366 lines
14 KiB
Python
366 lines
14 KiB
Python
import time
|
||
import random
|
||
import csv
|
||
import sys
|
||
sys.setrecursionlimit (50000)
|
||
from datetime import datetime
|
||
|
||
# ==================== СВЯЗНЫЙ СПИСОК ====================
|
||
|
||
def ll_insert(head, name, phone):
|
||
"""Добавляет или обновляет запись в связном списке"""
|
||
# Проверяем, не существует ли уже такой name
|
||
curr = head
|
||
while curr:
|
||
if curr['name'] == name:
|
||
curr['phone'] = phone # обновляем
|
||
return head
|
||
curr = curr['next']
|
||
|
||
# Если не нашли, вставляем в конец
|
||
new_node = {'name': name, 'phone': phone, 'next': None}
|
||
|
||
if head is None:
|
||
return new_node
|
||
|
||
curr = head
|
||
while curr['next']:
|
||
curr = curr['next']
|
||
curr['next'] = new_node
|
||
return head
|
||
|
||
def ll_find(head, name):
|
||
"""Ищет запись по имени, возвращает телефон или None"""
|
||
curr = head
|
||
while curr:
|
||
if curr['name'] == name:
|
||
return curr['phone']
|
||
curr = curr['next']
|
||
return None
|
||
|
||
def ll_delete(head, name):
|
||
"""Удаляет запись по имени, возвращает новую голову"""
|
||
if head is None:
|
||
return None
|
||
|
||
# Если удаляем голову
|
||
if head['name'] == name:
|
||
return head['next']
|
||
|
||
# Ищем элемент перед удаляемым
|
||
curr = head
|
||
while curr['next']:
|
||
if curr['next']['name'] == name:
|
||
curr['next'] = curr['next']['next']
|
||
return head
|
||
curr = curr['next']
|
||
return head
|
||
|
||
def ll_list_all(head):
|
||
"""Собирает все записи и сортирует по имени"""
|
||
records = []
|
||
curr = head
|
||
while curr:
|
||
records.append((curr['name'], curr['phone']))
|
||
curr = curr['next']
|
||
# Сортируем по имени
|
||
records.sort(key=lambda x: x[0])
|
||
return records
|
||
|
||
# ==================== ХЕШ-ТАБЛИЦА ====================
|
||
|
||
def hash_function(name, size):
|
||
"""Простая хеш-функция"""
|
||
return sum(ord(c) for c in name) % size
|
||
|
||
def ht_insert(buckets, name, phone):
|
||
"""Вставляет запись в хеш-таблицу"""
|
||
index = hash_function(name, len(buckets))
|
||
# Используем ll_insert для бакета
|
||
buckets[index] = ll_insert(buckets[index], name, phone)
|
||
return buckets
|
||
|
||
def ht_find(buckets, name):
|
||
"""Ищет запись в хеш-таблице"""
|
||
index = hash_function(name, len(buckets))
|
||
return ll_find(buckets[index], name)
|
||
|
||
def ht_delete(buckets, name):
|
||
"""Удаляет запись из хеш-таблицы"""
|
||
index = hash_function(name, len(buckets))
|
||
buckets[index] = ll_delete(buckets[index], name)
|
||
return buckets
|
||
|
||
def ht_list_all(buckets):
|
||
"""Собирает все записи из всех бакетов и сортирует"""
|
||
all_records = []
|
||
for bucket in buckets:
|
||
curr = bucket
|
||
while curr:
|
||
all_records.append((curr['name'], curr['phone']))
|
||
curr = curr['next']
|
||
all_records.sort(key=lambda x: x[0])
|
||
return all_records
|
||
|
||
# ==================== БИНАРНОЕ ДЕРЕВО ПОИСКА ====================
|
||
|
||
def bst_insert(root, name, phone):
|
||
"""Вставляет запись в BST (рекурсивно)"""
|
||
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:
|
||
# Обновляем существующую запись
|
||
root['phone'] = phone
|
||
return root
|
||
|
||
def bst_find(root, name):
|
||
"""Ищет запись в BST"""
|
||
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)
|
||
|
||
def bst_find_min(node):
|
||
"""Находит узел с минимальным значением"""
|
||
current = node
|
||
while current and current['left']:
|
||
current = current['left']
|
||
return current
|
||
|
||
def bst_delete(root, name):
|
||
"""Удаляет запись из BST"""
|
||
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:
|
||
# Узел найден
|
||
if root['left'] is None:
|
||
return root['right']
|
||
elif root['right'] is None:
|
||
return root['left']
|
||
|
||
# Узел с двумя детьми
|
||
temp = bst_find_min(root['right'])
|
||
root['name'] = temp['name']
|
||
root['phone'] = temp['phone']
|
||
