9.6 KiB
import csv import random import sys import time from collections import defaultdict
увеличиваем лимит рекурсии
sys.setrecursionlimit(25000)
1. связный список, узел: {'name': 'Имя', 'phone': '123', 'next': None}
проходит до конца и добавляет в конец
def ll_insert(head, name, phone): new_node = {'name': name, 'phone': phone, 'next': None} if head is None: return new_node current = head while current['next'] is not None: current = current['next'] current['next'] = new_node return head
ищет узел, возвращает телефон или None
def ll_find(head, name): current = head while current is not None: if current['name'] == name: return current['phone'] current = current['next'] return None
удаляет узел, возвращает новую голову
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
собирает все записи в список и сортирует
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
2. хеш-таблица
хеш-функция для вычисления бекета
def ht_hash(name, size): return hash(name) % size
вычисляет индекс, вызывает ll_insert для соответствующего бакета
def ht_insert(buckets, name, phone): size = len(buckets) idx = ht_hash(name, size) buckets[idx] = ll_insert(buckets[idx], name, phone)
поиск по хеш-таблице
def ht_find(buckets, name): size = len(buckets) idx = ht_hash(name, size) return ll_find(buckets[idx], name)
удаление из хеш-таблицы
def ht_delete(buckets, name): size = len(buckets) idx = ht_hash(name, size) buckets[idx] = ll_delete(buckets[idx], name)
собирает все записи из всех бакетов и сортирует
def ht_list_all(buckets): all_records = [] for head in buckets: current = head while current is not None: all_records.append((current['name'], current['phone'])) current = current['next'] all_records.sort(key=lambda x: x[0]) return all_records
3. двоичное дерево поиска
узел — словарь: {'name': 'Имя', 'phone': '123', 'left': None, 'right': None}
рекурсивно или итеративно вставляет, возвращает новый корень (если корень меняется)
def bst_insert(root, name, phone): if root is None: return {'name': name, 'phone': phone, 'left': None, 'right': None}
if name < root['name']:
root['left'] = bst_insert(root['left'], name, phone)
elif name > root['name']:
root['right'] = bst_insert(root['right'], name, phone)
else:
root['phone'] = phone
return root
поиск
def bst_find(root, name): if root is None: return None if name == root['name']: return root['phone'] elif name < root['name']: return bst_find(root['left'], name) else: return bst_find(root['right'], name)
удаление, возвращает новый корень
def bst_delete(root, name): if root is None: return None
if name < root['name']:
root['left'] = bst_delete(root['left'], name)
elif name > root['name']:
root['right'] = bst_delete(root['right'], name)
else:
# одна ветвь или её отсутствие
if root['left'] is None:
return root['right']
if root['right'] is None:
return root['left']
# две ветви
successor = root['right']
while successor['left'] is not None:
successor = successor['left']
root['name'] = successor['name']
root['phone'] = successor['phone']
root['right'] = bst_delete(root['right'], successor['name'])
return root
центрированный обход (рекурсивно собирает записи в отсортированном порядке)
def bst_list_all(root): records = [] def _inorder(node): if node is not None: _inorder(node['left']) records.append((node['name'], node['phone'])) _inorder(node['right']) _inorder(root) return records
ЭКСПЕРИМЕНТАЛЬНАЯ ЧАСТЬ
def run_experiments(): N = 3000 HASH_SIZE = 1007
print(f"генерация тестовых данных для N = {N}...")
records_sorted = [(f"User_{i:05d}", f"+7999123{i:04d}") for i in range(N)]
records_shuffled = records_sorted.copy()
random.seed(42)
random.shuffle(records_shuffled)
# подготовка выборок
existing_sample = [r[0] for r in random.sample(records_sorted, min(100, N))]
non_existing_sample = [f"None_{i}" for i in range(10)]
search_names = existing_sample + non_existing_sample
delete_names = [r[0] for r in random.sample(records_sorted, min(50, N))]
csv_rows = [["структура", "режим", "операция", "повторение", "время (сек)"]]
modes = [("случайный", records_shuffled), ("отсортированный", records_sorted)]
print("запуск экспериментов (5 повторений для каждого режима)")
ТЕСТ: СВЯЗНЫЙ СПИСОК
for mode_name, data in modes:
for rep in range(1, 6):
head = None
t_start = time.perf_counter()
for name, phone in data:
head = ll_insert(head, name, phone)
t_end = time.perf_counter()
csv_rows.append(["LinkedList", mode_name, "вставка", rep, t_end - t_start])
t_start = time.perf_counter()
for name in search_names:
ll_find(head, name)
t_end = time.perf_counter()
csv_rows.append(["LinkedList", mode_name, "поиск", rep, t_end - t_start])
t_start = time.perf_counter()
for name in delete_names:
head = ll_delete(head, name)
t_end = time.perf_counter()
csv_rows.append(["LinkedList", mode_name, "удаление", rep, t_end - t_start])
ТЕСТ: ХЕШ-ТАБЛИЦА
for mode_name, data in modes:
for rep in range(1, 6):
buckets = [None] * HASH_SIZE
t_start = time.perf_counter()
for name, phone in data:
ht_insert(buckets, name, phone)
t_end = time.perf_counter()
csv_rows.append(["HashTable", mode_name, "вставка", rep, t_end - t_start])
t_start = time.perf_counter()
for name in search_names:
ht_find(buckets, name)
t_end = time.perf_counter()
csv_rows.append(["HashTable", mode_name, "поиск", rep, t_end - t_start])
t_start = time.perf_counter()
for name in delete_names:
ht_delete(buckets, name)
t_end = time.perf_counter()
csv_rows.append(["HashTable", mode_name, "удаление", rep, t_end - t_start])
ТЕСТ: ДЕРЕВО ПОИСКА (BST)
for mode_name, data in modes:
for rep in range(1, 6):
root = None
t_start = time.perf_counter()
for name, phone in data:
root = bst_insert(root, name, phone)
t_end = time.perf_counter()
csv_rows.append(["BST", mode_name, "вставка", rep, t_end - t_start])
t_start = time.perf_counter()
for name in search_names:
bst_find(root, name)
t_end = time.perf_counter()
csv_rows.append(["BST", mode_name, "поиск", rep, t_end - t_start])
t_start = time.perf_counter()
for name in delete_names:
root = bst_delete(root, name)
t_end = time.perf_counter()
csv_rows.append(["BST", mode_name, "удаление", rep, t_end - t_start])
сохранение в csv
with open("results.csv", "w", newline="", encoding="utf-8") as f:
writer = csv.writer(f)
writer.writerows(csv_rows)
print("\nвсе замеры сохранены в файл 'results.csv'.")
show_summary(csv_rows)
функция для подсчета и вывода среднего времени
def show_summary(rows): summary = defaultdict(list) for row in rows[1:]: struct, mode, op, rep, elapsed = row summary[(struct, mode, op)].append(elapsed)
print("\nСВОДНЫЕ РЕЗУЛЬТАТЫ (СРЕДНЕЕ ВРЕМЯ ИЗ 5 ЗАПУСКОВ)")
print(f"{'структура':<12} | {'режим данных':<15} | {'операция':<10} | {'время (сек)':<12}")
print("-" * 59)
for (struct, mode, op), times in sorted(summary.items()):
avg_time = sum(times) / len(times)
print(f"{struct:<12} | {mode:<15} | {op:<10} | {avg_time:.6f}")
if name == "main": run_experiments()