This commit is contained in:
Андрей Мочалов 2026-05-19 21:21:14 +03:00
parent d2b04e6f0e
commit 2670cbf971
5 changed files with 725 additions and 0 deletions

View File

@ -0,0 +1,405 @@
import time
import random
import csv
import os
def create_node(name, phone):
return {'name': name, 'phone': phone, 'next': None}
def ll_insert(head, name, phone):
if head is None:
return create_node(name, phone)
if head['name'] == name:
head['phone'] = phone
return head
current = head
while current['next'] is not None:
if current['next']['name'] == name:
current['next']['phone'] = phone
return head
current = current['next']
current['next'] = create_node(name, phone)
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
def hash_function(name, table_size):
hash_value = 0
for char in name:
hash_value = (hash_value * 31 + ord(char)) % table_size
return hash_value
def create_hash_table(size=1000):
return [None] * size
def ht_insert(buckets, name, phone):
index = hash_function(name, len(buckets))
buckets[index] = ll_insert(buckets[index], name, phone)
return buckets
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)
return buckets
def ht_list_all(buckets):
all_records = []
for bucket in buckets:
if bucket is not None:
records = ll_list_all(bucket)
all_records.extend(records)
all_records.sort(key=lambda x: x[0])
return all_records
def bst_create_node(name, phone):
return {
'name': name,
'phone': phone,
'left': None,
'right': None
}
def bst_insert(root, name, phone):
if root is None:
return bst_create_node(name, phone)
current = root
while True:
if name < current['name']:
if current['left'] is None:
current['left'] = bst_create_node(name, phone)
return root
current = current['left']
elif name > current['name']:
if current['right'] is None:
current['right'] = bst_create_node(name, phone)
return root
current = current['right']
else:
current['phone'] = phone
return root
def bst_find(root, name):
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):
if root is None:
return None
if name < root['name']:
root['left'] = bst_delete(root['left'], name)
return root
elif name > root['name']:
root['right'] = bst_delete(root['right'], name)
return root
if root['left'] is None:
return root['right']
elif root['right'] is None:
return root['left']
min_node = bst_find_min(root['right'])
root['name'] = min_node['name']
root['phone'] = min_node['phone']
root['right'] = bst_delete(root['right'], min_node['name'])
return root
def bst_inorder_collect(root, records):
stack = []
current = root
while stack or current:
while current is not None:
stack.append(current)
current = current['left']
current = stack.pop()
records.append((current['name'], current['phone']))
current = current['right']
def bst_list_all(root):
records = []
bst_inorder_collect(root, records)
return records
def generate_test_data(n=1000):
names = []
for i in range(n):
name = f"User_{i:06d}"
phone = f"+7-999-{random.randint(1000000, 9999999)}"
names.append((name, phone))
shuffled = names.copy()
random.shuffle(shuffled)
sorted_records = sorted(names, key=lambda x: x[0])
return shuffled, sorted_records
def run_insert_benchmark(struct_type, data, struct_params=None):
if struct_type == "LinkedList":
head = None
start = time.perf_counter()
for name, phone in data:
head = ll_insert(head, name, phone)
end = time.perf_counter()
return end - start, head
elif struct_type == "HashTable":
size = struct_params.get('size', 1000) if struct_params else 1000
buckets = create_hash_table(size)
start = time.perf_counter()
for name, phone in data:
buckets = ht_insert(buckets, name, phone)
end = time.perf_counter()
return end - start, buckets
elif struct_type == "BST":
root = None
start = time.perf_counter()
for name, phone in data:
root = bst_insert(root, name, phone)
end = time.perf_counter()
return end - start, root
def run_find_benchmark(struct, struct_type, existing_names, non_existing_names):
start = time.perf_counter()
for name in existing_names:
if struct_type == "LinkedList":
result = ll_find(struct, name)
elif struct_type == "HashTable":
result = ht_find(struct, name)
elif struct_type == "BST":
result = bst_find(struct, name)
for name in non_existing_names:
if struct_type == "LinkedList":
result = ll_find(struct, name)
elif struct_type == "HashTable":
result = ht_find(struct, name)
elif struct_type == "BST":
