2026-rff_mp/BorisovMI/lab_1/docs/data/structures.py

import time
import random
import csv
import os
import matplotlib.pyplot as plt
import numpy as np
import sys
sys.setrecursionlimit(20000) 
# Связный список

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:
        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'] = 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):
    
    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

# Хэш функции

def hash_function(name, table_size):
    return sum(ord(c) for c in name) % table_size


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


def ht_insert(buckets, name, phone):
    size = len(buckets)
    index = hash_function(name, size)
    buckets[index] = ll_insert(buckets[index], name, phone)


def ht_find(buckets, name):
    size = len(buckets)
    index = hash_function(name, size)
    return ll_find(buckets[index], name)


def ht_delete(buckets, name):
    size = len(buckets)
    index = hash_function(name, size)
    buckets[index] = ll_delete(buckets[index], name)


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

# Функции для дерева поиска

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_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_list_all(root):
    
    records = []
    
    def inorder_traversal(node):
        if node is not None:
            inorder_traversal(node['left'])
            records.append((node['name'], node['phone']))
            inorder_traversal(node['right'])
    
    inorder_traversal(root)
    return records

 # Генерация тестовых данных

def generate_records(count=10000):
    
    records = []
    for i in range(count):
        name = f"User_{i:05d}"
        phone = f"+7-{random.randint(100,999)}-{random.randint(100,999)}-{random.randint(1000,9999)}"
        records.append((name, phone))
    
    shuffled = records.copy()
    random.shuffle(shuffled)
    sorted_records = sorted(records, key=lambda x: x[0])
    
    return shuffled, sorted_records



# Замер времени

def measure_insertion(structure_name, records):
    
    times = []
    filled_structure = None
    
    for run in range(5):
        if structure_name == "linked_list":
            structure = None
        elif structure_name == "hash_table":
            structure = ht_create(1000)
        elif structure_name == "bst":
            structure = None
        
        start = time.perf_counter()
        
        for name, phone in records:
            if structure_name == "linked_list":
                structure = ll_insert(structure, name, phone)
            elif structure_name == "hash_table":
                ht_insert(structure, name, phone)
            elif structure_name == "bst":
                structure = bst_insert(structure, name, phone)
        
        end = time.perf_counter()
        times.append(end - start)
        
        if run == 4:
            filled_structure = structure
    
    return times, filled_structure

def measure_search(structure_name, structure, search_names):
    
    times = []
    
    for run in range(5):
        start = time.perf_counter()
        
        for name in search_names:
            if structure_name == "linked_list":
                ll_find(structure, name)
            elif structure_name == "hash_table":
                ht_find(structure, name)
            elif structure_name == "bst":
                bst_find(structure, name)
        
        end = time.perf_counter()
        times.append(end - start)
    
    return times

def measure_deletion(structure_name, original_structure, delete_names):
    
    times = []
    
    for run in range(5):
        if structure_name == "linked_list":
            all_records = ll_list_all(original_structure)
            test_structure = None
            for name, phone in all_records:
                test_structure = ll_insert(test_structure, name, phone)
        
        elif structure_name == "hash_table":
            all_records = ht_list_all(original_structure)
            test_structure = ht_create(1000)
            for name, phone in all_records:
                ht_insert(test_structure, name, phone)
        
        elif structure_name == "bst":
            all_records = bst_list_all(original_structure)
            test_structure = None
            for name, phone in all_records:
                test_structure = bst_insert(test_structure, name, phone)
        
        start = time.perf_counter()
        
        for name in delete_names:
            if structure_name == "linked_list":
                test_structure = ll_delete(test_structure, name)
            elif structure_name == "hash_table":
                ht_delete(test_structure, name)
            elif structure_name == "bst":
                test_structure = bst_delete(test_structure, name)
        
        end = time.perf_counter()
        times.append(end - start)
    
    return times

# Основная часть

def run_experiment():
    
    current_dir = os.path.dirname(__name__)
    docs_dir = os.path.dirname(current_dir)
    csv_file = os.path.join(docs_dir, "experiment_results.csv")
    
    print("=" * 70)
    print("ЭКСПЕРИМЕНТАЛЬНОЕ СРАВНЕНИЕ СТРУКТУР ДАННЫХ")
    print("Телефонный справочник - 10000 записей")
    print("=" * 70)
    print(f"\nРезультаты будут сохранены в: {csv_file}")
    
    print("\n1. Генерация тестовых данных...")
    shuffled_records, sorted_records = generate_records(10000)
    print(f"   Сгенерировано 10000 записей")
    
    existing_names = [shuffled_records[i][0] for i in random.sample(range(10000), 100)]
    nonexisting_names = [f"NotExist_{i}" for i in range(10)]
    search_names = existing_names + nonexisting_names
    delete_names = [shuffled_records[i][0] for i in random.sample(range(10000), 50)]
    
    results = [["Структура", "Режим", "Операция", 
                "Замер1(с)", "Замер2(с)", "Замер3(с)", "Замер4(с)", "Замер5(с)", 
                "Среднее(с)"]]
    
    for mode_name, records in [("случайный", shuffled_records), 
                                ("отсортированный", sorted_records)]:
        
        print(f"\n2. Тестирование режима: {mode_name}")
        print("-" * 50)
        
        for struct_name in ["linked_list", "hash_table", "bst"]:
            print(f"\n   {struct_name.upper()}:")
            
            print("      Вставка 10000 записей...")
            insert_times, filled_struct = measure_insertion(struct_name, records)
            avg_insert = sum(insert_times) / 5
            print(f"      Время: {avg_insert:.4f} сек (среднее)")
            
