2026-rff_mp/kalinovskiymi/docs/data/task_1.py

import sys

sys.setrecursionlimit(10000)

import time
import random
import csv
import os
import matplotlib.pyplot as plt
import numpy as np


def ll_insert(head, name, phone):
    new_node = {'name': name, 'phone': phone, 'next': None}
    if head is None:
        return new_node
    if head['name'] > name:
        new_node['next'] = head
        return new_node
    current = head
    while current['next'] is not None and current['next']['name'] < name:
        current = current['next']
    if current['name'] == name:
        current['phone'] = phone
        return head
    new_node['next'] = current['next']
    current['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_list_all(head):
    result = []
    current = head
    while current is not None:
        result.append((current['name'], current['phone']))
        current = current['next']
    result.sort(key=lambda x: x[0])
    return result


def ht_insert(buckets, name, phone):
    index = hash(name) % len(buckets)
    buckets[index] = ll_insert(buckets[index], name, phone)


def ht_find(buckets, name):
    index = hash(name) % len(buckets)
    return ll_find(buckets[index], name)


def ht_delete(buckets, name):
    index = hash(name) % len(buckets)
    buckets[index] = ll_delete(buckets[index], name)


def ht_list_all(buckets):
    result = []
    for bucket in buckets:
        if bucket is not None:
            current = bucket
            while current is not None:
                result.append((current['name'], current['phone']))
                current = current['next']
    result.sort(key=lambda x: x[0])
    return result


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


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_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']
        if root['right'] is None:
            return root['left']
        min_node = root['right']
        while min_node['left'] is not None:
            min_node = min_node['left']
        root['name'] = min_node['name']
        root['phone'] = min_node['phone']
        root['right'] = bst_delete(root['right'], min_node['name'])
    return root


def bst_list_all(root):
    result = []

    def inorder(node):
        if node is not None:
            inorder(node['left'])
            result.append((node['name'], node['phone']))
            inorder(node['right'])

    inorder(root)
    return result


def generate_records(n, mode='shuffled'):
    names = [f"User_{i:05d}" for i in range(n)]
    if mode == 'shuffled':
        random.shuffle(names)
    records = [(name, f"Phone_{i}") for i, name in enumerate(names)]
    return records


def benchmark_insert(structure_type, records, buckets_size=512):
    if structure_type == 'LinkedList':
        head = None
        start = time.perf_counter()
        for name, phone in records:
            head = ll_insert(head, name, phone)
        end = time.perf_counter()
        return end - start, head
    elif structure_type == 'HashTable':
        buckets = [None] * buckets_size
        start = time.perf_counter()
        for name, phone in records:
            ht_insert(buckets, name, phone)
        end = time.perf_counter()
        return end - start, buckets
    elif structure_type == 'BST':
        root = None
        start = time.perf_counter()
        for name, phone in records:
            root = bst_insert(root, name, phone)
        end = time.perf_counter()
        return end - start, root


def benchmark_find(structure_type, structure, names):
    start = time.perf_counter()
    if structure_type == 'LinkedList':
        for name in names:
            ll_find(structure, name)
    elif structure_type == 'HashTable':
        for name in names:
            ht_find(structure, name)
    elif structure_type == 'BST':
        for name in names:
            bst_find(structure, name)
    end = time.perf_counter()
    return end - start


def benchmark_delete(structure_type, structure, names):
    start = time.perf_counter()
    if structure_type == 'LinkedList':
        head = structure
        for name in names:
            head = ll_delete(head, name)
        end = time.perf_counter()
        return end - start, head
    elif structure_type == 'HashTable':
        buckets = structure
        for name in names:
            ht_delete(buckets, name)
        end = time.perf_counter()
        return end - start, buckets
    elif structure_type == 'BST':
        root = structure
        for name in names:
            root = bst_delete(root, name)
        end = time.perf_counter()
        return end - start, root


def benchmark_list_all(structure_type, structure):
    start = time.perf_counter()
    if structure_type == 'LinkedList':
        ll_list_all(structure)
    elif structure_type == 'HashTable':
        ht_list_all(structure)
    elif structure_type == 'BST':
        bst_list_all(structure)
    end = time.perf_counter()
    return end - start


def main():
    random.seed(42)
    N = 1000
    REPETITIONS = 5

    all_results = []
    structures = ['LinkedList', 'HashTable', 'BST']
    modes = ['shuffled', 'sorted']

    os.makedirs('docs/data', exist_ok=True)

    for mode in modes:
        records = generate_records(N, mode)
        find_names = [random.choice(records)[0] for _ in range(100)] + [f"None_{i}" for i in range(10)]
        delete_names = [random.choice(records)[0] for _ in range(50)]

        for struct in structures:
            print(f"Тестирую {struct} на {mode} данных...")
            for rep in range(REPETITIONS):
                insert_time, structure = benchmark_insert(struct, records)
                all_results.append([struct, mode, 'insert', insert_time, rep + 1])

                find_time = benchmark_find(struct, structure, find_names)
                all_results.append([struct, mode, 'find', find_time, rep + 1])

                delete_time, _ = benchmark_delete(struct, structure, delete_names)
                all_results.append([struct, mode, 'delete', delete_time, rep + 1])

    with open('docs/data/results.csv', 'w', newline='') as f:
        writer = csv.writer(f)
        writer.writerow(['structure', 'order', 'operation', 'time', 'run'])
        writer.writerows(all_results)

    print("\nCSV сохранён в docs/data/results.csv")

    data = {}
    for row in all_results:
        key = (row[0], row[1], row[2])
        if key not in data:
            data[key] = []
        data[key].append(row[3])

