SimonovaMS/analysis_report.txt

@@ -0,0 +1,50 @@
+['Structura', 'shuffled/sorted', 'Operation', 'Time']
+LinkedList | shuffled | insert | 3.798362
+LinkedList | shuffled | find | 0.028610
+LinkedList | shuffled | delete | 0.035444
+LinkedList | sorted | insert | 3.117239
+LinkedList | sorted | find | 0.020465
+LinkedList | sorted | delete | 0.028734
+HashTable | shuffled | insert | 0.013259
+HashTable | shuffled | find | 0.000109
+HashTable | shuffled | delete | 0.000079
+HashTable | sorted | insert | 0.014760
+HashTable | sorted | find | 0.000107
+HashTable | sorted | delete | 0.000076
+Bst | shuffled | insert | 0.020712
+Bst | shuffled | find | 0.000246
+Bst | shuffled | delete | 0.000096
+Bst | sorted | insert | 3.905296
+Bst | sorted | find | 0.029092
+Bst | sorted | delete | 0.018350
+
+Результаты:
+Структура       Режим      вставка         поиск           удаление       
+LinkedList      shuffled   3.798362        0.028610        0.035444       
+LinkedList      sorted     3.117239        0.020465        0.028734       
+HashTable       shuffled   0.013259        0.000109        0.000079       
+HashTable       sorted     0.014760        0.000107        0.000076       
+Bst             shuffled   0.020712        0.000246        0.000096       
+Bst             sorted     3.905296        0.029092        0.018350       
+График
+График сохранён в файл: results_plot.png
+
+Анализ:
+
+ВСТАВКА:
+  Лучшая: HashTable (0.014010 сек)
+  Худшая: LinkedList (3.457801 сек)
+
+ПОИСК:
+  Лучшая: HashTable (0.000108 сек)
+  Худшая: LinkedList (0.024537 сек)
+
+УДАЛЕНИЕ:
+  Лучшая: HashTable (0.000077 сек)
+  Худшая: LinkedList (0.032089 сек)
+
+Вывод:
+Для вставок, поиска и удаления лучше всего использовать HashTable как для отсортированных, так и для неотсортированных данных
+BST неплох для отсортированных данных, но всё равно хуже HashTable
+LinkedList показал худшие результаты
+HashTable - оптимальный выбор для телефонного справочника

SimonovaMS/analyz_1.py

@@ -0,0 +1,134 @@
+import csv
+import matplotlib.pyplot as plt
+import numpy as np
+from collections import defaultdict
+import os
+
+report_file = open("analysis_report.txt", "w", encoding="utf-8")
+# Читаем файл
+data = defaultdict(lambda: defaultdict(dict))
+
+with open("C:/Users/Honor/Documents/dep2k/lab_inf_1/data/results.csv", "r", encoding="utf-8") as f:
+    reader = csv.reader(f)
+    header = next(reader)  # пропускаем заголовок
+    print(f"{header}")
+    report_file.write(f"{header}\n")
+
+    for row in reader:
+        if len(row) >= 4:
+            struct = row[0]      # LinkedList, HashTable, Bst
+            mode = row[1]         # shuffled или sorted
+            op = row[2]           # insert, find, delete
+            time_val = float(row[3])
+
+            data[struct][mode][op] = time_val
+            print(f"{struct} | {mode} | {op} | {time_val:.6f}")
+            report_file.write(f"{struct} | {mode} | {op} | {time_val:.6f}\n")
+
+# Словарь для нормальных названий операций
+op_names = {
+    'insert': 'вставка',
+    'find': 'поиск',
+    'delete': 'удаление'
+}
+
+# Структуры и режимы
+structures = ["LinkedList", "HashTable", "Bst"]
+modes = ["shuffled", "sorted"]
+operations = ["insert", "find", "delete"]
+
+# Вывод таблицы результатов
+print("Результаты:")
+report_file.write("\nРезультаты:\n")
+print(f"{'Структура':<15} {'Режим':<10} {'вставка':<15} {'поиск':<15} {'удаление':<15}")
+report_file.write(f"{'Структура':<15} {'Режим':<10} {'вставка':<15} {'поиск':<15} {'удаление':<15}\n")
+
+for struct in structures:
+    for mode in modes:
+        insert_time = data[struct][mode]['insert']
+        find_time = data[struct][mode]['find']
+        delete_time = data[struct][mode]['delete']
+        print(f"{struct:<15} {mode:<10} {insert_time:<15.6f} {find_time:<15.6f} {delete_time:<15.6f}")
+        report_file.write(f"{struct:<15} {mode:<10} {insert_time:<15.6f} {find_time:<15.6f} {delete_time:<15.6f}\n")
