2026-rff_mp/sorokinfi/427.md

import csv
import random
import sys
import time
from collections import defaultdict

# увеличиваем лимит рекурсии
sys.setrecursionlimit(25000)


# 1. связный список, узел: {'name': 'Имя', 'phone': '123', 'next': None}

# проходит до конца и добавляет в конец
def ll_insert(head, name, phone):
    new_node = {'name': name, 'phone': phone, 'next': None}
    if head is None:
        return new_node
    current = head
    while current['next'] is not None:
        current = current['next']
    current['next'] = new_node
    return head

# ищет узел, возвращает телефон или None
def ll_find(head, name):
    current = head
    while current is not None:
        if current['name'] == name:
            return current['phone']
        current = current['next']
    return None

# удаляет узел, возвращает новую голову
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

#  собирает все записи в список и сортирует
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


# 2. хеш-таблица

# хеш-функция для вычисления бекета
def ht_hash(name, size):
    return hash(name) % size

# вычисляет индекс, вызывает ll_insert для соответствующего бакета
def ht_insert(buckets, name, phone):
    size = len(buckets)
    idx = ht_hash(name, size)
    buckets[idx] = ll_insert(buckets[idx], name, phone)

# поиск по хеш-таблице
def ht_find(buckets, name):
    size = len(buckets)
    idx = ht_hash(name, size)
    return ll_find(buckets[idx], name)

# удаление из хеш-таблицы
def ht_delete(buckets, name):
    size = len(buckets)
    idx = ht_hash(name, size)
    buckets[idx] = ll_delete(buckets[idx], name)

# собирает все записи из всех бакетов и сортирует
def ht_list_all(buckets):
    all_records = []
    for head in buckets:
        current = head
        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


# 3. двоичное дерево поиска
# узел — словарь: {'name': 'Имя', 'phone': '123', 'left': None, 'right': None}

# рекурсивно или итеративно вставляет, возвращает новый корень (если корень меняется)
def bst_insert(root, name, phone):
    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:
        root['phone'] = phone
    return root

# поиск
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)
    
# удаление, возвращает новый корень
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:
        # одна ветвь или её отсутствие
        if root['left'] is None:
            return root['right']
        if root['right'] is None:
            return root['left']
        # две ветви
        successor = root['right']
        while successor['left'] is not None:
            successor = successor['left']
            
        root['name'] = successor['name']
        root['phone'] = successor['phone']
        root['right'] = bst_delete(root['right'], successor['name'])
        
    return root

# центрированный обход (рекурсивно собирает записи в отсортированном порядке)
def bst_list_all(root):
    records = []
    def _inorder(node):
        if node is not None:
            _inorder(node['left'])
            records.append((node['name'], node['phone']))
            _inorder(node['right'])
    _inorder(root)
    return records


# ЭКСПЕРИМЕНТАЛЬНАЯ ЧАСТЬ

def run_experiments():
    N = 3000 
    HASH_SIZE = 1007
    
    print(f"генерация тестовых данных для N = {N}...")
    records_sorted = [(f"User_{i:05d}", f"+7999123{i:04d}") for i in range(N)]
    records_shuffled = records_sorted.copy()
    random.seed(42)
    random.shuffle(records_shuffled)
    
    # подготовка выборок 
    existing_sample = [r[0] for r in random.sample(records_sorted, min(100, N))]
    non_existing_sample = [f"None_{i}" for i in range(10)]
    search_names = existing_sample + non_existing_sample
     
    delete_names = [r[0] for r in random.sample(records_sorted, min(50, N))]
    csv_rows = [["структура", "режим", "операция", "повторение", "время (сек)"]]
    modes = [("случайный", records_shuffled), ("отсортированный", records_sorted)]
    
    print("запуск экспериментов (5 повторений для каждого режима)")

# ТЕСТ: СВЯЗНЫЙ СПИСОК

    for mode_name, data in modes:
        for rep in range(1, 6):
            head = None
            t_start = time.perf_counter()
            for name, phone in data:
                head = ll_insert(head, name, phone)
            t_end = time.perf_counter()
            csv_rows.append(["LinkedList", mode_name, "вставка", rep, t_end - t_start])
            
            t_start = time.perf_counter()
            for name in search_names:
                ll_find(head, name)
            t_end = time.perf_counter()
            csv_rows.append(["LinkedList", mode_name, "поиск", rep, t_end - t_start])
            
            t_start = time.perf_counter()
            for name in delete_names:
                head = ll_delete(head, name)
            t_end = time.perf_counter()
            csv_rows.append(["LinkedList", mode_name, "удаление", rep, t_end - t_start])

# ТЕСТ: ХЕШ-ТАБЛИЦА

    for mode_name, data in modes:
        for rep in range(1, 6):
            buckets = [None] * HASH_SIZE
            t_start = time.perf_counter()
            for name, phone in data:
                ht_insert(buckets, name, phone)
            t_end = time.perf_counter()
            csv_rows.append(["HashTable", mode_name, "вставка", rep, t_end - t_start])
            
            t_start = time.perf_counter()
            for name in search_names:
                ht_find(buckets, name)
            t_end = time.perf_counter()
            csv_rows.append(["HashTable", mode_name, "поиск", rep, t_end - t_start])
            
            t_start = time.perf_counter()
            for name in delete_names:
                ht_delete(buckets, name)
            t_end = time.perf_counter()
            csv_rows.append(["HashTable", mode_name, "удаление", rep, t_end - t_start])

# ТЕСТ: ДЕРЕВО ПОИСКА (BST)

    for mode_name, data in modes:
        for rep in range(1, 6):
            root = None
            t_start = time.perf_counter()
            for name, phone in data:
                root = bst_insert(root, name, phone)
            t_end = time.perf_counter()
            csv_rows.append(["BST", mode_name, "вставка", rep, t_end - t_start])
            
            t_start = time.perf_counter()
            for name in search_names:
                bst_find(root, name)
            t_end = time.perf_counter()
            csv_rows.append(["BST", mode_name, "поиск", rep, t_end - t_start])
            
            t_start = time.perf_counter()
            for name in delete_names:
                root = bst_delete(root, name)
            t_end = time.perf_counter()
            csv_rows.append(["BST", mode_name, "удаление", rep, t_end - t_start])

# сохранение в csv
    with open("results.csv", "w", newline="", encoding="utf-8") as f:
        writer = csv.writer(f)
        writer.writerows(csv_rows)
    print("\nвсе замеры сохранены в файл 'results.csv'.")
    
    show_summary(csv_rows)

# функция для подсчета и вывода среднего времени
def show_summary(rows):
    summary = defaultdict(list)
    for row in rows[1:]:
        struct, mode, op, rep, elapsed = row
        summary[(struct, mode, op)].append(elapsed)

    print("\nСВОДНЫЕ РЕЗУЛЬТАТЫ (СРЕДНЕЕ ВРЕМЯ ИЗ 5 ЗАПУСКОВ)")
    print(f"{'структура':<12} | {'режим данных':<15} | {'операция':<10} | {'время (сек)':<12}")
    print("-" * 59)
    for (struct, mode, op), times in sorted(summary.items()):
        avg_time = sum(times) / len(times)
        print(f"{struct:<12} | {mode:<15} | {op:<10} | {avg_time:.6f}")


if __name__ == "__main__":
    run_experiments()