            print("      Поиск 110 записей...")
            search_times = measure_search(struct_name, filled_struct, search_names)
            avg_search = sum(search_times) / 5
            print(f"      Время: {avg_search:.4f} сек (среднее)")
            
            print("      Удаление 50 записей...")
            delete_times = measure_deletion(struct_name, filled_struct, delete_names)
            avg_delete = sum(delete_times) / 5
            print(f"      Время: {avg_delete:.4f} сек (среднее)")
            
            results.append([struct_name, mode_name, "вставка"] + insert_times + [avg_insert])
            results.append([struct_name, mode_name, "поиск"] + search_times + [avg_search])
            results.append([struct_name, mode_name, "удаление"] + delete_times + [avg_delete])
    
    print("\n3. Сохранение результатов...")
    with open(csv_file, "w", newline="", encoding="utf-8") as f:
        writer = csv.writer(f)
        writer.writerows(results)
    print(f"   Результаты сохранены в: {csv_file}")
    
    print("\n" + "=" * 70)
    print("СВОДНАЯ ТАБЛИЦА РЕЗУЛЬТАТОВ")
    print("=" * 70)
    print(f"{'Структура':<15} {'Режим':<12} {'Операция':<10} {'Среднее время (сек)':<20}")
    print("-" * 70)
    
    for row in results[1:]:
        struct, mode, op, t1, t2, t3, t4, t5, avg = row
        print(f"{struct:<15} {mode:<12} {op:<10} {avg:<20.6f}")
    
    return results, docs_dir

# Графики

def create_graphs(results, docs_dir):
    
    print("\n4. Построение графиков...")
    
    data = {}
    for row in results[1:]:
        struct = row[0]
        mode = row[1]
        op = row[2]
        avg = row[8]
        
        if struct not in data:
            data[struct] = {}
        if mode not in data[struct]:
            data[struct][mode] = {}
        data[struct][mode][op] = avg
    
    
    struct_labels = {
        'linked_list': 'LinkedList',
        'hash_table': 'HashTable',
        'bst': 'BST'
    }
    
    
    colors = {
        'linked_list': '#3498db',  
        'hash_table': '#2ecc71',   
        'bst': '#e74c3c'            
    }
    
    
    fig, axes = plt.subplots(1, 3, figsize=(15, 6))
    fig.suptitle('Сравнение производительности структур данных', fontsize=16, fontweight='bold')
    
    operations = ['вставка', 'поиск', 'удаление']
    operation_titles = ['Вставка\n(10000 записей)', 'Поиск\n(110 запросов)', 'Удаление\n(50 записей)']
    modes = ['случайный', 'отсортированный']
    mode_labels = ['Случайный', 'Отсортированный']
    
    for idx, (op, op_title) in enumerate(zip(operations, operation_titles)):
        ax = axes[idx]
        
        # Позиции для групп столбцов
        x = np.arange(len(modes))  # [0, 1]
        width = 0.25  # ширина одного столбца
        multiplier = 0
        
        for struct in ['linked_list', 'hash_table', 'bst']:
            values = [data[struct][mode][op] for mode in modes]
            offset = width * multiplier
            bars = ax.bar(x + offset, values, width, 
                         label=struct_labels[struct], 
                         color=colors[struct],
                         edgecolor='black', linewidth=0.5)
            
            
            for bar, val in zip(bars, values):
                if val < 0.01:
                    ax.text(bar.get_x() + bar.get_width()/2, bar.get_height() + val*0.05, 
                           f'{val:.5f}', ha='center', va='bottom', fontsize=8, rotation=0)
                else:
                    ax.text(bar.get_x() + bar.get_width()/2, bar.get_height() + val*0.02, 
                           f'{val:.4f}', ha='center', va='bottom', fontsize=8, rotation=0)
            
            multiplier += 1
        
        
        ax.set_title(op_title, fontsize=12, fontweight='bold')
        ax.set_ylabel('Время (секунды)', fontsize=10)
        ax.set_xlabel('Режим данных', fontsize=10)
        ax.set_xticks(x + width)
        ax.set_xticklabels(mode_labels)
        ax.legend(loc='upper left', fontsize=8)
        ax.grid(True, alpha=0.3, axis='y')
        
        
        all_values = [data[s][m][op] for s in ['linked_list', 'hash_table', 'bst'] for m in modes]
        if max(all_values) / min(all_values) > 100:
            ax.set_yscale('log')
            ax.set_ylabel('Время (секунды) - логарифмическая шкала', fontsize=9)
    
    plt.tight_layout()
    graph_path = os.path.join(docs_dir, "performance_graphs.png")
    plt.savefig(graph_path, dpi=150, bbox_inches='tight')
    plt.close()
    print(f"   Графики сохранены в: {graph_path}")
    
    return graph_path



if __name__ == "__main__":
    
    results, docs_dir = run_experiment()
    
    
    try:
        graph_file = create_graphs(results, docs_dir)
        
        print("\n" + "=" * 70)
        print("ЭКСПЕРИМЕНТ ЗАВЕРШЕН УСПЕШНО!")
        print("=" * 70)
        print("\nСОЗДАННЫЕ ФАЙЛЫ:")
        print(f"   Данные: {os.path.join(docs_dir, 'experiment_results.csv')}")
        print(f"   Графики: {graph_file}")
        
    except Exception as e:
        print(f"\nОшибка при построении графиков: {e}")
        print("   Убедитесь, что установлен matplotlib: pip install matplotlib")
        print("\n" + "=" * 70)
        print("ЭКСПЕРИМЕНТ ЗАВЕРШЕН (без графиков)")
        print("=" * 70)
        print(f"\nCSV файл сохранен: {os.path.join(docs_dir, 'experiment_results.csv')}")