root['right'] = bst_delete(root['right'], temp['name'])
|
||
return root
|
||
|
||
def bst_list_all(root):
|
||
"""Центрированный обход (возвращает отсортированный список)"""
|
||
records = []
|
||
|
||
def inorder_traversal(node):
|
||
if node:
|
||
inorder_traversal(node['left'])
|
||
records.append((node['name'], node['phone']))
|
||
inorder_traversal(node['right'])
|
||
|
||
inorder_traversal(root)
|
||
return records
|
||
|
||
# ==================== ГЕНЕРАЦИЯ ТЕСТОВЫХ ДАННЫХ ====================
|
||
|
||
def generate_test_data(n=10000):
|
||
"""Генерирует shuffled и sorted версии данных"""
|
||
# Генерируем имена с небольшим количеством коллизий
|
||
names_pool = [f"User_{i:05d}" for i in range(n // 10)] # 1000 уникальных имен
|
||
records = []
|
||
|
||
for i in range(n):
|
||
name = random.choice(names_pool) # повторяющиеся имена для коллизий
|
||
phone = f"+7-999-{random.randint(1000000, 9999999)}"
|
||
records.append((name, phone))
|
||
|
||
# Создаем shuffled и sorted версии
|
||
records_shuffled = records.copy()
|
||
random.shuffle(records_shuffled)
|
||
|
||
records_sorted = sorted(records, key=lambda x: x[0])
|
||
|
||
return records_shuffled, records_sorted
|
||
|
||
# ==================== ЗАМЕРЫ ВРЕМЕНИ ====================
|
||
|
||
def measure_insertion(struct_type, records, buckets_size=None):
|
||
"""Замеряет время вставки всех записей"""
|
||
if struct_type == "LinkedList":
|
||
head = None
|
||
start = time.perf_counter()
|
||
for name, phone in records:
|
||
head = ll_insert(head, name, phone)
|
||
end = time.perf_counter()
|
||
elif struct_type == "HashTable":
|
||
if buckets_size is None:
|
||
buckets_size = 1000
|
||
buckets = [None] * buckets_size
|
||
start = time.perf_counter()
|
||
for name, phone in records:
|
||
buckets = ht_insert(buckets, name, phone)
|
||
end = time.perf_counter()
|
||
elif struct_type == "BST":
|
||
root = None
|
||
start = time.perf_counter()
|
||
for name, phone in records:
|
||
root = bst_insert(root, name, phone)
|
||
end = time.perf_counter()
|
||
else:
|
||
return None, None
|
||
|
||
elapsed = end - start
|
||
return elapsed, (head if struct_type == "LinkedList" else (buckets if struct_type == "HashTable" else root))
|
||
|
||
def measure_find(struct_type, data_structure, records, num_existing=100, num_nonexistent=10):
|
||
"""Замеряет время поиска записей"""
|
||
# Выбираем существующие записи
|
||
existing_names = random.sample([name for name, _ in records[:len(records)//2]], min(num_existing, len(records)))
|
||
|
||
# Создаем несуществующие имена
|
||
nonexistent_names = [f"None_{i}" for i in range(num_nonexistent)]
|
||
|
||
all_queries = existing_names + nonexistent_names
|
||
random.shuffle(all_queries)
|
||
|
||
start = time.perf_counter()
|
||
for name in all_queries:
|
||
if struct_type == "LinkedList":
|
||
ll_find(data_structure, name)
|
||
elif struct_type == "HashTable":
|
||
ht_find(data_structure, name)
|
||
elif struct_type == "BST":
|
||
bst_find(data_structure, name)
|
||
end = time.perf_counter()
|
||
|
||
return end - start
|
||
|
||
def measure_delete(struct_type, data_structure, records, num_to_delete=50):
|
||
"""Замеряет время удаления записей"""
|
||
# Выбираем случайные имена для удаления
|
||
names_to_delete = random.sample([name for name, _ in records[:len(records)//2]], min(num_to_delete, len(records)))
|
||
|
||
start = time.perf_counter()
|
||
for name in names_to_delete:
|
||
if struct_type == "LinkedList":
|
||
data_structure = ll_delete(data_structure, name)
|
||
elif struct_type == "HashTable":
|
||
data_structure = ht_delete(data_structure, name)
|
||
elif struct_type == "BST":
|
||
data_structure = bst_delete(data_structure, name)
|
||
end = time.perf_counter()
|
||
|
||
return end - start
|
||
|
||
# ==================== ОСНОВНОЙ ЭКСПЕРИМЕНТ ====================
|
||
|
||
def run_experiment():
|
||
"""Запускает все эксперименты и сохраняет результаты"""
|
||
|
||
print("Генерация тестовых данных...")
