2026-rff_mp/SokolovNE/main.py

import time
import csv
import random
import copy
import os


# ============================================================
# 1. СВЯЗНЫЙ СПИСОК (LinkedList)
# ============================================================

def ll_insert(head, name, phone):
    if head is None:
        return {'name': name, 'phone': phone, 'next': None}

    curr = head
    while curr is not None:
        if curr['name'] == name:
            curr['phone'] = phone
            return head
        curr = curr['next']

    new_node = {'name': name, 'phone': phone, 'next': None}
    curr = head
    while curr['next'] is not None:
        curr = curr['next']
    curr['next'] = new_node
    return head


def ll_find(head, name):
    curr = head
    while curr is not None:
        if curr['name'] == name:
            return curr['phone']
        curr = curr['next']
    return None


def ll_delete(head, name):
    if head is None:
        return None
    if head['name'] == name:
        return head['next']

    prev = head
    curr = head['next']
    while curr is not None:
        if curr['name'] == name:
            prev['next'] = curr['next']
            return head
        prev = curr
        curr = curr['next']
    return head


def ll_list_all(head):
    records = []
    curr = head
    while curr is not None:
        records.append((curr['name'], curr['phone']))
        curr = curr['next']
    records.sort(key=lambda x: x[0])
    return records


# ============================================================
# 2. ХЕШ-ТАБЛИЦА (HashTable)
# ============================================================

def _hash(name, bucket_count):
    return sum(ord(ch) for ch in name) % bucket_count


def ht_create(bucket_count=1000):
    return [None] * bucket_count


def ht_insert(buckets, name, phone):
    idx = _hash(name, len(buckets))
    buckets[idx] = ll_insert(buckets[idx], name, phone)


def ht_find(buckets, name):
    idx = _hash(name, len(buckets))
    return ll_find(buckets[idx], name)


def ht_delete(buckets, name):
    idx = _hash(name, len(buckets))
    buckets[idx] = ll_delete(buckets[idx], name)


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


# ============================================================
# 3. ДВОИЧНОЕ ДЕРЕВО ПОИСКА (BST) — итеративная версия
# ============================================================

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']:
            return current['phone']
        elif name < current['name']:
            current = current['left']
        else:
            current = current['right']
    return None


def bst_min_node(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:
        child = current['right']
    elif current['right'] is None:
        child = current['left']
    else:
        successor_parent = current
        successor = current['right']
        while successor['left'] is not None:
            successor_parent = successor
            successor = successor['left']

        current['name'] = successor['name']
        current['phone'] = successor['phone']

        if successor_parent['left'] is successor:
            successor_parent['left'] = successor['right']
        else:
            successor_parent['right'] = successor['right']
        return root

    if parent is None:
        return child
    if parent['left'] is current:
        parent['left'] = child
    else:
        parent['right'] = child
    return root


def bst_list_all(root):
    result = []
    stack = []
    current = root

    while stack or current is not None:
        while current is not None:
            stack.append(current)
            current = current['left']
        current = stack.pop()
        result.append((current['name'], current['phone']))
        current = current['right']

    return result


# ============================================================
# 4. ГЕНЕРАЦИЯ ТЕСТОВЫХ ДАННЫХ
# ============================================================

def generate_records(N=5000):
    records = [(f"User_{i:05d}", f"phone_{i}") for i in range(N)]
    shuffled = copy.deepcopy(records)
    random.shuffle(shuffled)
    return shuffled, records


# ============================================================
# 5. ЗАМЕРЫ ДЛЯ LINKEDLIST
# ============================================================

def test_linked_list(records_shuffled, records_sorted, results):
    N = len(records_shuffled)

    # Вставка shuffled
    times = []
    for _ in range(5):
        head = None
        start = time.perf_counter()
        for name, phone in records_shuffled:
            head = ll_insert(head, name, phone)
        times.append(time.perf_counter() - start)
    results.append(["LinkedList", "shuffled", "insert", sum(times) / 5] + times)

