NKTKLN/mirea-projects
NKTKLN/mirea-projects
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
main
mirea-projects/Third term/Artificial intelligence systems and big data/2.ipynb

1402 lines
40 KiB
Plaintext
Raw Permalink Normal View History

first commit
2024-09-23 23:22:33 +00:00
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Рабочая тетрадь № 2"
]
},
{
"cell_type": "code",
many
2024-09-27 05:31:03 +00:00
"execution_count": 6,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd \n",
"from sklearn.preprocessing import MinMaxScaler, StandardScaler"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 1.3.1 Задание \n",
"\n",
"Создать 8x8 матрицу и заполнить её в шахматном порядке нулями и \n",
"единицами."
]
},
{
"cell_type": "code",
many
2024-09-27 05:31:03 +00:00
"execution_count": 7,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
many
2024-09-27 05:31:03 +00:00
"array([[0, 1, 0, 1, 0, 1, 0, 1, 0],\n",
" [1, 0, 1, 0, 1, 0, 1, 0, 1],\n",
" [0, 1, 0, 1, 0, 1, 0, 1, 0],\n",
" [1, 0, 1, 0, 1, 0, 1, 0, 1],\n",
" [0, 1, 0, 1, 0, 1, 0, 1, 0],\n",
" [1, 0, 1, 0, 1, 0, 1, 0, 1],\n",
" [0, 1, 0, 1, 0, 1, 0, 1, 0],\n",
" [1, 0, 1, 0, 1, 0, 1, 0, 1],\n",
" [0, 1, 0, 1, 0, 1, 0, 1, 0]])"
first commit
2024-09-23 23:22:33 +00:00
]
},
many
2024-09-27 05:31:03 +00:00
"execution_count": 7,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
many
2024-09-27 05:31:03 +00:00
"np.array([[(x + y) % 2 for x in range(9)] for y in range(9)])"
first commit
2024-09-23 23:22:33 +00:00
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 1.3.2 Задание\n",
"\n",
"Создать 5x5 матрицу со значениями в строках от 0 до 4. Для создания \n",
"необходимо использовать функцию arrange. "
]
},
{
"cell_type": "code",
many
2024-09-27 05:31:03 +00:00
"execution_count": 8,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[0, 1, 2, 3, 4],\n",
" [0, 1, 2, 3, 4],\n",
" [0, 1, 2, 3, 4],\n",
" [0, 1, 2, 3, 4],\n",
" [0, 1, 2, 3, 4]])"
]
},
many
2024-09-27 05:31:03 +00:00
"execution_count": 8,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"np.array([np.arange(0, 5) for _ in range(5)])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 1.3.3 Задание\n",
"\n",
"Создать массив 3x3x3 со случайными значениями. "
]
},
{
"cell_type": "code",
many
2024-09-27 05:31:03 +00:00
"execution_count": 9,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
many
2024-09-27 05:31:03 +00:00
"array([[[0.20345315, 0.43131518, 0.76966255],\n",
" [0.86176214, 0.92498056, 0.61472383],\n",
" [0.93945099, 0.1950391 , 0.23309391]],\n",
first commit
2024-09-23 23:22:33 +00:00
"\n",
many
2024-09-27 05:31:03 +00:00
" [[0.32571424, 0.91336522, 0.95073139],\n",
" [0.48109355, 0.32416483, 0.32925225],\n",
" [0.56116627, 0.8999968 , 0.58189073]],\n",
first commit
2024-09-23 23:22:33 +00:00
"\n",
many
2024-09-27 05:31:03 +00:00
" [[0.98682298, 0.58254628, 0.25540734],\n",
" [0.96791093, 0.96124583, 0.53073238],\n",
" [0.25062485, 0.88066294, 0.99449625]]])"
first commit
2024-09-23 23:22:33 +00:00
]
},
many
2024-09-27 05:31:03 +00:00
"execution_count": 9,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"np.random.random((3, 3, 3))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 1.3.4 Задание\n",
"\n",
"Создать матрицу с 0 внутри, и 1 на границах."
