UNN/2026-rff_mp
16
14
Fork 113
Code Issues Pull Requests 21 Actions Packages Projects Releases Wiki Activity

add test for HashTable and BinaryTree, bug fix

Browse Source
This commit is contained in:
4eker 2026-05-10 13:00:19 +03:00
parent 247e9a1224
commit fccea76cef
2 changed files with 379 additions and 58 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

60
pomelovsd/DataStruct/BinaryTree.py
View File

@ -1,53 +1,59 @@
def create_node(name,phone): def create_node(name, phone):
return {"name": name, "phone": phone, "left": None, "right": None} return {"name": name, "phone": phone, "left": None, "right": None}
def bst_insert(root, name, phone): def bst_insert(root, name, phone):
# Случай, если нет узлов
if root is None: if root is None:
return create_node(name, phone) return create_node(name, phone)
# Случай, если узел слева if name < root["name"]:
elif name < root["name"]:
root["left"] = bst_insert(root["left"], name, phone) root["left"] = bst_insert(root["left"], name, phone)
# Случай, если узел справа
elif name > root["name"]: elif name > root["name"]:
root["right"] = bst_insert(root["right"], name, phone) root["right"] = bst_insert(root["right"], name, phone)
# Случай, если мы перезаписываем узел
else: else:
root["phone"] = phone root["phone"] = phone
return root return root
def bst_insert_sort(sorted_data, left, right):
if left > right:
return None
mid = (left + right) // 2
name, phone = sorted_data[mid]
root = create_node(name, phone)
root["left"] = bst_insert_sort(sorted_data, left, mid - 1)
root["right"] = bst_insert_sort(sorted_data, mid + 1, right)
return root
def bst_find(root, name): def bst_find(root, name):
if root is None: if root is None:
return None return None
elif root == root["name"]: if name == root["name"]:
return root["phone"] return root["phone"]
elif root < root["name"]: if name < root["name"]:
return bst_find(root["left"], name) return bst_find(root["left"], name)
else: return bst_find(root["right"], name)
return bst_find(root["right"],name)
def bst_delete(root, name): def bst_delete(root, name):
if root is None: if root is None:
return None return None
elif root < root["name"]:
return bst_delete(root["left"], name) if name < root["name"]:
elif root > root["name"]: root["left"] = bst_delete(root["left"], name)
return bst_delete(root["right"], name) elif name > root["name"]:
# Узел, который надо удалить root["right"] = bst_delete(root["right"], name)
else: else:
# Если нет потомков # Нет детей или только один ребенок
if (root["left"] and root["right"]) is None:
return None
# Если есть только левый потомок
if root["left"] is None: if root["left"] is None:
return root["right"] return root["right"]
# Если есть только правый потомок
if root["right"] is None: if root["right"] is None:
return root["left"] return root["left"]
if (root["left"] or root["right"]) is None:
while current and current['left']: # Два ребенка
current = current['left'] current = root["right"]
root["name"] = current["name"] while current["left"] is not None:
root["phone"] = current["phone"] current = current["left"]
root["right"] = bst_delete(root["right"],current["name"])
return root root["name"] = current["name"]
root["phone"] = current["phone"]
# Удаляем преемника
root["right"] = bst_delete(root["right"], current["name"])
return root

373
pomelovsd/DataStruct/data_structures.ipynb
View File

@ -2,7 +2,7 @@
"cells": [ "cells": [
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 51, "execution_count": 1,
"id": "c533959c", "id": "c533959c",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -13,7 +13,8 @@