result = bst_find(struct, name)
end = time.perf_counter()
return end - start
def run_delete_benchmark(struct, struct_type, names_to_delete):
start = time.perf_counter()
for name in names_to_delete:
if struct_type == "LinkedList":
struct = ll_delete(struct, name)
elif struct_type == "HashTable":
struct = ht_delete(struct, name)
elif struct_type == "BST":
struct = bst_delete(struct, name)
end = time.perf_counter()
return end - start, struct
def run_experiment(n_records=1000, n_find=100, n_delete=50, n_repeats=3):
print("Генерация тестовых данных...")
shuffled_data, sorted_data = generate_test_data(n_records)
all_names = [name for name, _ in shuffled_data]
find_names = random.sample(all_names, min(n_find, len(all_names)))
delete_names = random.sample(all_names, min(n_delete, len(all_names)))
non_existing = [f"None_{i}" for i in range(10)]
results = []
structures = ["LinkedList", "HashTable", "BST"]
modes = ["random", "sorted"]
print("\nНачало эксперимента...")
print("=" * 80)
for struct_type in structures:
for mode in modes:
data = shuffled_data if mode == "random" else sorted_data
mode_rus = "случайный" if mode == "random" else "отсортированный"
print(f"\nТестирование: {struct_type}, режим: {mode_rus}")
for repeat in range(n_repeats):
print(f" Повторение {repeat + 1}/{n_repeats}")
insert_time, struct = run_insert_benchmark(
struct_type, data,
{'size': n_records} if struct_type == "HashTable" else None
)
results.append([
struct_type, mode_rus, "вставка", repeat + 1, insert_time
])
find_time = run_find_benchmark(
struct, struct_type, find_names, non_existing
)
results.append([
struct_type, mode_rus, "поиск", repeat + 1, find_time
])
delete_time, struct = run_delete_benchmark(
struct, struct_type, delete_names
)
results.append([
struct_type, mode_rus, "удаление", repeat + 1, delete_time
])
return results
def save_results_to_csv(results, filename="docs/data/results.csv"):
os.makedirs("docs/data", exist_ok=True)
with open(filename, 'w', newline='', encoding='utf-8') as f:
writer = csv.writer(f)
writer.writerow(["Структура", "Режим", "Операция", "Повторение", "Время (сек)"])
writer.writerows(results)
print(f"\nРезультаты сохранены в {filename}")
def print_statistics(results):
print("\n" + "=" * 80)
print("СТАТИСТИКА РЕЗУЛЬТАТОВ")
print("=" * 80)
stats = {}
for row in results:
struct, mode, op, _, time_val = row
key = (struct, mode, op)
if key not in stats:
stats[key] = []
stats[key].append(time_val)
for (struct, mode, op), times in stats.items():
avg_time = sum(times) / len(times)
min_time = min(times)
max_time = max(times)
print(f"\n{struct} - {mode} - {op}:")
print(f" Среднее: {avg_time:.6f} сек")
print(f" Мин: {min_time:.6f} сек")
print(f" Макс: {max_time:.6f} сек")
def verify_correctness():
print("\n" + "=" * 80)
print("ПРОВЕРКА КОРРЕКТНОСТИ РАБОТЫ")
print("=" * 80)
test_data = [
("Alice", "123-456"),
("Bob", "789-012"),
("Charlie", "345-678"),
("Alice", "999-999"),
]
structures = {
"LinkedList": (None, ll_insert, ll_find, ll_delete, ll_list_all),
"HashTable": (create_hash_table(10), ht_insert, ht_find, ht_delete, ht_list_all),
"BST": (None, bst_insert, bst_find, bst_delete, bst_list_all)
}
for name, (struct, insert_func, find_func, delete_func, list_func) in structures.items():
print(f"\n{name}:")
for n, p in test_data:
struct = insert_func(struct, n, p)
print(f" Поиск Alice: {find_func(struct, 'Alice')}")
print(f" Поиск Bob: {find_func(struct, 'Bob')}")
print(f" Поиск Unknown: {find_func(struct, 'Unknown')}")
struct = delete_func(struct, "Bob")
print(f" После удаления Bob: {find_func(struct, 'Bob')}")
all_records = list_func(struct)
print(f" Все записи: {all_records}")
def main():
print("ТЕЛЕФОННЫЙ СПРАВОЧНИК - СРАВНЕНИЕ СТРУКТУР ДАННЫХ")
print("=" * 80)
verify_correctness()
print("\n" + "=" * 80)
print("ЗАПУСК ЭКСПЕРИМЕНТА")
print("=" * 80)
N_RECORDS = 1000
N_FIND = 100
N_DELETE = 50
N_REPEATS = 3
print(f"\nПараметры эксперимента:")
print(f" Количество записей: {N_RECORDS}")
print(f" Поиск: {N_FIND} существующих + 10 отсутствующих")
print(f" Удаление: {N_DELETE} записей")
print(f" Повторений: {N_REPEATS}")
results = run_experiment(N_RECORDS, N_FIND, N_DELETE, N_REPEATS)
save_results_to_csv(results)
print_statistics(results)
print("\n" + "=" * 80)
print("ЭКСПЕРИМЕНТ ЗАВЕРШЕН")
print("=" * 80)
if __name__ == "__main__":
main()

