494 lines
15 KiB
Python
494 lines
15 KiB
Python
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() |