    # Вставка sorted
    times = []
    for _ in range(5):
        head = None
        start = time.perf_counter()
        for name, phone in records_sorted:
            head = ll_insert(head, name, phone)
        times.append(time.perf_counter() - start)
    results.append(["LinkedList", "sorted", "insert", sum(times) / 5] + times)

    # Подготовка для поиска/удаления
    head = None
    for name, phone in records_shuffled:
        head = ll_insert(head, name, phone)

    # Поиск
    existing = [f"User_{i:05d}" for i in random.sample(range(N), 100)]
    nonexisting = [f"None_{i}" for i in range(10)]
    search_names = existing + nonexisting

    times = []
    for _ in range(5):
        start = time.perf_counter()
        for name in search_names:
            ll_find(head, name)
        times.append(time.perf_counter() - start)
    results.append(["LinkedList", "shuffled", "search", sum(times) / 5] + times)

    # Удаление
    delete_names = [f"User_{i:05d}" for i in random.sample(range(N), 50)]
    times = []
    for _ in range(5):
        head_copy = None
        for name, phone in records_shuffled:
            head_copy = ll_insert(head_copy, name, phone)
        start = time.perf_counter()
        for name in delete_names:
            head_copy = ll_delete(head_copy, name)
        times.append(time.perf_counter() - start)
    results.append(["LinkedList", "shuffled", "delete", sum(times) / 5] + times)


# ============================================================
# 6. ЗАМЕРЫ ДЛЯ ХЕШ-ТАБЛИЦЫ
# ============================================================

def test_hash_table(records_shuffled, records_sorted, results):
    N = len(records_shuffled)
    bucket_count = 1000

    # Вставка shuffled
    times = []
    for _ in range(5):
        buckets = ht_create(bucket_count)
        start = time.perf_counter()
        for name, phone in records_shuffled:
            ht_insert(buckets, name, phone)
        times.append(time.perf_counter() - start)
    results.append(["HashTable", "shuffled", "insert", sum(times) / 5] + times)

    # Вставка sorted
    times = []
    for _ in range(5):
        buckets = ht_create(bucket_count)
        start = time.perf_counter()
        for name, phone in records_sorted:
            ht_insert(buckets, name, phone)
        times.append(time.perf_counter() - start)
    results.append(["HashTable", "sorted", "insert", sum(times) / 5] + times)

    # Подготовка
    buckets = ht_create(bucket_count)
    for name, phone in records_shuffled:
        ht_insert(buckets, name, phone)

    # Поиск
    existing = [f"User_{i:05d}" for i in random.sample(range(N), 100)]
    nonexisting = [f"None_{i}" for i in range(10)]
    search_names = existing + nonexisting

    times = []
    for _ in range(5):
        start = time.perf_counter()
        for name in search_names:
            ht_find(buckets, name)
        times.append(time.perf_counter() - start)
    results.append(["HashTable", "shuffled", "search", sum(times) / 5] + times)

    # Удаление
    delete_names = [f"User_{i:05d}" for i in random.sample(range(N), 50)]
    times = []
    for _ in range(5):
        buckets_copy = ht_create(bucket_count)
        for name, phone in records_shuffled:
            ht_insert(buckets_copy, name, phone)
        start = time.perf_counter()
        for name in delete_names:
            ht_delete(buckets_copy, name)
        times.append(time.perf_counter() - start)
    results.append(["HashTable", "shuffled", "delete", sum(times) / 5] + times)


# ============================================================
# 7. ЗАМЕРЫ ДЛЯ BST
# ============================================================

def test_bst(records_shuffled, records_sorted, results):
    N = len(records_shuffled)

    # Вставка shuffled
    times = []
    for _ in range(5):
        root = None
        start = time.perf_counter()
        for name, phone in records_shuffled:
            root = bst_insert(root, name, phone)
        times.append(time.perf_counter() - start)
    results.append(["BST", "shuffled", "insert", sum(times) / 5] + times)