]
},
{
"cell_type": "code",
many
2024-09-27 05:31:03 +00:00
"execution_count": 25,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
many
2024-09-27 05:31:03 +00:00
"array([[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],\n",
" [1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],\n",
" [1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],\n",
" [1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],\n",
" [1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],\n",
" [1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],\n",
" [1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],\n",
" [1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],\n",
" [1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],\n",
" [1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],\n",
" [1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],\n",
" [1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],\n",
" [1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],\n",
" [1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],\n",
" [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]])"
first commit
2024-09-23 23:22:33 +00:00
]
},
many
2024-09-27 05:31:03 +00:00
"execution_count": 25,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
many
2024-09-27 05:31:03 +00:00
"np.array([[int((x in [0, 14]) or (y in [0, 14])) for x in range(15)] for y in range(15)])"
first commit
2024-09-23 23:22:33 +00:00
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 1.3.5 Задание\n",
"\n",
"Создайте массив и отсортируйте его по убыванию. "
]
},
{
"cell_type": "code",
many
2024-09-27 05:31:03 +00:00
"execution_count": 36,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
many
2024-09-27 05:31:03 +00:00
"array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])"
first commit
2024-09-23 23:22:33 +00:00
]
},
many
2024-09-27 05:31:03 +00:00
"execution_count": 36,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"arr = np.arange(0, 10)\n",
many
2024-09-27 05:31:03 +00:00
"np.sort(arr)"
first commit
2024-09-23 23:22:33 +00:00
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 1.3.6 Задание\n",
"\n",
"Создайте матрицу, выведите ее форму, размер и размерность."
]
},
{
"cell_type": "code",
many
2024-09-27 05:31:03 +00:00
"execution_count": 32,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
many
2024-09-27 05:31:03 +00:00
"Размерность массива по каждой оси: (2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2)\n",
"Число измерений: 12\n",
"Колличество элементов: 4096\n"
first commit
2024-09-23 23:22:33 +00:00
]
}
],
"source": [
many
2024-09-27 05:31:03 +00:00
"arr = np.random.random(np.full(12, 2))\n",
first commit
2024-09-23 23:22:33 +00:00
"\n",
many
2024-09-27 05:31:03 +00:00
"print(\"Размерность массива по каждой оси:\", arr.shape)\n",
"print(\"Число измерений:\", arr.ndim)\n",
"print(\"Колличество элементов:\", arr.size)"
first commit
2024-09-23 23:22:33 +00:00
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 2.3.1 Задание\n",
"\n",
"Найди евклидово расстояние между двумя Series (точками) a и b, не \n",
"используя встроенную формулу."
]
},
{
"cell_type": "code",
many
2024-09-27 05:31:03 +00:00
"execution_count": 26,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
many
2024-09-27 05:31:03 +00:00
"1.4142135623730951\n"
first commit
2024-09-23 23:22:33 +00:00
]
}
],
"source": [
"from math import sqrt\n",
"\n",
many
2024-09-27 05:31:03 +00:00
"first_dot = pd.Series([1, 0])\n",
"second_dot = pd.Series([0, 1])\n",
first commit
2024-09-23 23:22:33 +00:00
"\n",
"s = 0\n",
"for dim in range(first_dot.size):\n",
" s += (first_dot.array[dim] - second_dot.array[dim]) ** 2\n",
"\n",
"print(sqrt(s))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 2.3.2 Задание \n",
"\n",
"Найдите в Интернете ссылку на любой csv файл и сформируйте из него \n",
"фрейм данных (например, коллекцию фреймов данных можно найти \n",
"здесь: https://github.com/akmand/datasets)."