+
+# Создаём графики
+fig, axes = plt.subplots(1, 3, figsize=(15, 5))
+
+for idx, op in enumerate(operations):
+    ax = axes[idx]
+
+    x = np.arange(len(structures))
+    width = 0.35
+
+    shuffled_vals = [data[s]["shuffled"][op] for s in structures]
+    sorted_vals = [data[s]["sorted"][op] for s in structures]
+
+    bars1 = ax.bar(x - width/2, shuffled_vals, width, label='shuffled', color='orange', alpha=0.8)
+    bars2 = ax.bar(x + width/2, sorted_vals, width, label='sorted', color='cyan', alpha=0.8)
+
+    ax.set_xlabel('Структура')
+    ax.set_ylabel('Время (сек)')
+    ax.set_title(f'{op_names[op]}')
+    ax.set_xticks(x)
+    ax.set_xticklabels(structures, rotation=45)
+    ax.legend()
+    ax.set_yscale('log')
+
+    # Добавляем значения
+    for bar in bars1:
+        height = bar.get_height()
+        ax.text(bar.get_x() + bar.get_width()/2, height,
+               f'{height:.3f}', ha='center', va='bottom', fontsize=8)
+    for bar in bars2:
+        height = bar.get_height()
+        ax.text(bar.get_x() + bar.get_width()/2, height,
+               f'{height:.3f}', ha='center', va='bottom', fontsize=8)
+
+plt.tight_layout()
+plot_filename = "results_plot.png"
+plt.savefig('results_plot.png', dpi=150)
+plt.show()
+
+report_file.write("График\n")
+report_file.write(f"График сохранён в файл: {plot_filename}\n")
+# Анализ
+print("Анализ:")
+report_file.write("\nАнализ:\n")
+
+# Для каждой операции определяем лучшую структуру
+for op in operations:
+    print(f"\n{op_names[op].upper()}:")
+    report_file.write(f"\n{op_names[op].upper()}:\n")
+
+    # Среднее по двум режимам
+    avg_times = []
+    for s in structures:
+        avg = (data[s]["shuffled"][op] + data[s]["sorted"][op]) / 2
+        avg_times.append((s, avg))
+
+    avg_times.sort(key=lambda x: x[1])
+    print(f"  Лучшая: {avg_times[0][0]} ({avg_times[0][1]:.6f} сек)")
+    print(f"  Худшая: {avg_times[-1][0]} ({avg_times[-1][1]:.6f} сек)")
+    report_file.write(f"  Лучшая: {avg_times[0][0]} ({avg_times[0][1]:.6f} сек)\n")
+    report_file.write(f"  Худшая: {avg_times[-1][0]} ({avg_times[-1][1]:.6f} сек)\n")
+# Влияние порядка на BST
+# print("ВЛИЯНИЕ ПОРЯДКА ДАННЫХ НА BST:")
+# bst_insert_shuffled = data["Bst"]["shuffled"]["insert"]
+# bst_insert_sorted = data["Bst"]["sorted"]["insert"]
+# print(f"  Вставка shuffled: {bst_insert_shuffled:.6f} сек")
+# print(f"  Вставка sorted:   {bst_insert_sorted:.6f} сек")
+# print(f"  Разница: {bst_insert_sorted/bst_insert_shuffled:.1f} раз")
+
+# Итоговый вывод
+print("Вывод:")
+report_file.write("\nВывод:\n")
+print("Для вставок, поиска и удаления лучше всего использовать HashTable как для отсортированных, так и для неотсортированных данных")
+print("BST неплох для отсортированных данных, но всё равно хуже HashTable")
+print("LinkedList показал худшие результаты")
+print("HashTable - оптимальный выбор для телефонного справочника")
+
+report_file.write("Для вставок, поиска и удаления лучше всего использовать HashTable как для отсортированных, так и для неотсортированных данных\n")
+report_file.write("BST неплох для отсортированных данных, но всё равно хуже HashTable\n")
+report_file.write("LinkedList показал худшие результаты\n")
+report_file.write("HashTable - оптимальный выбор для телефонного справочника\n")
+report_file.close()

SimonovaMS/generator_1.py

@@ -0,0 +1,48 @@
+import random
+from typing import List, Tuple
+
+def generate_data(n=10000):
+    records = []
+    for i in range(n):
+        name = f"User_{i:05d}"
+        phone = f"8{random.randint(900,999)}{random.randint(100,999)}{random.randint(0,9)}{random.randint(0,9)}{random.randint(0,9)}{random.randint(0,9)}"
+        records.append((name,phone))
+
+    records_shuffled = records.copy()
+    random.shuffle(records_shuffled)
+    records_sorted = sorted(records, key=lambda x:x[0])
+
