2026-rff_mp/stepinim/lab1_structure/test.py

import sys
sys.setrecursionlimit(30000)

csv_path = '/stepinim/docs/data/lab1_results.csv'

#Связный список
def ll_insert(head, name, phone):
    new_node = {'name': name, 'phone': phone, 'next': None}
    if head is None:
        return new_node

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

def ll_find(head, name):
    curr = head
    while curr:
        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']
    curr = head
    while curr['next']:
        if curr['next']['name'] == name:
            curr['next'] = curr['next']['next']
            return head
        curr = curr['next']
    return head

def ll_list_all(head):
    result = []
    curr = head
    while curr:
        result.append((curr['name'], curr['phone']))
        curr = curr['next']
    result.sort(key=lambda x: x[0])
    return result

#Хэш-таблица
HASH_SIZE = 1009
def _hash_name(name):
    return hash(name) % HASH_SIZE

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

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

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

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

#Двоичное дерево 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):
    curr = root
    while curr:
        if name == curr['name']:
            return curr['phone']
        elif name < curr['name']:
            curr = curr['left']
        else:
            curr = curr['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']:
            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:
            inorder(node['left'])
            result.append((node['name'], node['phone']))
            inorder(node['right'])
    inorder(root)
    return result

# ============================================================
# TECT
# ============================================================

import os
import random
import time
import csv
import pandas as pd
import matplotlib.pyplot as plt

# ============================================================
# ПОДГОТОВКА ПАПОК
# ============================================================

DATA_DIR = os.path.join("docs", "data")
os.makedirs(DATA_DIR, exist_ok=True)

csv_path = os.path.join(DATA_DIR, "lab1_results.csv")
graph_path = os.path.join(DATA_DIR, "lab1_graph.png")

# ============================================================
# ТЕСТОВЫЕ ДАННЫЕ
# ============================================================

random.seed(42)

N = 3000

base_records = [
    (f"User_{i:05d}", f"123-{i:05d}")
    for i in range(N)
]

records_shuffled = base_records.copy()
random.shuffle(records_shuffled)

records_sorted = sorted(base_records, key=lambda x: x[0])

# Поиск
search_existing = [
    name for name, _ in random.sample(base_records, 100)
]

search_nonexist = [
    f"None_{i}"
    for i in range(10)
]

# Удаление
delete_names = [
    name for name, _ in random.sample(base_records, 50)
]

# ============================================================
# СОЗДАНИЕ СТРУКТУР
# ============================================================

def build_structure(records, struct_type):

    if struct_type == "ll":
        structure = None

        for name, phone in records:
            structure = ll_insert(structure, name, phone)

        return structure

    elif struct_type == "ht":
        structure = [None] * HASH_SIZE

        for name, phone in records:
            ht_insert(structure, name, phone)

        return structure

    elif struct_type == "bst":
        structure = None

        for name, phone in records:
            structure = bst_insert(structure, name, phone)

        return structure


# ============================================================
# INSERT
# ============================================================

def measure_insert(records, struct_type):

    start = time.perf_counter()

    build_structure(records, struct_type)

    end = time.perf_counter()

    return end - start


# ============================================================
# SEARCH
# ============================================================

def measure_search(records, struct_type):

    structure = build_structure(records, struct_type)

    start = time.perf_counter()

    if struct_type == "ll":
        for name in search_existing + search_nonexist:
            ll_find(structure, name)

    elif struct_type == "ht":
        for name in search_existing + search_nonexist:
            ht_find(structure, name)

    elif struct_type == "bst":
        for name in search_existing + search_nonexist:
            bst_find(structure, name)

    end = time.perf_counter()

    return end - start


# ============================================================
# DELETE
# ============================================================

def measure_delete(records, struct_type):

    structure = build_structure(records, struct_type)

    start = time.perf_counter()

    if struct_type == "ll":
        for name in delete_names:
            structure = ll_delete(structure, name)

    elif struct_type == "ht":
        for name in delete_names:
            ht_delete(structure, name)

    elif struct_type == "bst":
        for name in delete_names:
            structure = bst_delete(structure, name)

    end = time.perf_counter()

    return end - start


# ============================================================
# ЗАМЕРЫ
# ============================================================

all_data = []

experiments = [
    ("LinkedList", "ll"),
    ("HashTable", "ht"),
    ("BST", "bst")
]

modes = [
    ("shuffled", records_shuffled),
    ("sorted", records_sorted)
]

for struct_name, struct_type in experiments:

    for mode_name, records in modes:

        for rep in range(1, 4):

            insert_time = measure_insert(records, struct_type)

            search_time = measure_search(records, struct_type)

            delete_time = measure_delete(records, struct_type)

            all_data.append([
                struct_name,
                mode_name,
                rep,
                "insert",
                insert_time
            ])

            all_data.append([
                struct_name,
                mode_name,
                rep,
                "search",
                search_time
            ])

            all_data.append([
                struct_name,
                mode_name,
                rep,
                "delete",
                delete_time
            ])

# ============================================================
# CSV
# ============================================================

with open(csv_path, "w", newline="", encoding="utf-8") as f:

    writer = csv.writer(f)

    writer.writerow([
        "Структура",
        "Режим",
        "Повтор",
        "Операция",
        "Время (сек)"
    ])

    writer.writerows(all_data)

print(f"CSV сохранён: {csv_path}")

# ============================================================
# ГРАФИК
# ============================================================

df = pd.read_csv(csv_path)

df_avg = (
    df.groupby(
        ["Структура", "Режим", "Операция"]
    )["Время (сек)"]
    .mean()
    .reset_index()
)

fig, ax = plt.subplots(figsize=(12, 6))

ops = ["insert", "search", "delete"]

x = range(len(ops))

width = 0.12

configs = [
    ("LinkedList", "shuffled"),
    ("LinkedList", "sorted"),
    ("HashTable", "shuffled"),
    ("HashTable", "sorted"),
    ("BST", "shuffled"),
    ("BST", "sorted")
]

for i, (struct, mode) in enumerate(configs):

    subset = df_avg[
        (df_avg["Структура"] == struct)
        &
        (df_avg["Режим"] == mode)
    ]

    times = [
        subset[
            subset["Операция"] == op
        ]["Время (сек)"].values[0]
        for op in ops
    ]

    ax.bar(
        [p + i * width for p in x],
        times,
        width,
        label=f"{struct} ({mode})"
    )

ax.set_xticks([p + 2.5 * width for p in x])

ax.set_xticklabels(ops)

ax.set_ylabel("Среднее время (сек)")

ax.set_title("Сравнение структур данных")

ax.legend(
    bbox_to_anchor=(1.05, 1),
    loc="upper left"
)

plt.tight_layout()

plt.savefig(graph_path)

print(f"График сохранён: {graph_path}")

plt.show()