|
||
records_shuffled, records_sorted = generate_test_data(10000)
|
||
|
||
structures = ["LinkedList", "HashTable", "BST"]
|
||
modes = {"shuffled": records_shuffled, "sorted": records_sorted}
|
||
|
||
all_results = []
|
||
all_results.append(["Структура", "Режим", "Операция", "Повторение", "Время (сек)"])
|
||
|
||
# Количество повторений
|
||
repeats = 5
|
||
|
||
for struct in structures:
|
||
for mode_name, records in modes.items():
|
||
print(f"\nТестирование: {struct}, режим {mode_name}")
|
||
|
||
# Вставка
|
||
insertion_times = []
|
||
for rep in range(repeats):
|
||
print(f" Вставка, повторение {rep+1}/{repeats}...")
|
||
elapsed, data_struct = measure_insertion(struct, records)
|
||
insertion_times.append(elapsed)
|
||
all_results.append([struct, mode_name, "вставка", rep+1, elapsed])
|
||
|
||
# Используем последнюю структуру для поиска и удаления
|
||
# (пересоздаем для чистоты эксперимента)
|
||
_, data_struct = measure_insertion(struct, records)
|
||
|
||
# Поиск
|
||
find_times = []
|
||
for rep in range(repeats):
|
||
print(f" Поиск, повторение {rep+1}/{repeats}...")
|
||
elapsed = measure_find(struct, data_struct, records)
|
||
find_times.append(elapsed)
|
||
all_results.append([struct, mode_name, "поиск", rep+1, elapsed])
|
||
|
||
# Удаление
|
||
delete_times = []
|
||
# Создаем свежую структуру для удаления
|
||
_, fresh_data_struct = measure_insertion(struct, records)
|
||
for rep in range(repeats):
|
||
print(f" Удаление, повторение {rep+1}/{repeats}...")
|
||
elapsed = measure_delete(struct, fresh_data_struct, records)
|
||
delete_times.append(elapsed)
|
||
all_results.append([struct, mode_name, "удаление", rep+1, elapsed])
|
||
|
||
# Выводим средние значения
|
||
print(f" Среднее время вставки: {sum(insertion_times)/len(insertion_times):.6f} сек")
|
||
print(f" Среднее время поиска: {sum(find_times)/len(find_times):.6f} сек")
|
||
print(f" Среднее время удаления: {sum(delete_times)/len(delete_times):.6f} сек")
|
||
|
||
# Сохраняем результаты в CSV
|
||
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
|
||
csv_filename = f"experiment_results_{timestamp}.csv"
|
||
|
||
with open(csv_filename, 'w', newline='', encoding='utf-8') as f:
|
||
writer = csv.writer(f)
|
||
writer.writerows(all_results)
|
||
|
||
print(f"\nРезультаты сохранены в файл: {csv_filename}")
|
||
|
||
# Сохраняем также средние значения для удобства
|
||
avg_results = []
|
||
avg_results.append(["Структура", "Режим", "Операция", "Среднее время (сек)", "Мин", "Макс"])
|
||
|
||
# Группируем по структуре, режиму, операции
|
||
grouped = {}
|
||
for row in all_results[1:]: # пропускаем заголовок
|
||
struct, mode, op, rep, time_val = row
|
||
key = (struct, mode, op)
|
||
if key not in grouped:
|
||
grouped[key] = []
|
||
grouped[key].append(time_val)
|
||
|
||
for (struct, mode, op), times in grouped.items():
|
||
avg_time = sum(times) / len(times)
|
||
min_time = min(times)
|
||
max_time = max(times)
|
||
avg_results.append([struct, mode, op, avg_time, min_time, max_time])
|
||
|
||
avg_filename = f"average_results_{timestamp}.csv"
|
||
with open(avg_filename, 'w', newline='', encoding='utf-8') as f:
|
||
writer = csv.writer(f)
|
||
writer.writerows(avg_results)
|
||
|
||
print(f"Средние значения сохранены в файл: {avg_filename}")
|
||
|
||
return all_results, avg_results
|
||
|
||
if __name__ == "__main__":
|
||
print("Начало эксперимента...")
|
||
print("="*50)
|
||
results, avg_results = run_experiment()
|
||
print("="*50)
|
||
print("Эксперимент завершен!") |