505 lines
20 KiB
Python
505 lines
20 KiB
Python
import time
|
||
import random
|
||
import csv
|
||
import sys
|
||
import matplotlib.pyplot as plt
|
||
import numpy as np
|
||
|
||
sys.setrecursionlimit(20000)
|
||
|
||
REPEATS = 5
|
||
N = 10000
|
||
def ll_insert(head, name, phone):
|
||
current = head
|
||
prev = None
|
||
while current is not None:
|
||
if current['name'] == name:
|
||
current['phone'] = phone
|
||
return head
|
||
prev = current
|
||
current = current['next']
|
||
new_node = {'name': name, 'phone': phone, 'next': None}
|
||
if prev is None:
|
||
return new_node
|
||
else:
|
||
prev['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_collect_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
|
||
def hash_function(name, size):
|
||
total = 0
|
||
for ch in name:
|
||
total = (total * 31 + ord(ch)) % size
|
||
return total
|
||
|
||
def ht_create(size=2000):
|
||
return [None] * size
|
||
|
||
def ht_insert(buckets, name, phone):
|
||
idx = hash_function(name, len(buckets))
|
||
buckets[idx] = ll_insert(buckets[idx], name, phone)
|
||
|
||
def ht_find(buckets, name):
|
||
idx = hash_function(name, len(buckets))
|
||
return ll_find(buckets[idx], name)
|
||
|
||
def ht_delete(buckets, name):
|
||
idx = hash_function(name, len(buckets))
|
||
buckets[idx] = ll_delete(buckets[idx], name)
|
||
|
||
def ht_collect_all(buckets):
|
||
all_records = []
|
||
for bucket in buckets:
|
||
current = bucket
|
||
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
|
||
def bst_insert(root, name, phone):
|
||
new_node = {'name': name, 'phone': phone, 'left': None, 'right': None}
|
||
if root is None:
|
||
return new_node
|
||
current = root
|
||
while True:
|
||
if name < current['name']:
|
||
if current['left'] is None:
|
||
current['left'] = new_node
|
||
break
|
||
current = current['left']
|
||
elif name > current['name']:
|
||
if current['right'] is None:
|
||
current['right'] = new_node
|
||
break
|
||
current = current['right']
|
||
else:
|
||
current['phone'] = phone
|
||
break
|
||
return root
|
||
|
||
def bst_find(root, name):
|
||
current = root
|
||
while current is not None:
|
||
if name < current['name']:
|
||
current = current['left']
|
||
elif name > current['name']:
|
||
current = current['right']
|
||
else:
|
||
return current['phone']
|
||
return None
|
||
|
||
def bst_find_min(node):
|
||
while node['left'] is not None:
|
||
node = node['left']
|
||
return node
|
||
|
||
def bst_delete(root, name):
|
||
parent = None
|
||
current = root
|
||
while current is not None and current['name'] != name:
|
||
parent = current
|
||
if name < current['name']:
|
||
current = current['left']
|
||
else:
|
||
current = current['right']
|
||
if current is None:
|
||
return root
|
||
if current['left'] is None and current['right'] is None:
|
||
if parent is None:
|
||
return None
|
||
if parent['left'] is current:
|
||
parent['left'] = None
|
||
else:
|
||
parent['right'] = None
|
||
return root
|
||
if current['left'] is None:
|
||
if parent is None:
|
||
return current['right']
|
||
if parent['left'] is current:
|
||
parent['left'] = current['right']
|
||
else:
|
||
parent['right'] = current['right']
|
||
return root
|
||
if current['right'] is None:
|
||
if parent is None:
|
||
return current['left']
|
||
if parent['left'] is current:
|
||
parent['left'] = current['left']
|
||
else:
|
||
parent['right'] = current['left']
|
||
return root
|
||
succ_parent = current
|
||
succ = current['right']
|
||
while succ['left'] is not None:
|
||
succ_parent = succ
|
||
succ = succ['left']
|
||
current['name'] = succ['name']
|
||
current['phone'] = succ['phone']
|
||
if succ_parent['left'] is succ:
|
||
succ_parent['left'] = succ['right']
|
||
else:
|
||
succ_parent['right'] = succ['right']
|
||
return root
|
||
|
||
def bst_inorder_collect(root, records=None):
|
||
if records is None:
|
||
records = []
|
||
if root is not None:
|
||
bst_inorder_collect(root['left'], records)
|
||
records.append((root['name'], root['phone']))
|
||
bst_inorder_collect(root['right'], records)
|
||
return records
|