]
},
{
"cell_type": "code",
many
2024-09-27 05:31:03 +00:00
"execution_count": 14,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"outputs": [
{
"data": {
"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>Airline</th>\n",
" <th>Flight</th>\n",
" <th>AirportFrom</th>\n",
" <th>AirportTo</th>\n",
" <th>DayOfWeek</th>\n",
" <th>Time</th>\n",
" <th>Length</th>\n",
" <th>Delay</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>CO</td>\n",
" <td>269</td>\n",
" <td>SFO</td>\n",
" <td>IAH</td>\n",
" <td>3</td>\n",
" <td>15</td>\n",
" <td>205</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>US</td>\n",
" <td>1558</td>\n",
" <td>PHX</td>\n",
" <td>CLT</td>\n",
" <td>3</td>\n",
" <td>15</td>\n",
" <td>222</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>AA</td>\n",
" <td>2400</td>\n",
" <td>LAX</td>\n",
" <td>DFW</td>\n",
" <td>3</td>\n",
" <td>20</td>\n",
" <td>165</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>AA</td>\n",
" <td>2466</td>\n",
" <td>SFO</td>\n",
" <td>DFW</td>\n",
" <td>3</td>\n",
" <td>20</td>\n",
" <td>195</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>AS</td>\n",
" <td>108</td>\n",
" <td>ANC</td>\n",
" <td>SEA</td>\n",
" <td>3</td>\n",
" <td>30</td>\n",
" <td>202</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>539378</th>\n",
" <td>CO</td>\n",
" <td>178</td>\n",
" <td>OGG</td>\n",
" <td>SNA</td>\n",
" <td>5</td>\n",
" <td>1439</td>\n",
" <td>326</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>539379</th>\n",
" <td>FL</td>\n",
" <td>398</td>\n",
" <td>SEA</td>\n",
" <td>ATL</td>\n",
" <td>5</td>\n",
" <td>1439</td>\n",
" <td>305</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>539380</th>\n",
" <td>FL</td>\n",
" <td>609</td>\n",
" <td>SFO</td>\n",
" <td>MKE</td>\n",
" <td>5</td>\n",
" <td>1439</td>\n",
" <td>255</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>539381</th>\n",
" <td>UA</td>\n",
" <td>78</td>\n",
" <td>HNL</td>\n",
" <td>SFO</td>\n",
" <td>5</td>\n",
" <td>1439</td>\n",
" <td>313</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>539382</th>\n",
" <td>US</td>\n",
" <td>1442</td>\n",
" <td>LAX</td>\n",
" <td>PHL</td>\n",
" <td>5</td>\n",
" <td>1439</td>\n",
" <td>301</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>539383 rows × 8 columns</p>\n",
"</div>"
],
"text/plain": [
" Airline Flight AirportFrom AirportTo DayOfWeek Time Length Delay\n",
"0 CO 269 SFO IAH 3 15 205 1\n",
"1 US 1558 PHX CLT 3 15 222 1\n",
"2 AA 2400 LAX DFW 3 20 165 1\n",
"3 AA 2466 SFO DFW 3 20 195 1\n",
"4 AS 108 ANC SEA 3 30 202 0\n",
"... ... ... ... ... ... ... ... ...\n",
"539378 CO 178 OGG SNA 5 1439 326 0\n",
"539379 FL 398 SEA ATL 5 1439 305 0\n",
"539380 FL 609 SFO MKE 5 1439 255 0\n",
"539381 UA 78 HNL SFO 5 1439 313 1\n",
"539382 US 1442 LAX PHL 5 1439 301 1\n",
"\n",
"[539383 rows x 8 columns]"
]
},
many
2024-09-27 05:31:03 +00:00
"execution_count": 14,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"url = 'https://raw.githubusercontent.com/akmand/datasets/refs/heads/main/airlines.csv'\n",
"\n",
"df = pd.read_csv(url)\n",
"\n",
"df"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 2.3.3 Задание\n",
"\n",
"Проделайте с получившемся из предыдущего задания фреймом данных \n",
"те же действия, что и в примерах 2.2.5-2.2.7. "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### 2.2.5\n",
"\n",
"Пронализировать характеристики фрейма данных."