"import time \n", "import time \n",
"import random as rand\n", "import random as rand\n",
"import csv\n", "import csv\n",
"import numpy as np" "import numpy as np\n",
"import sys"
] ]
}, },
{ {
@ -26,15 +27,16 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 52, "execution_count": 2,
"id": "88611f78", "id": "88611f78",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"N = 10000\n", "N = 10000\n",
"sys.setrecursionlimit(10000) \n",
"records_sorted = [(f\"User_{i:05d}\", f\"+7999{i:07d}\") for i in range(N)] \n", "records_sorted = [(f\"User_{i:05d}\", f\"+7999{i:07d}\") for i in range(N)] \n",
"records_shuffled = records_sorted.copy()\n", "records_shuffled = records_sorted.copy()\n",
"rand.shuffle(records_shuffled) " "rand.shuffle(records_shuffled)"
] ]
}, },
{ {
@ -42,7 +44,7 @@
"id": "9fd1b8cd", "id": "9fd1b8cd",
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Исследование для LinkedList " "## Исследование для LinkedList"
] ]
}, },
{ {
@ -51,18 +53,20 @@
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Добавление всех элементов произвольного кортежа\n", "### Добавление всех элементов произвольного кортежа\n",
"- **data_ll_sh** - структура произвольных данных (только последний замер)\n", "- **data_ll_sh** - Структура произвольных данных (только последний замер)\n",
"- **time_ll_insert_sh** - Замер времени работы 10000 элементов (5 замеров) " "- **time_ll_insert_sh** - Замер времени работы 10000 элементов (5 замеров) \n",
"- **heads_ll_sh** - Массив голов для массив для произвольного массива"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 53, "execution_count": 3,
"id": "11634fa4", "id": "11634fa4",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"time_ll_insert_sh = [] \n", "time_ll_insert_sh = [] \n",
"heads_ll_sh = []\n",
"for n in range(5):\n", "for n in range(5):\n",
" head = None\n", " head = None\n",
" data_ll_sh = []\n", " data_ll_sh = []\n",
@ -71,6 +75,7 @@
" head = ll.ll_insert(head, records_shuffled[i][0], records_shuffled[i][1])\n", " head = ll.ll_insert(head, records_shuffled[i][0], records_shuffled[i][1])\n",
" data_ll_sh.append(head)\n", " data_ll_sh.append(head)\n",
" end = time.perf_counter()\n", " end = time.perf_counter()\n",
" heads_ll_sh.append(head)\n",
" time_ll_insert_sh.append(end - start)" " time_ll_insert_sh.append(end - start)"
] ]
}, },
@ -81,17 +86,19 @@
"source": [ "source": [
"### Добавление всех элементов сортированного кортежа\n", "### Добавление всех элементов сортированного кортежа\n",
"- **data_ll_so** - Структура отсортированных данных (только последний замер)\n", "- **data_ll_so** - Структура отсортированных данных (только последний замер)\n",
"- **time_ll_insert_so** - Замер времени работы 10000 элементов (5 замеров) " "- **time_ll_insert_so** - Замер времени работы 10000 элементов (5 замеров) \n",
"- **heads_ll_so** - Массив голов для массив для сортированного массива"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 54, "execution_count": 4,
"id": "9eab4641", "id": "9eab4641",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"time_ll_insert_so = [] \n", "time_ll_insert_so = [] \n",
"heads_ll_so = []\n",
"for n in range(5):\n", "for n in range(5):\n",
" head = None\n", " head = None\n",
" data_ll_so = []\n", " data_ll_so = []\n",
@ -100,6 +107,7 @@
" head = ll.ll_insert(head, records_sorted[i][0], records_sorted[i][1])\n", " head = ll.ll_insert(head, records_sorted[i][0], records_sorted[i][1])\n",
" data_ll_so.append(head)\n", " data_ll_so.append(head)\n",
