stud203797/MasteringJupyterLab
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Work pandas & numpy

Browse Source
This commit is contained in:
Александр Костюхин (изменено через API) 2026-05-05 19:59:46 +03:00
parent f96e378671
commit 2894cd3050
1 changed files with 219 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

245
week2_analysis.ipynb
View File

@ -1,46 +1,239 @@
{
"cells": [
{
"metadata": {},
"cell_type": "markdown",
"source": [
"# Проверка результатов Jupyter lab\n",
"## Ниже представлен код для проверки того, что всё работает верно\n",
"\n"
],
"id": "2933ef7d9aa256a2"
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2026-05-05T15:58:26.593266100Z",
"start_time": "2026-05-05T15:58:26.530495400Z"
"end_time": "2026-05-05T16:56:23.391024900Z",
"start_time": "2026-05-05T16:56:23.052361300Z"
}
},
"cell_type": "code",
"source": "print(\"Привет, JupyterLab работает!\")",
"source": [
"import pandas as pd\n",
"\n",
"# Создадим DataFrame\n",
"data = {\n",
" \"Имя\": [\"Анна\", \"Борис\", \"Виктор\", \"Галина\", \"Саша\"],\n",
" \"Возраст\": [21, 22, 23, 24, 22],\n",
" \"Баллы\": [89, 76, 95, 82, 80]\n",
"}\n",
"df = pd.DataFrame(data)\n",
"print(\"Первый взгляд на данные:\")\n",
"print(df.head())\n",
"print(df.info())\n",
"print(df.describe())\n",
"print(df.isnull().sum())\n",
"df[\"Новый столбец\"] = df[\"Баллы\"] * 1.1\n",
"\n",
"groups = df.groupby(\"Возраст\")[\"Баллы\"].agg('mean')\n",
"df_filter = df[df[\"Возраст\"] > 21]\n",
"\n",
"print(\"Студенты старше 21 года:\")\n",
"display(df_filter)\n",
"\n",
"print(\"Средние баллы по возрастам:\")\n",
"df\n",
"groups"
],
"id": "c6257ab155ac3a98",
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Привет, JupyterLab работает!\n"
"Первый взгляд на данные:\n",
" Имя Возраст Баллы\n",
"0 Анна 21 89\n",
"1 Борис 22 76\n",
"2 Виктор 23 95\n",
"3 Галина 24 82\n",
"4 Саша 22 80\n",
"<class 'pandas.DataFrame'>\n",
"RangeIndex: 5 entries, 0 to 4\n",
"Data columns (total 3 columns):\n",
" # Column Non-Null Count Dtype\n",
"--- ------ -------------- -----\n",
" 0 Имя 5 non-null str \n",
" 1 Возраст 5 non-null int64\n",
" 2 Баллы 5 non-null int64\n",
"dtypes: int64(2), str(1)\n",
"memory usage: 252.0 bytes\n",
"None\n",
" Возраст Баллы\n",
"count 5.000000 5.000000\n",
"mean 22.400000 84.400000\n",
"std 1.140175 7.569676\n",
"min 21.000000 76.000000\n",
"25% 22.000000 80.000000\n",
"50% 22.000000 82.000000\n",
"75% 23.000000 89.000000\n",
"max 24.000000 95.000000\n",
"Имя 0\n",
"Возраст 0\n",
"Баллы 0\n",
"dtype: int64\n",
"Студенты старше 21 года:\n"
]
},
{
"data": {
"text/plain": [
" Имя Возраст Баллы Новый столбец\n",
"1 Борис 22 76 83.6\n",
"2 Виктор 23 95 104.5\n",
"3 Галина 24 82 90.2\n",
"4 Саша 22 80 88.0"
],
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Имя</th>\n",
" <th>Возраст</th>\n",
" <th>Баллы</th>\n",
" <th>Новый столбец</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Борис</td>\n",
" <td>22</td>\n",
" <td>76</td>\n",
" <td>83.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Виктор</td>\n",
" <td>23</td>\n",
" <td>95</td>\n",
" <td>104.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Галина</td>\n",
" <td>24</td>\n",
" <td>82</td>\n",
" <td>90.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Саша</td>\n",
" <td>22</td>\n",
" <td>80</td>\n",
" <td>88.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
]
},
"metadata": {},
"output_type": "display_data",
"jetTransient": {
"display_id": null
}
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Средние баллы по возрастам:\n"
]
},
{
"data": {
"text/plain": [
"Возраст\n",
"21 89.0\n",
"22 78.0\n",
"23 95.0\n",
"24 82.0\n",
"Name: Баллы, dtype: float64"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"execution_count": 22
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2026-05-05T16:56:23.914438700Z",
"start_time": "2026-05-05T16:56:23.527643100Z"
}
},
"cell_type": "code",
"source": [
"import numpy as np\n",
"\n",
"arr = np.array([1, 2, 3, 4, 5])\n",
"X = np.array([[1, 2], [3, 4]])\n",
"\n",
"\n",
"#Создание ровных интервалов\n",
"range = np.linspace(np.min(X), np.max(X), 5)\n",
"print(\"\\nИнтервал от min(A) до max(A):\\n\", range)\n",
"\n",
"\n",
"#Стандартное нормальное распределение\n",
"norm_random_array = np.random.randn(*X.shape)\n",
"print(\"\\nСлучайный массив того же размера, что и A:\\n\", norm_random_array)\n",
"\n",
"#Матричное умножение\n",
"res_dot = np.dot(X, X)\n",
"print(\"\\nРезультат умножения матриц:\\n\", res_dot)\n",
"\n",
"\n",
"print(\"\\nСумма элементов массива:\", np.sum(arr))\n",
"print(\"Среднее значение:\", np.mean(arr))\n",
"print(\"Медиана:\", np.median(arr))\n",
"print(\"Стандартное отклонение:\", np.std(arr))\n"
],
"id": "159535e1a3ef473a",
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Интервал от min(A) до max(A):\n",
" [1. 1.75 2.5 3.25 4. ]\n",
"\n",
"Случайный массив того же размера, что и A:\n",
" [[-0.03315556 -0.16675026]\n",
" [-0.91077853 -0.68547878]]\n",
"\n",
"Результат умножения матриц:\n",
" [[ 7 10]\n",
" [15 22]]\n",
"\n",
"Сумма элементов массива: 15\n",
"Среднее значение: 3.0\n",
"Медиана: 3.0\n",
"Стандартное отклонение: 1.4142135623730951\n"
]
}
],
"execution_count": 4
},
{
"metadata": {},
"cell_type": "markdown",
"source": [
"## Выводы\n",
"\n",
"- В этом блокноте была проведена небольшая проверка работы Jupyter lab\n",
"- Всё работает"
],
"id": "9d044d9676b9de17"
"execution_count": 23
}
],
"metadata": {