[2] добавлен main.py

SokolovNE/main.py

@@ -0,0 +1,494 @@
+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()