" end = time.perf_counter()\n", " end = time.perf_counter()\n",
" heads_ll_so.append(head)\n",
" time_ll_insert_so.append(end - start)" " time_ll_insert_so.append(end - start)"
] ]
}, },
@ -115,7 +123,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 55, "execution_count": 5,
"id": "aac6cd23", "id": "aac6cd23",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -147,7 +155,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 56, "execution_count": 6,
"id": "5e5ae537", "id": "5e5ae537",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -178,31 +186,22 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 7,
"id": "6cdf8a70", "id": "6cdf8a70",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [],
{
"ename": "KeyError",
"evalue": "9873",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[59], line 7\u001b[0m\n\u001b[1;32m 5\u001b[0m i \u001b[38;5;241m=\u001b[39m rand\u001b[38;5;241m.\u001b[39mrandint(\u001b[38;5;241m0\u001b[39m, N\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m)\n\u001b[1;32m 6\u001b[0m str_delete \u001b[38;5;241m=\u001b[39m records_shuffled[i][\u001b[38;5;241m0\u001b[39m]\n\u001b[0;32m----> 7\u001b[0m data_ll_sh \u001b[38;5;241m=\u001b[39m ll\u001b[38;5;241m.\u001b[39mll_delete(\u001b[43mdata_ll_sh\u001b[49m\u001b[43m[\u001b[49m\u001b[43mi\u001b[49m\u001b[43m]\u001b[49m[\u001b[38;5;241m2\u001b[39m], str_delete)\n\u001b[1;32m 8\u001b[0m end \u001b[38;5;241m=\u001b[39m time\u001b[38;5;241m.\u001b[39mperf_counter()\n\u001b[1;32m 9\u001b[0m time_ll_delete_sh\u001b[38;5;241m.\u001b[39mappend(end \u001b[38;5;241m-\u001b[39m start)\n",
"\u001b[0;31mKeyError\u001b[0m: 9873"
]
}
],
"source": [ "source": [
"time_ll_delete_sh = []\n", "time_ll_delete_sh = []\n",
"for n in range(5):\n", "for n in range(5):\n",
" current_head = heads_ll_sh[n]\n",
"\n",
" start = time.perf_counter()\n", " start = time.perf_counter()\n",
" for m in range(50): \n", " for m in range(50): \n",
" i = rand.randint(0, N-1)\n", " i = rand.randint(0, N-1)\n",
" str_delete = records_shuffled[i][0]\n", " str_delete = records_shuffled[i][0]\n",
" data_ll_sh = ll.ll_delete(data_ll_sh[i][2], str_delete)\n", " current_head = ll.ll_delete(current_head, str_delete)\n",
" end = time.perf_counter()\n", " end = time.perf_counter()\n",
"\n",
" time_ll_delete_sh.append(end - start)" " time_ll_delete_sh.append(end - start)"
] ]
}, },
@ -211,9 +210,325 @@
"id": "8d6156e9", "id": "8d6156e9",
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Удаление элементов в произвольном массиве\n", "### Удаление элементов в сортированном массиве\n",
"- **time_ll_delete_sh** - Време поиска в произвольном массиве (для 5 замеров)" "- **time_ll_delete_so** - Време поиска в произвольном массиве (для 5 замеров)"
] ]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "575e375c",
"metadata": {},
"outputs": [],
"source": [
"time_ll_delete_so = []\n",
"for n in range(5):\n",
" current_head = heads_ll_so[n]\n",
"\n",
" start = time.perf_counter()\n",
" for m in range(50): \n",
" i = rand.randint(0, N-1)\n",
" str_delete = records_sorted[i][0]\n",
" current_head = ll.ll_delete(current_head, str_delete)\n",
" end = time.perf_counter()\n",
"\n",
" time_ll_delete_sh.append(end - start)"
]
},
{
"cell_type": "markdown",
"id": "9a95a40b",
"metadata": {},
"source": [
"## Исследование BinaryTree"
]
},
{
"cell_type": "markdown",
"id": "54c92d21",
"metadata": {},
"source": [
"### Добавление всех элементов произвольного кортежа\n",
"- **data_bt_sh** - Структура произвольных данных (только последний замер)\n",