View File

@ -0,0 +1,70 @@
def bst_create_node(name, phone):
return {
'name': name,
'phone': phone,
'left': None,
'right': None
}
def bst_insert(root, name, phone):
if root is None:
return bst_create_node(name, phone)
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
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)
def bst_find_min(node):
current = node
while current['left'] is not None:
current = current['left']
return current
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:
if root['left'] is None:
return root['right']
elif root['right'] is None:
return root['left']
min_node = bst_find_min(root['right'])
root['name'] = min_node['name']
root['phone'] = min_node['phone']
root['right'] = bst_delete(root['right'], min_node['name'])
return root
def bst_inorder_collect(root, records):
if root is not None:
bst_inorder_collect(root['left'], records)
records.append((root['name'], root['phone']))
bst_inorder_collect(root['right'], records)
def bst_list_all(root):
records = []
bst_inorder_collect(root, records)
return records

View File

@ -0,0 +1,35 @@
from src.linked_list_phonebook import ll_insert, ll_find, ll_delete, ll_list_all
def hash_function(name, table_size):
hash_value = 0
for char in name:
hash_value = (hash_value * 31 + ord(char)) % table_size
return hash_value
def create_hash_table(size=1000):
return [None] * size
def ht_insert(buckets, name, phone):
index = hash_function(name, len(buckets))
buckets[index] = ll_insert(buckets[index], name, phone)
return buckets
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)
return buckets
def ht_list_all(buckets):
all_records = []
for bucket in buckets:
if bucket is not None:
records = ll_list_all(bucket)
all_records.extend(records)
all_records.sort(key=lambda x: x[0])
return all_records

View File

@ -0,0 +1,55 @@
def create_node(name, phone):
return {'name': name, 'phone': phone, 'next': None}
def ll_insert(head, name, phone):
if head is None:
return create_node(name, phone)
if head['name'] == name:
head['phone'] = phone
return head
current = head
while current['next'] is not None:
if current['next']['name'] == name:
current['next']['phone'] = phone
return head
current = current['next']
current['next'] = create_node(name, phone)
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