||
def generate_records(N=10000):
|
||
records = []
|
||
for i in range(N):
|
||
name = f"User_{i:05d}"
|
||
phone = f"+7-999-{random.randint(1000000, 9999999)}"
|
||
records.append((name, phone))
|
||
return records
|
||
|
||
def measure_insertion(struct_type, records):
|
||
times = []
|
||
for _ in range(REPEATS):
|
||
if struct_type == 'll':
|
||
head = None
|
||
start = time.perf_counter()
|
||
for name, phone in records:
|
||
head = ll_insert(head, name, phone)
|
||
end = time.perf_counter()
|
||
elif struct_type == 'ht':
|
||
buckets = ht_create(2000)
|
||
start = time.perf_counter()
|
||
for name, phone in records:
|
||
ht_insert(buckets, name, phone)
|
||
end = time.perf_counter()
|
||
else:
|
||
root = None
|
||
start = time.perf_counter()
|
||
for name, phone in records:
|
||
root = bst_insert(root, name, phone)
|
||
end = time.perf_counter()
|
||
times.append(end - start)
|
||
return times
|
||
|
||
def build_structure(struct_type, records):
|
||
if struct_type == 'll':
|
||
head = None
|
||
for name, phone in records:
|
||
head = ll_insert(head, name, phone)
|
||
return head
|
||
elif struct_type == 'ht':
|
||
buckets = ht_create(2000)
|
||
for name, phone in records:
|
||
ht_insert(buckets, name, phone)
|
||
return buckets
|
||
else:
|
||
root = None
|
||
for name, phone in records:
|
||
root = bst_insert(root, name, phone)
|
||
return root
|
||
|
||
def measure_search(struct_type, structure, records):
|
||
times = []
|
||
N_records = len(records)
|
||
for _ in range(REPEATS):
|
||
indices = random.sample(range(N_records), 100)
|
||
existing_names = [records[i][0] for i in indices]
|
||
missing_names = [f"None_{i}" for i in range(10)]
|
||
search_names = existing_names + missing_names
|
||
random.shuffle(search_names)
|
||
start = time.perf_counter()
|
||
if struct_type == 'll':
|
||
for name in search_names:
|
||
ll_find(structure, name)
|
||
elif struct_type == 'ht':
|
||
for name in search_names:
|
||
ht_find(structure, name)
|
||
else:
|
||
for name in search_names:
|
||
bst_find(structure, name)
|
||
times.append(time.perf_counter() - start)
|
||
return times
|
||
|
||
def measure_deletion(struct_type, records):
|
||
times = []
|
||
N_records = len(records)
|
||
for _ in range(REPEATS):
|
||
indices = random.sample(range(N_records), 50)
|
||
delete_names = [records[i][0] for i in indices]
|
||
if struct_type == 'll':
|
||
head = None
|
||
for name, phone in records:
|
||
head = ll_insert(head, name, phone)
|
||
start = time.perf_counter()
|
||
for name in delete_names:
|
||
head = ll_delete(head, name)
|
||
end = time.perf_counter()
|
||
elif struct_type == 'ht':
|
||
buckets = ht_create(2000)
|
||
for name, phone in records:
|
||
ht_insert(buckets, name, phone)
|
||
start = time.perf_counter()
|
||
for name in delete_names:
|
||
ht_delete(buckets, name)
|
||
end = time.perf_counter()
|
||
else:
|
||
root = None
|
||
for name, phone in records:
|
||
root = bst_insert(root, name, phone)
|
||
start = time.perf_counter()
|
||
for name in delete_names:
|
||
root = bst_delete(root, name)
|
||
end = time.perf_counter()
|
||
times.append(end - start)
|
||
return times
|
||
def plot_bar_charts(insert_data, search_data, delete_data):
|
||
"""Построение столбчатых диаграмм"""
|
||
|
||
structures = ['ll', 'ht', 'bst']
|
||
labels = ['Связный список', 'Хеш-таблица', 'Двоичное дерево']
|
||
mode_labels = ['Случайный порядок', 'Отсортированный порядок']
|
||
colors = ['skyblue', 'salmon']
|
||
|
||
x = np.arange(len(structures))
|
||
width = 0.35
|
||
|
||
# График вставки
|
||
fig1, ax1 = plt.subplots(figsize=(10, 6))
|
||
means_sh = [sum(insert_data[s]['shuffled'])/len(insert_data[s]['shuffled']) for s in structures]
|
||
means_so = [sum(insert_data[s]['sorted'])/len(insert_data[s]['sorted']) for s in structures]
|
||
|
||
rects1 = ax1.bar(x - width/2, means_sh, width, label=mode_labels[0], color=colors[0])
|
||
rects2 = ax1.bar(x + width/2, means_so, width, label=mode_labels[1], color=colors[1])
|
||
|
||
ax1.set_ylabel('Время (секунды)')
|
||
ax1.set_title('Вставка всех записей (10000 шт.)')
