forked from UNN/2026-rff_mp
405 lines
12 KiB
Python
405 lines
12 KiB
Python
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() |