View File

@ -0,0 +1,160 @@
import matplotlib.pyplot as plt
import csv
import numpy as np
import os
plt.rcParams['font.size'] = 10
plt.rcParams['font.family'] = 'sans-serif'
def plot_results(csv_file="docs/data/results.csv"):
if not os.path.exists(csv_file):
print(f"Файл {csv_file} не найден. Сначала запустите benchmark.py")
return
data = {}
with open(csv_file, 'r', encoding='utf-8') as f:
reader = csv.reader(f)
next(reader)
for row in reader:
if len(row) < 5:
continue
struct, mode, op, _, time_val = row
try:
time_val = float(time_val)
except:
continue
if struct not in data:
data[struct] = {}
if mode not in data[struct]:
data[struct][mode] = {}
if op not in data[struct][mode]:
data[struct][mode][op] = []
data[struct][mode][op].append(time_val)
operations = ['вставка', 'поиск', 'удаление']
op_names = ['Вставка', 'Поиск', 'Удаление']
structures = ['LinkedList', 'HashTable', 'BST']
modes = ['случайный', 'отсортированный']
colors = {'LinkedList': '#3498db', 'HashTable': '#2ecc71', 'BST': '#e74c3c'}
fig, axes = plt.subplots(1, 3, figsize=(14, 5))
fig.suptitle('Сравнение производительности структур данных\n(500 записей, 3 повторения)', fontsize=14, fontweight='bold')
for idx, (op, op_name) in enumerate(zip(operations, op_names)):
ax = axes[idx]
x_positions = []
labels = []
values = []
errors = []
colors_list = []
position = 0
for struct in structures:
for mode in modes:
if struct in data and mode in data[struct] and op in data[struct][mode]:
times = data[struct][mode][op]
if times:
avg_time = np.mean(times)
std_time = np.std(times) if len(times) > 1 else 0
x_positions.append(position)
labels.append(f'{struct}\n({mode[:4]})')
values.append(avg_time)
errors.append(std_time)
colors_list.append(colors[struct])
position += 1
bars = ax.bar(x_positions, values, yerr=errors, capsize=5, color=colors_list, alpha=0.8, edgecolor='black', linewidth=0.5)
ax.set_xticks(x_positions)
ax.set_xticklabels(labels, fontsize=8, rotation=45, ha='right')
ax.set_ylabel('Время (секунды)', fontsize=10)
ax.set_title(f'{op_name}', fontsize=12, fontweight='bold')
ax.grid(True, alpha=0.3, axis='y')
for bar, val in zip(bars, values):
if val > 0:
height = bar.get_height()
ax.text(bar.get_x() + bar.get_width()/2., height + max(values)*0.02,
f'{val:.4f}', ha='center', va='bottom', fontsize=7, rotation=0)
plt.tight_layout()
plt.savefig('docs/data/performance_graphs.png', dpi=300, bbox_inches='tight')
plt.show()
fig2, ax2 = plt.subplots(figsize=(10, 6))
fig2.suptitle('Влияние порядка данных на производительность BST', fontsize=14, fontweight='bold')
if 'BST' in data:
bst_data = data['BST']
x_pos = []
labels = []
random_vals = []
sorted_vals = []
for idx, op in enumerate(operations):
random_time = 0
sorted_time = 0
if 'случайный' in bst_data and op in bst_data['случайный']:
random_time = np.mean(bst_data['случайный'][op])
if 'отсортированный' in bst_data and op in bst_data['отсортированный']:
sorted_time = np.mean(bst_data['отсортированный'][op])
x_pos.append(idx)
x_pos.append(idx + 0.35)
labels.append(op)
random_vals.append(random_time)
sorted_vals.append(sorted_time)
width = 0.35
bars1 = ax2.bar([i - width/2 for i in range(len(operations))], random_vals, width,
label='Случайный порядок', color='#2ecc71', alpha=0.8, edgecolor='black')
bars2 = ax2.bar([i + width/2 for i in range(len(operations))], sorted_vals, width,
label='Отсортированный порядок', color='#e74c3c', alpha=0.8, edgecolor='black')
ax2.set_xticks(range(len(operations)))
ax2.set_xticklabels(['Вставка', 'Поиск', 'Удаление'], fontsize=10)
ax2.set_ylabel('Время (секунды)', fontsize=10)
ax2.set_xlabel('Операция', fontsize=10)
ax2.legend(fontsize=10)
ax2.grid(True, alpha=0.3, axis='y')
for bar, val in zip(bars1, random_vals):
if val > 0:
ax2.text(bar.get_x() + bar.get_width()/2., bar.get_height() + max(random_vals + sorted_vals)*0.02,
f'{val:.4f}', ha='center', va='bottom', fontsize=8)
for bar, val in zip(bars2, sorted_vals):
if val > 0:
ax2.text(bar.get_x() + bar.get_width()/2., bar.get_height() + max(random_vals + sorted_vals)*0.02,
f'{val:.4f}', ha='center', va='bottom', fontsize=8)
plt.tight_layout()
plt.savefig('docs/data/bst_comparison.png', dpi=300, bbox_inches='tight')
plt.show()
print("\n" + "="*60)
print("ИТОГОВАЯ ТАБЛИЦА РЕЗУЛЬТАТОВ")
print("="*60)
print(f"{'Структура':<15} {'Режим':<12} {'Вставка':<12} {'Поиск':<12} {'Удаление':<12}")
print("-"*60)
for struct in structures:
for mode in modes:
if struct in data and mode in data[struct]:
insert_times = data[struct][mode].get('вставка', [0])
find_times = data[struct][mode].get('поиск', [0])
delete_times = data[struct][mode].get('удаление', [0])
insert_avg = np.mean(insert_times) if insert_times else 0
find_avg = np.mean(find_times) if find_times else 0
delete_avg = np.mean(delete_times) if delete_times else 0
print(f"{struct:<15} {mode:<12} {insert_avg:<12.6f} {find_avg:<12.6f} {delete_avg:<12.6f}")
print("="*60)
if __name__ == "__main__":
plot_results()