+    return records_shuffled, records_sorted
+
+def generate_search(records, exist_count=100, no_exist_count=10):
+    exist_names = [name for name, _ in records]
+    select_exist = random.sample(exist_names, min(exist_count, len(exist_names)))
+
+    no_exist_count=[f"None_{i:05d}" for i in range(no_exist_count)]
+    
+    return select_exist + no_exist_count
+
+def generate_delete(records, count=50):
+    names = [name for name, _ in records]
+    return  random.sample(names, min(count, len(names)))
+
+## Генерируем данные
+# shuffled, sorted_records = generate_data(10)  # 10 записей для примера
+#
+# print("=== Перемешанные записи (первые 5) ===")
+# for record in shuffled[:5]:
+#     print(f"  {record}")
+#
+# print("\n=== Отсортированные записи (первые 5) ===")
+# for record in sorted_records[:5]:
+#     print(f"  {record}")
+#
+# # Генерируем поисковые запросы
+# search_queries = generate_search(sorted_records, exist_count=5, no_exist_count=3)
+# print(f"\n=== Поисковые запросы (всего {len(search_queries)}) ===")
+# print(search_queries)
+#
+# # Генерируем запросы на удаление
+# delete_queries = generate_delete(sorted_records, count=5)
+# print(f"\n=== Запросы на удаление (всего {len(delete_queries)}) ===")
+# print(delete_queries)

SimonovaMS/phonebook_1_2.py

@@ -0,0 +1,265 @@
+import time
+import csv
+import random
+from functools import lru_cache
+from operator import index
+
+
+#LinkedListPhoneBook
+def create_node(name, phone):
+    return {'name': name, 'phone': phone, 'next': None}
+
+def ll_insert(head, name, phone):
+    new_node = create_node(name,phone)
+
+    if head is None:
+        return new_node
+    # if head['name'] == name:
+    #     new_node['next']=head['next']
+    #     return new_node
+    current = head
+    while current['next'] is not None:
+        if current['next']['name'] == name:
+            new_node['next'] = current['next']['next']
+            current['next']=new_node
+            return head
+        current=current['next']
+
+    current['next'] = new_node
+    return head
+
+def ll_find(head, name):
+    current = head
+    while current is not None:
+        if current['name'] ==name:
+            return current['phone']
+        current=current['next']
+    return None
+def ll_delete(head, name):
+    if head is None:
+        return None
+    if head['name'] == name:
+        return head['next']
+
+    current =head
+    while current['next'] is not None:
+        if current['next']['name'] == name:
+            current['next'] = current['next']['next']
+            return head
+        current=current['next']
+
+    return head
+
+def ll_list_all(head):
+    records = []
+    current = head
+    while current is not None:
+        records.append((current['name'], current['phone']))
+        current = current['next']
+
+    records.sort(key=lambda x: x[0])
+    return records
+
+#хеш=тфблица
+
+def create_buckets(size=1000):
+    return [None] * size
+
+def hash_function(name, buckest_size):
+    hash_value = 0
+    for char in name:
+        hash_value = (hash_value * 31 + ord(char)) % buckest_size
+    return hash_value
+
+def ht_insert(buckets, name, phone):
+    index = hash_function(name, len(buckets))
+    buckets[index] = ll_insert(buckets[index], name, phone)
+
+def ht_find(buckets, name):
+    index = hash_function(name, len(buckets))
+    return ll_find(buckets[index], name)
+
+def ht_delete(buckets, name):
+    index = hash_function(name, len(buckets))
+    buckets[index] = ll_delete(buckets[index], name)
+
+def ht_list_all(buckets):
+    records = []
+    for bucket in buckets:
+        current = bucket
+        while current is not None:
+            records.append((current['name'], current['phone']))
+            current = current['next']
+    records.sort(key=lambda x:x[0])
+    return records
+
+#bts
+def create_bst_node(name, phone):
+    return {'name': name, 'phone': phone, 'left': None, 'right': None}