|
||
ax1.set_xticks(x)
|
||
ax1.set_xticklabels(labels)
|
||
ax1.legend()
|
||
ax1.set_yscale('log')
|
||
|
||
for rect in rects1 + rects2:
|
||
h = rect.get_height()
|
||
ax1.annotate(f'{h:.4f}', xy=(rect.get_x() + rect.get_width()/2, h),
|
||
xytext=(0, 3), textcoords="offset points", ha='center', va='bottom', fontsize=8)
|
||
|
||
plt.tight_layout()
|
||
plt.savefig('insert_comparison.png', dpi=150)
|
||
plt.show()
|
||
print(" График вставки сохранён: insert_comparison.png")
|
||
|
||
# График поиска
|
||
fig2, ax2 = plt.subplots(figsize=(10, 6))
|
||
means_sh = [sum(search_data[s]['shuffled'])/len(search_data[s]['shuffled']) for s in structures]
|
||
means_so = [sum(search_data[s]['sorted'])/len(search_data[s]['sorted']) for s in structures]
|
||
|
||
rects1 = ax2.bar(x - width/2, means_sh, width, label=mode_labels[0], color=colors[0])
|
||
rects2 = ax2.bar(x + width/2, means_so, width, label=mode_labels[1], color=colors[1])
|
||
|
||
ax2.set_ylabel('Время (секунды)')
|
||
ax2.set_title('Поиск (100 существующих + 10 отсутствующих)')
|
||
ax2.set_xticks(x)
|
||
ax2.set_xticklabels(labels)
|
||
ax2.legend()
|
||
|
||
for rect in rects1 + rects2:
|
||
h = rect.get_height()
|
||
ax2.annotate(f'{h:.6f}', xy=(rect.get_x() + rect.get_width()/2, h),
|
||
xytext=(0, 3), textcoords="offset points", ha='center', va='bottom', fontsize=8)
|
||
|
||
plt.tight_layout()
|
||
plt.savefig('search_comparison.png', dpi=150)
|
||
plt.show()
|
||
print(" График поиска сохранён: search_comparison.png")
|
||
|
||
# График удаления
|
||
fig3, ax3 = plt.subplots(figsize=(10, 6))
|
||
means_sh = [sum(delete_data[s]['shuffled'])/len(delete_data[s]['shuffled']) for s in structures]
|
||
means_so = [sum(delete_data[s]['sorted'])/len(delete_data[s]['sorted']) for s in structures]
|
||
|
||
rects1 = ax3.bar(x - width/2, means_sh, width, label=mode_labels[0], color=colors[0])
|
||
rects2 = ax3.bar(x + width/2, means_so, width, label=mode_labels[1], color=colors[1])
|
||
|
||
ax3.set_ylabel('Время (секунды)')
|
||
ax3.set_title('Удаление 50 случайных записей')
|
||
ax3.set_xticks(x)
|
||
ax3.set_xticklabels(labels)
|
||
ax3.legend()
|
||
|
||
for rect in rects1 + rects2:
|
||
h = rect.get_height()
|
||
ax3.annotate(f'{h:.6f}', xy=(rect.get_x() + rect.get_width()/2, h),
|
||
xytext=(0, 3), textcoords="offset points", ha='center', va='bottom', fontsize=8)
|
||
|
||
plt.tight_layout()
|
||
plt.savefig('delete_comparison.png', dpi=150)
|
||
plt.show()
|
||
print(" График удаления сохранён: delete_comparison.png")
|
||
|
||
|
||
def plot_attempts_graphs(data, op_name, op_title):
|
||
"""Построение графиков по 5 попыткам"""
|
||
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(12, 5))
|
||
|
||
struct_config = [
|
||
('ll', 'Связный список', 'red', 'o'),
|
||
('ht', 'Хеш-таблица', 'green', 's'),
|
||
('bst', 'Двоичное дерево', 'blue', '^')
|
||
]
|
||
|
||
# Случайный порядок
|
||
for struct, label, color, marker in struct_config:
|
||
times = data[struct]['shuffled']
|
||
x = range(1, len(times) + 1)
|