]
},
{
"cell_type": "code",
many
2024-09-27 05:31:03 +00:00
"execution_count": 15,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"outputs": [
{
"data": {
"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>Airline</th>\n",
" <th>Flight</th>\n",
" <th>AirportFrom</th>\n",
" <th>AirportTo</th>\n",
" <th>DayOfWeek</th>\n",
" <th>Time</th>\n",
" <th>Length</th>\n",
" <th>Delay</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>CO</td>\n",
" <td>269</td>\n",
" <td>SFO</td>\n",
" <td>IAH</td>\n",
" <td>3</td>\n",
" <td>15</td>\n",
" <td>205</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>US</td>\n",
" <td>1558</td>\n",
" <td>PHX</td>\n",
" <td>CLT</td>\n",
" <td>3</td>\n",
" <td>15</td>\n",
" <td>222</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Airline Flight AirportFrom AirportTo DayOfWeek Time Length Delay\n",
"0 CO 269 SFO IAH 3 15 205 1\n",
"1 US 1558 PHX CLT 3 15 222 1"
]
},
many
2024-09-27 05:31:03 +00:00
"execution_count": 15,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head(2)"
]
},
{
"cell_type": "code",
many
2024-09-27 05:31:03 +00:00
"execution_count": 16,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"outputs": [
{
"data": {
"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>Airline</th>\n",
" <th>Flight</th>\n",
" <th>AirportFrom</th>\n",
" <th>AirportTo</th>\n",
" <th>DayOfWeek</th>\n",
" <th>Time</th>\n",
" <th>Length</th>\n",
" <th>Delay</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>539380</th>\n",
" <td>FL</td>\n",
" <td>609</td>\n",
" <td>SFO</td>\n",
" <td>MKE</td>\n",
" <td>5</td>\n",
" <td>1439</td>\n",
" <td>255</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>539381</th>\n",
" <td>UA</td>\n",
" <td>78</td>\n",
" <td>HNL</td>\n",
" <td>SFO</td>\n",
" <td>5</td>\n",
" <td>1439</td>\n",
" <td>313</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>539382</th>\n",
" <td>US</td>\n",
" <td>1442</td>\n",
" <td>LAX</td>\n",
" <td>PHL</td>\n",
" <td>5</td>\n",
" <td>1439</td>\n",
" <td>301</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Airline Flight AirportFrom AirportTo DayOfWeek Time Length Delay\n",
"539380 FL 609 SFO MKE 5 1439 255 0\n",
"539381 UA 78 HNL SFO 5 1439 313 1\n",
"539382 US 1442 LAX PHL 5 1439 301 1"
]
},
many
2024-09-27 05:31:03 +00:00
"execution_count": 16,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.tail(3)"
]
},
{
"cell_type": "code",
many
2024-09-27 05:31:03 +00:00
"execution_count": 17,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(539383, 8)"
]
},
many
2024-09-27 05:31:03 +00:00
"execution_count": 17,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.shape"
]
},
{
"cell_type": "code",
many
2024-09-27 05:31:03 +00:00
"execution_count": 18,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"outputs": [
{
"data": {
"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>Flight</th>\n",
" <th>DayOfWeek</th>\n",
" <th>Time</th>\n",
" <th>Length</th>\n",
" <th>Delay</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>539383.000000</td>\n",
" <td>539383.000000</td>\n",
" <td>539383.000000</td>\n",
" <td>539383.000000</td>\n",
" <td>539383.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>2427.928630</td>\n",
" <td>3.929668</td>\n",
" <td>802.728963</td>\n",