+
+def bst_insert(root, name, phone):
+    new_node = create_bst_node(name, phone)
+    if root is None:
+        return new_node
+    current = root
+    while True:
+        if name == current['name']:
+            current['phone'] = phone
+            return root
+        elif name < current['name']:
+            if current['left'] is None:
+                current['left'] = new_node
+                return root
+            current = current['left']
+        else:
+            if current['right'] is None:
+                current['right'] = new_node
+                return root
+            current = current['right']
+
+
+def bst_find(root, name):
+#    if root is None:
+#        return None
+    current = root
+    while current is not None:
+        if name == current['name']:
+            return current['phone']
+        elif name < current['name']:
+            current=current['left']
+        else:
+            current=current['right']
+    return None
+
+def bst_find_min(node):
+    current = node
+    while current['left'] is not None:
+        current = current['left']
+    return current
+
+
+def bst_delete(root, name):
+    """ИТЕРАТИВНОЕ удаление (без рекурсии)"""
+    if root is None:
+        return None
+
+    # Специальный случай: удаляем корень
+    if root['name'] == name:
+        # Нет потомков
+        if root['left'] is None and root['right'] is None:
+            return None
+        # Только правый потомок
+        if root['left'] is None:
+            return root['right']
+        # Только левый потомок
+        if root['right'] is None:
+            return root['left']
+        # Есть оба потомка
+        # Находим минимальный узел в правом поддереве
+        parent = root
+        min_node = root['right']
+        while min_node['left']:
+            parent = min_node
+            min_node = min_node['left']
+
+        # Копируем данные
+        root['name'] = min_node['name']
+        root['phone'] = min_node['phone']
+
+        # Удаляем минимальный узел
+        if parent == root:
+            parent['right'] = min_node['right']
+        else:
+            parent['left'] = min_node['right']
+
+        return root
+
+    # Ищем узел для удаления и его родителя
+    parent = None
+    current = root
+    while current and current['name'] != name:
+        parent = current
+        if name < current['name']:
+            current = current['left']
+        else:
+            current = current['right']
+
+    # Если не нашли
+    if current is None:
+        return root
+
+    # Случай 1: нет потомков
+    if current['left'] is None and current['right'] is None:
+        if parent['left'] == current:
+            parent['left'] = None
+        else:
+            parent['right'] = None
+
+    # Случай 2: только правый потомок
+    elif current['left'] is None:
+        if parent['left'] == current:
+            parent['left'] = current['right']
+        else:
+            parent['right'] = current['right']
+
+    # Случай 3: только левый потомок
+    elif current['right'] is None:
+        if parent['left'] == current:
+            parent['left'] = current['left']
+        else:
+            parent['right'] = current['left']
+
+    # Случай 4: есть оба потомка
+    else:
+        # Находим минимальный узел в правом поддереве
+        min_parent = current
+        min_node = current['right']
+        while min_node['left']:
+            min_parent = min_node
+            min_node = min_node['left']
+
+        # Копируем данные
+        current['name'] = min_node['name']
+        current['phone'] = min_node['phone']
+
+        # Удаляем минимальный узел
+        if min_parent == current:
+            min_parent['right'] = min_node['right']
+        else:
+            min_parent['left'] = min_node['right']
+
+    return root
+
+
+def bst_list_all(root):
+    """Центрированный обход с использованием стека"""