    averaged = []
    for key, times in data.items():
        avg_time = sum(times) / len(times)
        averaged.append([key[0], key[1], key[2], avg_time])

    print("\nУСРЕДНЁННЫЕ РЕЗУЛЬТАТЫ (сек):")
    print(f"{'Структура':<15} {'Режим':<15} {'Операция':<10} {'Среднее время':<15}")
    print("-" * 55)
    for row in sorted(averaged, key=lambda x: (x[0], x[1], x[2])):
        print(f"{row[0]:<15} {row[1]:<15} {row[2]:<10} {row[3]:<15.6f}")

    structures_list = ['LinkedList', 'HashTable', 'BST']
    operations_list = ['insert', 'find', 'delete']

    fig, axes = plt.subplots(1, 3, figsize=(18, 6))

    for i, op in enumerate(operations_list):
        ax = axes[i]
        x = np.arange(len(structures_list))
        width = 0.35

        shuffled_times = []
        sorted_times = []

        for struct in structures_list:
            shuffled_times.append(
                next(row[3] for row in averaged if row[0] == struct and row[1] == 'shuffled' and row[2] == op))
            sorted_times.append(
                next(row[3] for row in averaged if row[0] == struct and row[1] == 'sorted' and row[2] == op))

        bars1 = ax.bar(x - width / 2, shuffled_times, width, label='Случайный', color='#3498db')
        bars2 = ax.bar(x + width / 2, sorted_times, width, label='Отсортированный', color='#e74c3c')

        for bar in bars1:
            height = bar.get_height()
            ax.text(bar.get_x() + bar.get_width() / 2., height + max(shuffled_times) * 0.01,
                    f'{height:.6f}', ha='center', va='bottom', fontsize=7)
        for bar in bars2:
            height = bar.get_height()
            ax.text(bar.get_x() + bar.get_width() / 2., height + max(sorted_times) * 0.01,
                    f'{height:.6f}', ha='center', va='bottom', fontsize=7)

        ax.set_xlabel('Структура данных')
        ax.set_ylabel('Время (сек)')
        ax.set_title(f'Операция: {op}')
        ax.set_xticks(x)
        ax.set_xticklabels(structures_list)
        ax.legend()
        ax.grid(axis='y', alpha=0.3)

        if op == 'find':
            ax.set_yscale('log')

    plt.suptitle(f'Сравнение производительности структур данных (N = {N} записей)',
                 fontsize=14, fontweight='bold')
    plt.tight_layout()

    os.makedirs('docs', exist_ok=True)
    plt.savefig('docs/benchmark_results.png', dpi=150, bbox_inches='tight')
    plt.show()
    print(f"График сохранён в docs/benchmark_results.png")

    print("\nАНАЛИЗ РЕЗУЛЬТАТОВ")

    print("\n1. Влияние порядка данных на BST:")
    bst_shuffled_insert = next(
        row[3] for row in averaged if row[0] == 'BST' and row[1] == 'shuffled' and row[2] == 'insert')
    bst_sorted_insert = next(
        row[3] for row in averaged if row[0] == 'BST' and row[1] == 'sorted' and row[2] == 'insert')
    print(f"   - Случайные данные: {bst_shuffled_insert:.6f} сек")
    print(f"   - Отсортированные данные: {bst_sorted_insert:.6f} сек")
    if bst_shuffled_insert > 0:
        print(f"   - Замедление в {bst_sorted_insert / bst_shuffled_insert:.1f} раз")
    print("   Причина: на отсортированных данных BST вырождается в связный список (глубина = N)")

    print("\n2. Стабильность хеш-таблицы:")
    ht_shuffled = next(
        row[3] for row in averaged if row[0] == 'HashTable' and row[1] == 'shuffled' and row[2] == 'insert')
    ht_sorted = next(row[3] for row in averaged if row[0] == 'HashTable' and row[1] == 'sorted' and row[2] == 'insert')
    print(f"   - Случайные: {ht_shuffled:.6f} сек")
    print(f"   - Отсортированные: {ht_sorted:.6f} сек")
    print("   Причина: хеш-функция равномерно распределяет ключи независимо от порядка")

    print("\n3. Медленный поиск в связном списке:")
    ll_search = next(row[3] for row in averaged if row[0] == 'LinkedList' and row[1] == 'shuffled' and row[2] == 'find')
    ht_search = next(row[3] for row in averaged if row[0] == 'HashTable' and row[1] == 'shuffled' and row[2] == 'find')
    print(f"   - LinkedList: {ll_search:.6f} сек")
    print(f"   - HashTable: {ht_search:.6f} сек")
    if ht_search > 0:
        print(f"   - Хеш-таблица быстрее в {ll_search / ht_search:.1f} раз")
    print("   Причина: поиск в списке всегда O(n), в хеш-таблице ~O(1)")

    print("\n4. Удаление:")
    for label in ['LinkedList', 'HashTable', 'BST']:
        del_shuff = next(row[3] for row in averaged if row[0] == label and row[1] == 'shuffled' and row[2] == 'delete')
        del_sort = next(row[3] for row in averaged if row[0] == label and row[1] == 'sorted' and row[2] == 'delete')
        print(f"   - {label:15}: случ.={del_shuff:.6f} сек, отсорт.={del_sort:.6f} сек")

    print("\n5. Рекомендации:")
    print("   - Частый поиск + вставки → Хеш-таблица")
    print("   - Нужна сортировка «из коробки» → Сбалансированное BST (AVL/Красно-чёрное)")
    print("   - Только добавление в конец → Связный список")
    print("   - Обычный BST опасен на реальных частично упорядоченных данных!")

if __name__ == '__main__':
    main()