" <td>132.202007</td>\n",
" <td>0.445442</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>2067.429837</td>\n",
" <td>1.914664</td>\n",
" <td>278.045911</td>\n",
" <td>70.117016</td>\n",
" <td>0.497015</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>10.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>712.000000</td>\n",
" <td>2.000000</td>\n",
" <td>565.000000</td>\n",
" <td>81.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>1809.000000</td>\n",
" <td>4.000000</td>\n",
" <td>795.000000</td>\n",
" <td>115.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>3745.000000</td>\n",
" <td>5.000000</td>\n",
" <td>1035.000000</td>\n",
" <td>162.000000</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>7814.000000</td>\n",
" <td>7.000000</td>\n",
" <td>1439.000000</td>\n",
" <td>655.000000</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
many
2024-09-27 05:31:03 +00:00
" Flight DayOfWeek Time Length \\\n",
"count 539383.000000 539383.000000 539383.000000 539383.000000 \n",
first commit
2024-09-23 23:22:33 +00:00
"mean 2427.928630 3.929668 802.728963 132.202007 \n",
"std 2067.429837 1.914664 278.045911 70.117016 \n",
"min 1.000000 1.000000 10.000000 0.000000 \n",
"25% 712.000000 2.000000 565.000000 81.000000 \n",
"50% 1809.000000 4.000000 795.000000 115.000000 \n",
"75% 3745.000000 5.000000 1035.000000 162.000000 \n",
"max 7814.000000 7.000000 1439.000000 655.000000 \n",
"\n",
" Delay \n",
"count 539383.000000 \n",
"mean 0.445442 \n",
"std 0.497015 \n",
"min 0.000000 \n",
"25% 0.000000 \n",
"50% 0.000000 \n",
"75% 1.000000 \n",
"max 1.000000 "
]
},
many
2024-09-27 05:31:03 +00:00
"execution_count": 18,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.describe()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### 2.2.6\n",
"\n",
"Выберите индивидуальные данные или срезы фрейма данных."
]
},
{
"cell_type": "code",
many
2024-09-27 05:31:03 +00:00
"execution_count": 19,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"outputs": [
{
"data": {
"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>Airline</th>\n",
" <th>Flight</th>\n",
" <th>AirportFrom</th>\n",
" <th>AirportTo</th>\n",
" <th>DayOfWeek</th>\n",
" <th>Time</th>\n",
" <th>Length</th>\n",
" <th>Delay</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>US</td>\n",
" <td>1558</td>\n",
" <td>PHX</td>\n",
" <td>CLT</td>\n",
" <td>3</td>\n",
" <td>15</td>\n",
" <td>222</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>AA</td>\n",
" <td>2400</td>\n",
" <td>LAX</td>\n",
" <td>DFW</td>\n",
" <td>3</td>\n",
" <td>20</td>\n",
" <td>165</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>AA</td>\n",
" <td>2466</td>\n",
" <td>SFO</td>\n",
" <td>DFW</td>\n",
" <td>3</td>\n",
" <td>20</td>\n",
" <td>195</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Airline Flight AirportFrom AirportTo DayOfWeek Time Length Delay\n",
"1 US 1558 PHX CLT 3 15 222 1\n",
"2 AA 2400 LAX DFW 3 20 165 1\n",
"3 AA 2466 SFO DFW 3 20 195 1"
]
},
many
2024-09-27 05:31:03 +00:00
"execution_count": 19,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.iloc[1:4]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### 2.2.7\n",
"\n",
"Требуется отобрать строки фрейма данных на основе некоторого \n",
"условия."