+    records = []
+    stack = []
+    current = root
+
+    while stack or current:
+        while current:
+            stack.append(current)
+            current = current['left']
+
+        current = stack.pop()
+        records.append((current['name'], current['phone']))
+        current = current['right']
+
+    return records
+
+def bst_list_all(root):
+    records =[]
+    stack = []
+    current = root
+    while stack or current is not None:
+        while current is not None:
+            stack.append(current)
+            current=current['left']
+
+        current=stack.pop()
+        records.append((current['name'], current['phone']))
+
+        current=current['right']
+    return records
+

SimonovaMS/test_1.1.py

@@ -0,0 +1,211 @@
+import time
+import csv
+import random
+
+from phonebook_1_2 import (ll_insert, ll_find, ll_delete, create_buckets, ht_insert, ht_find, ht_delete, bst_insert, bst_find, bst_delete)
+from generator_1 import generate_data
+
+def run_exp():
+    records_shuffled, records_sorted = generate_data(10000)
+    all_names = [name for name, _ in records_shuffled]
+    search_names = random.sample(all_names, 100) + [f"None_{i}" for i in range(10)]
+    delete_names = random.sample(all_names, 50)
+
+    results = [["Structura", "shuffled/sorted", "Operation", "Time"]]
+
+    times =[]
+    print('LinkedList - shuffled')
+    for r in range(5):
+        head = None
+        start = time.perf_counter()
+        for name, phone in records_shuffled:
+            head = ll_insert(head, name, phone)
+        times.append(time.perf_counter() - start)
+    avg = sum(times)/5
+    results.append(["LinkedList", "shuffled", "insert", avg])
+    print(f"вставка - {avg:.6f}")
+
+    times=[]
+    for r in range(5):
+        start = time.perf_counter()
+        for name in search_names:
+            ll_find(head, name)
+        times.append(time.perf_counter() - start)
+    avg = sum(times) / 5
+    results.append(["LinkedList", "shuffled", "find", avg])
+    print(f"поиск - {avg:.6f}")
+
+    times=[]
+    for r in range(5):
+        start = time.perf_counter()
+        for name in delete_names:
+            head = ll_delete(head, name)
+        times.append(time.perf_counter() - start)
+    avg = sum(times) / 5
+    results.append(["LinkedList", "shuffled", "delete", avg])
+    print(f"удаление - {avg:.6f}")
+
+    print('LinkedList - sorted')
+    for r in range(5):
+        head = None
+        start = time.perf_counter()
+        for name, phone in records_sorted:
+            head = ll_insert(head, name, phone)
+        times.append(time.perf_counter() - start)
+    avg = sum(times) / 5
+    results.append(["LinkedList", "sorted", "insert", avg])
+    print(f"вставка - {avg:.6f}")
+
+    times = []
+    for r in range(5):
+        start = time.perf_counter()
+        for name in search_names:
+            ll_find(head, name)
+        times.append(time.perf_counter() - start)
+    avg = sum(times) / 5
+    results.append(["LinkedList", "sorted", "find", avg])
+    print(f"поиск - {avg:.6f}")
+
+    times = []
+    for r in range(5):
+        start = time.perf_counter()
+        for name in delete_names:
+            head = ll_delete(head, name)
+        times.append(time.perf_counter() - start)
+    avg = sum(times) / 5
+    results.append(["LinkedList", "sorted", "delete", avg])
+    print(f"удаление - {avg:.6f}")
+
+    print('HashTable - shuffled')
+    times =[]
+    for r in range(5):
+        buckets = create_buckets(1000)
+        start = time.perf_counter()
+        for name, phone in records_shuffled:
+            ht_insert(buckets,name,phone)
+        times.append(time.perf_counter() - start)
+    avg = sum(times) / 5
+    results.append(["HashTable", "shuffled", "insert", avg])
+    print(f"вставка - {avg:.6f}")
+
+    times = []
+    for r in range(5):
+        start = time.perf_counter()