||
ax1.plot(x, times, marker=marker, color=color, label=label,
|
||
linestyle='--', linewidth=1)
|
||
ax1.scatter(x, times, color=color, s=60, zorder=5)
|
||
|
||
ax1.set_xlabel('Номер попытки')
|
||
ax1.set_ylabel('Время (секунды)')
|
||
ax1.set_title(f'{op_title} – случайный порядок')
|
||
ax1.legend()
|
||
ax1.grid(True, linestyle=':', alpha=0.7)
|
||
|
||
# Отсортированный порядок
|
||
for struct, label, color, marker in struct_config:
|
||
times = data[struct]['sorted']
|
||
x = range(1, len(times) + 1)
|
||
ax2.plot(x, times, marker=marker, color=color, label=label,
|
||
linestyle='--', linewidth=1)
|
||
ax2.scatter(x, times, color=color, s=60, zorder=5)
|
||
|
||
ax2.set_xlabel('Номер попытки')
|
||
ax2.set_ylabel('Время (секунды)')
|
||
ax2.set_title(f'{op_title} – отсортированный порядок')
|
||
ax2.legend()
|
||
ax2.grid(True, linestyle=':', alpha=0.7)
|
||
|
||
plt.tight_layout()
|
||
plt.savefig(f'{op_name}_5attempts.png', dpi=150)
|
||
plt.show()
|
||
print(f" График {op_name}_5attempts.png сохранён")
|
||
|
||
def main():
|
||
print("ЛАБОРАТОРНАЯ РАБОТА №1: СРАВНЕНИЕ СТРУКТУР ДАННЫХ")
|
||
|
||
print("\n1. Генерация тестовых данных...")
|
||
records = generate_records(N)
|
||
random.shuffle(records)
|
||
records_sorted = sorted(records, key=lambda x: x[0])
|
||
print(f" Сгенерировано {N} записей")
|
||
|
||
results = []
|
||
struct_names = {'ll': 'Связный список', 'ht': 'Хеш-таблица', 'bst': 'Двоичное дерево'}
|
||
mode_names = {'shuffled': 'случайный', 'sorted': 'отсортированный'}
|
||
op_names = {'insert': 'Вставка всех записей', 'find': 'Поиск записей', 'delete': 'Удаление записей'}
|
||
|
||
insert_data = {'ll': {}, 'ht': {}, 'bst': {}}
|
||
search_data = {'ll': {}, 'ht': {}, 'bst': {}}
|
||
delete_data = {'ll': {}, 'ht': {}, 'bst': {}}
|
||
|
||
# Вставка
|
||
print("\n2. Тестирование ВСТАВКИ (10000 записей):")
|
||
for struct in ['ll', 'ht', 'bst']:
|
||
print(f"\n {struct_names[struct]}:")
|
||
times_sh = measure_insertion(struct, records)
|
||
times_so = measure_insertion(struct, records_sorted)
|
||
insert_data[struct]['shuffled'] = times_sh
|
||
insert_data[struct]['sorted'] = times_so
|
||
print(f" случайный: {[round(t,6) for t in times_sh]}, среднее = {sum(times_sh)/len(times_sh):.6f}")
|
||
print(f" отсортированный: {[round(t,6) for t in times_so]}, среднее = {sum(times_so)/len(times_so):.6f}")
|
||
results.append([struct_names[struct], mode_names['shuffled'], op_names['insert'], sum(times_sh)/len(times_sh)] + times_sh)
|
||
results.append([struct_names[struct], mode_names['sorted'], op_names['insert'], sum(times_so)/len(times_so)] + times_so)
|
||
|
||
# Поиск
|
||
print("\n3. Тестирование ПОИСКА (110 запросов):")
|
||
for struct in ['ll', 'ht', 'bst']:
|
||
print(f"\n {struct_names[struct]}:")
|
||
structure_sh = build_structure(struct, records)
|
||
times_find_sh = measure_search(struct, structure_sh, records)
|
||
search_data[struct]['shuffled'] = times_find_sh
|
||
print(f" случайный: {[round(t,6) for t in times_find_sh]}, среднее = {sum(times_find_sh)/len(times_find_sh):.6f}")