]
},
{
"cell_type": "code",
many
2024-09-27 05:31:03 +00:00
"execution_count": 20,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"outputs": [
{
"data": {
"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>Airline</th>\n",
" <th>Flight</th>\n",
" <th>AirportFrom</th>\n",
" <th>AirportTo</th>\n",
" <th>DayOfWeek</th>\n",
" <th>Time</th>\n",
" <th>Length</th>\n",
" <th>Delay</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>US</td>\n",
" <td>1558</td>\n",
" <td>PHX</td>\n",
" <td>CLT</td>\n",
" <td>3</td>\n",
" <td>15</td>\n",
" <td>222</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>US</td>\n",
" <td>498</td>\n",
" <td>DEN</td>\n",
" <td>CLT</td>\n",
" <td>3</td>\n",
" <td>55</td>\n",
" <td>179</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Airline Flight AirportFrom AirportTo DayOfWeek Time Length Delay\n",
"1 US 1558 PHX CLT 3 15 222 1\n",
"15 US 498 DEN CLT 3 55 179 0"
]
},
many
2024-09-27 05:31:03 +00:00
"execution_count": 20,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[df['Airline'] == 'US'].head(2)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 3.3.2 Задание\n",
"\n",
"Загрузить фрейм данных по ссылке: \n",
"https://raw.githubusercontent.com/akmand/datasets/master/iris.csv. \n",
"Необходимо выполнить нормализацию первого числового признака \n",
"(sepal_length_cm) с использованием минимаксного преобразования, а \n",
"второго (sepal_width_cm) с задействованием z-масштабирования. "
]
},
{
"cell_type": "code",
many
2024-09-27 05:31:03 +00:00
"execution_count": 21,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"outputs": [
{
"data": {
"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>sepal_length_cm</th>\n",
" <th>sepal_width_cm</th>\n",
" <th>petal_length_cm</th>\n",
" <th>petal_width_cm</th>\n",
" <th>species</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>4.9</td>\n",
" <td>3.0</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4.7</td>\n",
" <td>3.2</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4.6</td>\n",
" <td>3.1</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5.0</td>\n",
" <td>3.6</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>145</th>\n",
" <td>6.7</td>\n",
" <td>3.0</td>\n",
" <td>5.2</td>\n",
" <td>2.3</td>\n",
" <td>virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <th>146</th>\n",
" <td>6.3</td>\n",
" <td>2.5</td>\n",
" <td>5.0</td>\n",
" <td>1.9</td>\n",
" <td>virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <th>147</th>\n",
" <td>6.5</td>\n",
" <td>3.0</td>\n",
" <td>5.2</td>\n",
" <td>2.0</td>\n",
" <td>virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <th>148</th>\n",
" <td>6.2</td>\n",
" <td>3.4</td>\n",
" <td>5.4</td>\n",
" <td>2.3</td>\n",
" <td>virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <th>149</th>\n",
" <td>5.9</td>\n",
" <td>3.0</td>\n",
" <td>5.1</td>\n",
" <td>1.8</td>\n",
" <td>virginica</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>150 rows × 5 columns</p>\n",
"</div>"
],
"text/plain": [
many
2024-09-27 05:31:03 +00:00
" sepal_length_cm sepal_width_cm petal_length_cm petal_width_cm \\\n",
"0 5.1 3.5 1.4 0.2 \n",
first commit
2024-09-23 23:22:33 +00:00
"1 4.9 3.0 1.4 0.2 \n",
"2 4.7 3.2 1.3 0.2 \n",
"3 4.6 3.1 1.5 0.2 \n",
"4 5.0 3.6 1.4 0.2 \n",
".. ... ... ... ... \n",
"145 6.7 3.0 5.2 2.3 \n",
"146 6.3 2.5 5.0 1.9 \n",
"147 6.5 3.0 5.2 2.0 \n",
"148 6.2 3.4 5.4 2.3 \n",
"149 5.9 3.0 5.1 1.8 \n",
"\n",
" species \n",
"0 setosa \n",
"1 setosa \n",
"2 setosa \n",
"3 setosa \n",
"4 setosa \n",
".. ... \n",
"145 virginica \n",
"146 virginica \n",
"147 virginica \n",
"148 virginica \n",
"149 virginica \n",
"\n",
"[150 rows x 5 columns]"
]
},
many
2024-09-27 05:31:03 +00:00
"execution_count": 21,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"url = 'https://raw.githubusercontent.com/akmand/datasets/master/iris.csv'\n",