+        for name in search_names:
+            ht_find(buckets, name)
+        times.append(time.perf_counter() - start)
+    avg = sum(times) / 5
+    results.append(["HashTable", "shuffled", "find", avg])
+    print(f"поиск - {avg:.6f}")
+
+    times = []
+    for r in range(5):
+        start = time.perf_counter()
+        for name in delete_names:
+            ht_delete(buckets, name)
+        times.append(time.perf_counter() - start)
+    avg = sum(times) / 5
+    results.append(["HashTable", "shuffled", "delete", avg])
+    print(f"удаление - {avg:.6f}")
+
+    print('sorted')
+    times = []
+    for r in range(5):
+        buckets = create_buckets(1000)
+        start = time.perf_counter()
+        for name, phone in records_sorted:
+            ht_insert(buckets, name, phone)
+        times.append(time.perf_counter() - start)
+    avg = sum(times) / 5
+    results.append(["HashTable", "sorted", "insert", avg])
+    print(f"вставка - {avg:.6f}")
+
+    times = []
+    for r in range(5):
+        start = time.perf_counter()
+        for name in search_names:
+            ht_find(buckets, name)
+        times.append(time.perf_counter() - start)
+    avg = sum(times) / 5
+    results.append(["HashTable", "sorted", "find", avg])
+    print(f"поиск - {avg:.6f}")
+
+    times = []
+    for r in range(5):
+        start = time.perf_counter()
+        for name in delete_names:
+            ht_delete(buckets, name)
+        times.append(time.perf_counter() - start)
+    avg = sum(times) / 5
+    results.append(["HashTable", "sorted", "delete", avg])
+    print(f"удаление - {avg:.6f}")
+
+    print("BST - shuffled")
+    times = []
+    for r in range(5):
+        root = None
+        start = time.perf_counter()
+        for name, phone in records_shuffled:
+            root = bst_insert(root, name, phone)
+        times.append(time.perf_counter() - start)
+    avg = sum(times) / 5
+    results.append(["Bst", "shuffled", "insert", avg])
+    print(f"вставка - {avg:.6f}")
+
+    times = []
+    for r in range(5):
+        start = time.perf_counter()
+        for name in search_names:
+            bst_find(root, name)
+        times.append(time.perf_counter() - start)
+    avg = sum(times) / 5
+    results.append(["Bst", "shuffled", "find", avg])
+    print(f"поиск - {avg:.6f}")
+
+    times = []
+    for r in range(5):
+        start = time.perf_counter()
+        for name in delete_names:
+            root = bst_delete(root, name)
+        times.append(time.perf_counter() - start)
+    avg = sum(times) / 5
+    results.append(["Bst", "shuffled", "delete", avg])
+    print(f"удаление - {avg:.6f}")
+
+    print('sorted')
+    times = []
+    for r in range(5):
+        root = None
+        start = time.perf_counter()
+        for name, phone in records_sorted:
+            root = bst_insert(root, name, phone)
+        times.append(time.perf_counter() - start)
+    avg = sum(times) / 5
+    results.append(["Bst", "sorted", "insert", avg])
+    print(f"вставка - {avg:.6f}")
+
+    times = []
+    for r in range(5):
+        start = time.perf_counter()
+        for name in search_names:
+            bst_find(root, name)
+        times.append(time.perf_counter() - start)
+    avg = sum(times) / 5
+    results.append(["Bst", "sorted", "find", avg])
+    print(f"поиск - {avg:.6f}")
+
+    times = []
+    for r in range(5):
+        start = time.perf_counter()
+        for name in delete_names:
+            root = bst_delete(root, name)
+        times.append(time.perf_counter() - start)
+    avg = sum(times) / 5
+    results.append(["Bst", "sorted", "delete", avg])
+    print(f"удаление - {avg:.6f}")
+
+    with open("C:/Users/Honor/Documents/dep2k/lab_inf_1/data/results.csv", "w", newline="", encoding="utf-8") as f:
+        writer = csv.writer(f)
+        writer.writerows(results)
+if __name__ == "__main__":
+    run_exp()