|
||
results.append([struct_names[struct], mode_names['shuffled'], op_names['find'], sum(times_find_sh)/len(times_find_sh)] + times_find_sh)
|
||
|
||
structure_so = build_structure(struct, records_sorted)
|
||
times_find_so = measure_search(struct, structure_so, records_sorted)
|
||
search_data[struct]['sorted'] = times_find_so
|
||
print(f" отсортированный: {[round(t,6) for t in times_find_so]}, среднее = {sum(times_find_so)/len(times_find_so):.6f}")
|
||
results.append([struct_names[struct], mode_names['sorted'], op_names['find'], sum(times_find_so)/len(times_find_so)] + times_find_so)
|
||
|
||
# Удаление
|
||
print("\n4. Тестирование УДАЛЕНИЯ (50 записей):")
|
||
for struct in ['ll', 'ht', 'bst']:
|
||
print(f"\n {struct_names[struct]}:")
|
||
times_del_sh = measure_deletion(struct, records)
|
||
delete_data[struct]['shuffled'] = times_del_sh
|
||
print(f" случайный: {[round(t,6) for t in times_del_sh]}, среднее = {sum(times_del_sh)/len(times_del_sh):.6f}")
|
||
results.append([struct_names[struct], mode_names['shuffled'], op_names['delete'], sum(times_del_sh)/len(times_del_sh)] + times_del_sh)
|
||
|
||
times_del_so = measure_deletion(struct, records_sorted)
|
||
delete_data[struct]['sorted'] = times_del_so
|
||
print(f" отсортированный: {[round(t,6) for t in times_del_so]}, среднее = {sum(times_del_so)/len(times_del_so):.6f}")
|
||
results.append([struct_names[struct], mode_names['sorted'], op_names['delete'], sum(times_del_so)/len(times_del_so)] + times_del_so)
|
||
|
||
# Сохранение CSV
|
||
print("\n5. Сохранение результатов в CSV...")
|
||
with open("phonebook_results.csv", "w", newline="", encoding="utf-8") as f:
|
||
writer = csv.writer(f)
|
||
writer.writerow(['Структура', 'Режим', 'Операция', 'Среднее', 'Замер1', 'Замер2', 'Замер3', 'Замер4', 'Замер5'])
|
||
writer.writerows(results)
|
||
print(" CSV-файл сохранён: phonebook_results.csv")
|
||
|
||
# Сводная таблица
|
||
print("СВОДНАЯ ТАБЛИЦА РЕЗУЛЬТАТОВ (средние значения)")
|
||
print(f"{'Структура':<20} {'Режим':<15} {'Вставка(с)':<12} {'Поиск(с)':<12} {'Удаление(с)':<12}")
|
||
print("-" * 70)
|
||
|
||
for struct in ['ll', 'ht', 'bst']:
|
||
for mode in ['shuffled', 'sorted']:
|
||
ins_avg = sum(insert_data[struct][mode]) / REPEATS
|
||
sea_avg = sum(search_data[struct][mode]) / REPEATS
|
||
del_avg = sum(delete_data[struct][mode]) / REPEATS
|
||
mode_rus = "случайный" if mode == 'shuffled' else "отсортированный"
|
||
print(f"{struct_names[struct]:<20} {mode_rus:<15} {ins_avg:<12.6f} {sea_avg:<12.6f} {del_avg:<12.6f}")
|
||
|
||
# Построение графиков
|
||
print("\n6. Построение графиков...")
|
||
try:
|
||
plot_bar_charts(insert_data, search_data, delete_data)
|
||
plot_attempts_graphs(insert_data, 'insert', 'Вставка')
|
||
plot_attempts_graphs(search_data, 'search', 'Поиск')
|
||
plot_attempts_graphs(delete_data, 'delete', 'Удаление')
|
||
print("\n Все графики успешно сохранены!")
|
||
except Exception as e:
|
||
print(f" Ошибка при построении графиков: {e}")
|
||
|
||
|