"\n",
"iris_df = pd.read_csv(url)\n",
"\n",
"iris_df"
]
},
{
"cell_type": "code",
many
2024-09-27 05:31:03 +00:00
"execution_count": 22,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"outputs": [],
"source": [
"length_feature = np.array(iris_df['sepal_length_cm']).reshape(-1,1)\n",
"\n",
"minmax_scale = MinMaxScaler(feature_range = (0, 1))\n",
"scaled_sepal_length = minmax_scale.fit_transform(length_feature)\n",
"iris_df['sepal_length_cm'] = scaled_sepal_length;"
]
},
{
"cell_type": "code",
many
2024-09-27 05:31:03 +00:00
"execution_count": 23,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"outputs": [],
"source": [
"width_feature = np.array(iris_df['sepal_width_cm']).reshape(-1,1)\n",
"\n",
"z_scale = StandardScaler()\n",
"scaled_sepal_width = z_scale.fit_transform(width_feature)\n",
"iris_df['sepal_width_cm'] = scaled_sepal_width"
]
},
{
"cell_type": "code",
many
2024-09-27 05:31:03 +00:00
"execution_count": 24,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"outputs": [
{
"data": {
"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>sepal_length_cm</th>\n",
" <th>sepal_width_cm</th>\n",
" <th>petal_length_cm</th>\n",
" <th>petal_width_cm</th>\n",
" <th>species</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.222222</td>\n",
" <td>1.032057</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.166667</td>\n",
" <td>-0.124958</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.111111</td>\n",
" <td>0.337848</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0.083333</td>\n",
" <td>0.106445</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0.194444</td>\n",
" <td>1.263460</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>145</th>\n",
" <td>0.666667</td>\n",
" <td>-0.124958</td>\n",
" <td>5.2</td>\n",
" <td>2.3</td>\n",
" <td>virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <th>146</th>\n",
" <td>0.555556</td>\n",
" <td>-1.281972</td>\n",
" <td>5.0</td>\n",
" <td>1.9</td>\n",
" <td>virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <th>147</th>\n",
" <td>0.611111</td>\n",
" <td>-0.124958</td>\n",
" <td>5.2</td>\n",
" <td>2.0</td>\n",
" <td>virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <th>148</th>\n",
" <td>0.527778</td>\n",
" <td>0.800654</td>\n",
" <td>5.4</td>\n",
" <td>2.3</td>\n",
" <td>virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <th>149</th>\n",
" <td>0.444444</td>\n",
" <td>-0.124958</td>\n",
" <td>5.1</td>\n",
" <td>1.8</td>\n",
" <td>virginica</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>150 rows × 5 columns</p>\n",
"</div>"
],
"text/plain": [
many
2024-09-27 05:31:03 +00:00
" sepal_length_cm sepal_width_cm petal_length_cm petal_width_cm \\\n",
"0 0.222222 1.032057 1.4 0.2 \n",
first commit
2024-09-23 23:22:33 +00:00
"1 0.166667 -0.124958 1.4 0.2 \n",
"2 0.111111 0.337848 1.3 0.2 \n",
"3 0.083333 0.106445 1.5 0.2 \n",
"4 0.194444 1.263460 1.4 0.2 \n",
".. ... ... ... ... \n",
"145 0.666667 -0.124958 5.2 2.3 \n",
"146 0.555556 -1.281972 5.0 1.9 \n",
"147 0.611111 -0.124958 5.2 2.0 \n",
"148 0.527778 0.800654 5.4 2.3 \n",
"149 0.444444 -0.124958 5.1 1.8 \n",
"\n",
" species \n",
"0 setosa \n",
"1 setosa \n",
"2 setosa \n",
"3 setosa \n",
"4 setosa \n",
".. ... \n",
"145 virginica \n",
"146 virginica \n",
"147 virginica \n",
"148 virginica \n",
"149 virginica \n",
"\n",
"[150 rows x 5 columns]"
]
},
many
2024-09-27 05:31:03 +00:00
"execution_count": 24,
first commit
2024-09-23 23:22:33 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"iris_df"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
many
2024-09-27 05:31:03 +00:00
"version": "3.12.5"
first commit
2024-09-23 23:22:33 +00:00
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Reference in New Issue Copy Permalink