void benchmarkAVL(std::vector<int> *sequence, FILE *file) {
   Tree *bst = nullptr;
   for (int value : *sequence) {
     bst = insert(bst, value);
@@ -147,19 +148,28 @@ int main() {
   }
 
   for (int n = 1; n < 26; n++) {
+    // Using a set here ensures that there are no duplicates
     std::set<int> sequence;
     while (sequence.size() < n * 1000) {
       sequence.insert(dis(gen));
     }
 
-    // Display this like a cascade
+    std::vector<int> random_sequence_vec;
+    for (int val : sequence) {
+        random_sequence_vec.push_back(val);
+    }
+
+    // Then randomize the sequence so the bst isn't a list (Set keeps the elements in order)
+    std::shuffle(random_sequence_vec.begin(), random_sequence_vec.end(), gen);
+
+    // Display the times like a cascade
     std::cout << "Running tests for " << n * 1000 << " elements..."
               << std::endl;
     if (mode == 1) {
-      measureList(&sequence, file);
-      measureBST(&sequence, file);
+      measureList(&random_sequence_vec, file);
+      measureBST(&random_sequence_vec, file);
     } else {
-      benchmarkAVL(&sequence, file);
+      benchmarkAVL(&random_sequence_vec, file);
     }
   }
 

Lab2/bst/bst.cpp

@@ -24,33 +24,6 @@ Tree *search(Tree *root, int value) {
   return nullptr;
 }
 
-void traverseInOrder(Tree *root, std::vector<int> *vec) {
-  if (root != nullptr) {
-    traverseInOrder(root->left, vec);
-    vec->push_back(root->info);
-    traverseInOrder(root->right, vec);
-  }
-}
-
-Tree *rebuild(std::vector<int> *vec, int start, int end) {
-  if (start > end)
-    return nullptr;
-
-  int mid = (start + end) / 2;
-  Tree *node = new Tree();
-  node->info = vec->at(mid);
-  node->left = rebuild(vec, start, mid - 1);
-  node->right = rebuild(vec, mid + 1, end);
-
-  return node;
-}
-
-Tree *balance(Tree *root) {
-  std::vector<int> vec;
-  traverseInOrder(root, &vec);
-  return rebuild(&vec, 0, vec.size() - 1);
-}
-
 void deleteTree(Tree *root) {
   if (root != nullptr) {
     deleteTree(root->left);
@@ -60,7 +33,8 @@ void deleteTree(Tree *root) {
 }
 
 int getHeight(Tree *root, int height) {
-  if (root == nullptr) return height;
+  if (root == nullptr)
+    return height;
   height += 1;
   int leftHeight = getHeight(root->left, height);
   int rightHeight = getHeight(root->right, height);

Lab2/bst/bst.h

@@ -8,8 +8,5 @@ struct Tree {
 
 Tree *insert(Tree *root, int value);
 Tree *search(Tree *root, int value);
-void traverseInOrder(Tree *root,std::vector<int> &vec);
-Tree *rebuild(std::vector<int> *vec, int start, int end);
-Tree *balance(Tree *root);
 void deleteTree(Tree *root);
 int getHeight(Tree *root, int height);

Lab2/list/list.cpp

@@ -16,9 +16,10 @@ List *insert(List *head, int value) {
     head = newHead;
   } else {
     List *tmp = head;
-    while (tmp->next != nullptr && tmp->data < value) {
-        tmp = tmp->next;
+    while (tmp->next != nullptr && tmp->next->data < value) {
+      tmp = tmp->next;
     }
+
     List *tail = new List();
     tail->data = value;
     // Set the pointer to the next, we don't know if its at the end or not
@@ -32,24 +33,19 @@ List *insert(List *head, int value) {
 List *search(List *list, int value) {
   List *ptr = list;
   while (ptr != nullptr && ptr->data != value) {
-      ptr = ptr->next;
+    if (ptr->data > value) return nullptr;
+    ptr = ptr->next;
   }
 
-  if (ptr->data == value) {
-    return ptr;
-  }
-
-  return nullptr;
+  return ptr;
 }
 
-
-
 // Remove the first element
 List *remove(List *head) {
-    if (head == nullptr) {
-        return nullptr;
-    }
-    List *newHead = head->next;
-    delete head;
-    return newHead;
+  if (head == nullptr) {
+    return nullptr;
+  }
+  List *newHead = head->next;
+  delete head;
+  return newHead;
 }

Lab2/plot.py

@@ -1,11 +1,11 @@
 import matplotlib.pyplot as plt
 
-def plot(header:str, first:list[int], second:list[int], log=False, labels=("Lista", "Drzewo BST")):
+def plot(header:str, first:list[int], second:list[int], log=False, labels=("Lista", "Drzewo BST"), ylabel= "Czas (ms)"):
     plt.figure(figsize=(10, 6))
     plt.plot(range(1000,25001,1000), first, label=labels[0])
     plt.plot(range(1000,25001,1000), second, label=labels[1])
     plt.xlabel("Rozmiar tablicy")
-    plt.ylabel("Czas (ms)")
+    plt.ylabel(ylabel)
     if log:
         plt.yscale('log', base=2)
     plt.title(header)
@@ -42,7 +42,7 @@ if __name__ == "__main__":
                 listTimes['delete'].append(float(row[3]))
 
 
-        plot("Tworzenie", listTimes['build'], bstTimes['build'])
+        plot("Tworzenie", listTimes['build'], bstTimes['build'], log=True)
         plot("Wyszukiwanie", listTimes['search'], bstTimes['search'], log=True)
         plot("Usuwanie", listTimes['delete'], bstTimes['delete'])
 
@@ -55,4 +55,4 @@ if __name__ == "__main__":
         bstHeights = [int(x[0]) for x in values]
         avlHeights = [int(x[1]) for x in values]
 
-        plot("AVl", bstHeights, avlHeights, log=True, labels=("Drzewo BST", "Drzewo AVL"))
+        plot("AVL", bstHeights, avlHeights, log=True, labels=("Drzewo BST", "Drzewo AVL"), ylabel="Wysokość drzewa")