2026-rff_mp/tseremonnikovaaa/task 1/docs/data/main.py

505 lines
20 KiB
Python
Raw Normal View History

2026-05-22 19:08:31 +00:00
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
2026-05-22 19:59:13 +00:00
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")
2026-05-22 20:11:58 +00:00
def main():
print("ЛАБОРАТОРНАЯ РАБОТА №1: СРАВНЕНИЕ СТРУКТУР ДАННЫХ")
2026-05-22 20:11:58 +00:00
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}")