    # Вставка sorted
    times = []
    for _ in range(5):
        root = None
        start = time.perf_counter()
        for name, phone in records_sorted:
            root = bst_insert(root, name, phone)
        times.append(time.perf_counter() - start)
    results.append(["BST", "sorted", "insert", sum(times) / 5] + times)

    # Подготовка
    root = None
    for name, phone in records_shuffled:
        root = bst_insert(root, name, phone)

    # Поиск
    existing = [f"User_{i:05d}" for i in random.sample(range(N), 100)]
    nonexisting = [f"None_{i}" for i in range(10)]
    search_names = existing + nonexisting

    times = []
    for _ in range(5):
        start = time.perf_counter()
        for name in search_names:
            bst_find(root, name)
        times.append(time.perf_counter() - start)
    results.append(["BST", "shuffled", "search", sum(times) / 5] + times)

    # Удаление
    delete_names = [f"User_{i:05d}" for i in random.sample(range(N), 50)]
    times = []
    for _ in range(5):
        root_copy = None
        for name, phone in records_shuffled:
            root_copy = bst_insert(root_copy, name, phone)
        start = time.perf_counter()
        for name in delete_names:
            root_copy = bst_delete(root_copy, name)
        times.append(time.perf_counter() - start)
    results.append(["BST", "shuffled", "delete", sum(times) / 5] + times)


# ============================================================
# 8. СОХРАНЕНИЕ РЕЗУЛЬТАТОВ В CSV
# ============================================================

def save_results(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(["Structure", "Mode", "Operation", "AvgSec", "Run1", "Run2", "Run3", "Run4", "Run5"])
        for row in results:
            writer.writerow(row)
    print(f"Результаты сохранены в {filename}")


# ============================================================
# 9. ПОСТРОЕНИЕ ГРАФИКОВ
# ============================================================

def plot_results():
    """Построение графиков по результатам из CSV"""
    try:
        import matplotlib.pyplot as plt
        import pandas as pd
    except ImportError:
        print("Библиотеки matplotlib или pandas не установлены. Пропускаем графики.")
        print("Установите: pip install matplotlib pandas")
        return

    try:
        df = pd.read_csv("docs/data/results.csv")
    except FileNotFoundError:
        print("Файл results.csv не найден. Сначала запустите main.py для генерации данных.")
        return

    operations = df["Operation"].unique()

    for op in operations:
        subset = df[df["Operation"] == op]
        plt.figure(figsize=(10, 6))

        labels = [f"{row.Structure}\n({row.Mode})" for _, row in subset.iterrows()]
        values = subset["AvgSec"]

        plt.bar(labels, values, color=['blue', 'orange', 'green', 'red', 'purple', 'brown'])
        plt.title(f"Сравнение времени {op} (5 замеров, N=5000)")
        plt.ylabel("Время (секунды)")
        plt.xticks(rotation=45)
        plt.tight_layout()

        filename = f"docs/graph_{op}.png"
        plt.savefig(filename)
        print(f"Сохранён график: {filename}")
        plt.close()

    print("\nГрафики построены и сохранены в папке docs/")


# ============================================================
# 10. MAIN
# ============================================================

def main():
    print("Генерация тестовых данных (N=5000)...")
    shuffled, sorted_records = generate_records(5000)

    results = []

    print("Тестирование LinkedList...")
    test_linked_list(shuffled, sorted_records, results)

    print("Тестирование HashTable...")
    test_hash_table(shuffled, sorted_records, results)

    print("Тестирование BST...")
    test_bst(shuffled, sorted_records, results)

    save_results(results)

    # Построение графиков
    plot_results()

    print("\nГотово! Файл results.csv и графики сохранены в папке docs/")


if __name__ == "__main__":
    main()