"- **time_bt_insert_sh** - Замер времени работы 10000 элементов (5 замеров) \n",
"- **heads_bt_sh** - Массив голов для массив для произвольного массива"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "939aa900",
"metadata": {},
"outputs": [],
"source": [
"time_bt_insert_sh = [] \n",
"heads_bt_sh = []\n",
"for n in range(5):\n",
" head = None\n",
" data_bt_sh = []\n",
" start = time.perf_counter()\n",
" for i in range(N):\n",
" head = bt.bst_insert(head, records_shuffled[i][0], records_shuffled[i][1])\n",
" data_bt_sh.append(head)\n",
" end = time.perf_counter()\n",
" heads_bt_sh.append(head)\n",
" time_bt_insert_sh.append(end - start)"
]
},
{
"cell_type": "markdown",
"id": "e91b5893",
"metadata": {},
"source": [
"### Добавление всех элементов сортированного кортежа\n",
"- **data_bt_so** - Структура сортированных данных (только последний замер)\n",
"- **time_bt_insert_so** - Замер времени работы 10000 элементов (5 замеров) \n",
"- **heads_bt_so** - Массив голов для массив для сортированного массива"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "d17b8108",
"metadata": {},
"outputs": [],
"source": [
"time_bt_insert_so = [] \n",
"heads_bt_so = []\n",
"for n in range(5):\n",
" head = None\n",
" data_bt_so = []\n",
" start = time.perf_counter()\n",
" head = bt.bst_insert_sort(records_sorted, 0, len(records_sorted) - 1)\n",
" data_bt_so.append(head)\n",
" end = time.perf_counter()\n",
" heads_bt_so.append(head)\n",
" time_bt_insert_so.append(end - start)"
]
},
{
"cell_type": "markdown",
"id": "1e8a3f9e",
"metadata": {},
"source": [
"### Поиск элементов в произвольном массиве\n",
"- **time_bt_find_sh** - Време поиска в произвольном массиве (для 5 замеров)\n",
"- **find_bt_sh** - массив найденных данных в произвольном массиве (только последний замер)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "4352b11d",
"metadata": {},
"outputs": [],
"source": [
"time_bt_find_sh = []\n",
"for n in range(5):\n",
" find_bt_sh = []\n",
" start = time.perf_counter()\n",
" for m in range(100): # замер для 100 случайных узлов \n",
" i = rand.randint(0, N-1)\n",
" str_find = records_shuffled[i][0]\n",
" find_bt_sh.append(bt.bst_find(data_bt_sh[0], str_find))\n",
" for m in range(10): # недоступные данные\n",
" str_find = f\"Node_{m}\"\n",
" find_bt_sh.append(bt.bst_find(data_bt_sh[0], str_find))\n",
" end = time.perf_counter()\n",
" time_bt_find_sh.append(end - start)"
]
},
{
"cell_type": "markdown",
"id": "8db5208b",
"metadata": {},
"source": [
"### Поиск элементов в отсортированном массиве\n",
"- **time_bt_find_so** - Време поиска в сортированном массиве (для 5 замеров)\n",
"- **find_bt_so** - массив найденных данных в сортированном массиве (только последний замер)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "7941e689",
"metadata": {},
"outputs": [],
"source": [
"time_bt_find_so = []\n",
"for n in range(5):\n",
" find_bt_so = []\n",
" start = time.perf_counter()\n",
" for m in range(100): # замер для 100 случайных узлов \n",
" i = rand.randint(0, N-1)\n",
" str_find = records_sorted[i][0]\n",
" find_bt_so.append(bt.bst_find(data_bt_so[0], str_find))\n",
" for m in range(10): # недоступные данные\n",
" str_find = f\"Node_{m}\"\n",
" find_bt_so.append(bt.bst_find(data_bt_so[0], str_find))\n",
" end = time.perf_counter()\n",
" time_bt_find_sh.append(end - start)"
]
},
{
"cell_type": "markdown",
"id": "ffbe3dfe",
"metadata": {},
"source": [
"### Удаление элементов в произвольном массиве\n",
"- **time_bt_delete_sh** - Време поиска в произвольном массиве (для 5 замеров)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "4043a9dc",
"metadata": {},
"outputs": [],
"source": [
"time_bt_delete_sh = []\n",
"for n in range(5):\n",
" current_head = heads_bt_sh[n]\n",
"\n",
" start = time.perf_counter()\n",
" for m in range(50): \n",
" i = rand.randint(0, N-1)\n",
" str_delete = records_shuffled[i][0]\n",
" current_head = bt.bst_delete(current_head, str_delete)\n",
" end = time.perf_counter()\n",
"\n",
" time_bt_delete_sh.append(end - start)"
]
},
{
"cell_type": "markdown",
"id": "7db94391",
"metadata": {},
"source": [
"### Удаление элементов в сортированном массиве\n",
"- **time_bt_delete_so** - Време поиска в произвольном массиве (для 5 замеров)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "7ab6136c",
"metadata": {},
"outputs": [],
"source": [
"time_bt_delete_so = []\n",
"for n in range(5):\n",
" current_head = heads_bt_so[n]\n",
"\n",
" start = time.perf_counter()\n",
" for m in range(50): \n",
" i = rand.randint(0, N-1)\n",
" str_delete = records_sorted[i][0]\n",
" current_head = bt.bst_delete(current_head, str_delete)\n",
" end = time.perf_counter()\n",
"\n",
" time_bt_delete_so.append(end - start)"
]
},
{
"cell_type": "markdown",
"id": "0bf5b406",
"metadata": {},
"source": [
"## Исследование HashTable"
]
},
{
"cell_type": "markdown",
"id": "75586bbc",
"metadata": {},
"source": [
"### Добавление всех элементов произвольного кортежа\n",
"- **data_ht_sh** - Структура произвольных данных (только последний замер)\n",
"- **time_ht_insert_sh** - Замер времени работы 10000 элементов (5 замеров) \n",
"- **heads_ht_sh** - Массив голов для массив для произвольного массива"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "cb1788d1",
"metadata": {},
"outputs": [],
"source": [
"time_ht_insert_sh = [] \n",
"for n in range(5):\n",
" buckets = ht.create_ht(size = N)\n",
" data_ht_sh = []\n",
" start = time.perf_counter()\n",
" for i in range(N):\n",
" buckets = ht.ht_insert(buckets, records_shuffled[i][0], records_shuffled[i][1])\n",
" data_ht_sh.append(buckets)\n",
" end = time.perf_counter()\n",
" time_ht_insert_sh.append(end - start)"
]
},
{
"cell_type": "markdown",
"id": "6bb2aa16",
"metadata": {},
"source": [
"### Добавление всех элементов сортированного кортежа\n",
"- **data_ht_so** - Структура сортированных данных (только последний замер)\n",
"- **time_ht_insert_so** - Замер времени работы 10000 элементов (5 замеров) \n",
"- **heads_ht_so** - Массив голов для массив для сортированного массива"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "4cb524e4",
"metadata": {},
"outputs": [],
"source": [
"time_ht_insert_so = [] \n",
"for n in range(5):\n",
" buckets = ht.create_ht(size = N)\n",
" data_ht_so = []\n",
" start = time.perf_counter()\n",
" for i in range(N):\n",
" buckets = ht.ht_insert(buckets, records_sorted[i][0], records_sorted[i][1])\n",
" data_ht_so.append(buckets)\n",
" end = time.perf_counter()\n",
" time_ht_insert_so.append(end - start)"
]
},
{
"cell_type": "markdown",
"id": "9d79016f",
"metadata": {},
"source": [
"### Поиск элементов в произвольном массиве\n",
"- **time_ht_find_sh** - Време поиска в произвольном массиве (для 5 замеров)\n",
"- **find_ht_sh** - массив найденных данных в произвольном массиве (только последний замер)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "45cec102",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"id": "8f11dbad",
"metadata": {},
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "19e7a19a",
"metadata": {},
"outputs": [],
"source": []
} }
], ],
"metadata": { "metadata": {