2week/week2_analysis.ipynb

319 lines
9.5 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "43d948e5-c6ab-49bc-af02-cce09d448c0a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"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",
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 4 entries, 0 to 3\n",
"Data columns (total 3 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 Имя 4 non-null object\n",
" 1 Возраст 4 non-null int64 \n",
" 2 Баллы 4 non-null int64 \n",
"dtypes: int64(2), object(1)\n",
"memory usage: 228.0+ bytes\n",
"None\n",
" Возраст Баллы\n",
"count 4.000000 4.000000\n",
"mean 22.500000 85.500000\n",
"std 1.290994 8.266398\n",
"min 21.000000 76.000000\n",
"25% 21.750000 80.500000\n",
"50% 22.500000 85.500000\n",
"75% 23.250000 90.500000\n",
"max 24.000000 95.000000\n",
"Имя 0\n",
"Возраст 0\n",
"Баллы 0\n",
"dtype: int64\n"
]
}
],
"source": [
"import pandas as pd\n",
"\n",
"# Создадим DataFrame\n",
"data = {\n",
" \"Имя\": [\"Анна\", \"Борис\", \"Виктор\", \"Галина\"],\n",
" \"Возраст\": [21, 22, 23, 24],\n",
" \"Баллы\": [89, 76, 95, 82]\n",
"}\n",
"df = pd.DataFrame(data)\n",
"\n",
"print(\"Первый взгляд на данные:\")\n",
"print(df.head())\n",
"print(df.info())\n",
"print(df.describe())\n",
"print(df.isnull().sum())"
]
},
{
"cell_type": "markdown",
"id": "22288d55-04b9-4e80-8120-2da41b1a32b0",
"metadata": {},
"source": [
"стандартный код, без изменений"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "4d8c96fc-1e83-4218-a96b-81575c28f0d7",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"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",
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 4 entries, 0 to 3\n",
"Data columns (total 3 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 Имя 4 non-null object\n",
" 1 Возраст 4 non-null int64 \n",
" 2 Баллы 4 non-null int64 \n",
"dtypes: int64(2), object(1)\n",
"memory usage: 228.0+ bytes\n",
"None\n",
" Возраст Баллы\n",
"count 4.000000 4.000000\n",
"mean 22.500000 85.500000\n",
"std 1.290994 8.266398\n",
"min 21.000000 76.000000\n",
"25% 21.750000 80.500000\n",
"50% 22.500000 85.500000\n",
"75% 23.250000 90.500000\n",
"max 24.000000 95.000000\n",
"Имя 0\n",
"Возраст 0\n",
"Баллы 0\n",
"dtype: int64\n"
]
},
{
"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>Имя</th>\n",
" <th>Возраст</th>\n",
" <th>Баллы</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Анна</td>\n",
" <td>21</td>\n",
" <td>89</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Борис</td>\n",
" <td>22</td>\n",
" <td>76</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Виктор</td>\n",
" <td>23</td>\n",
" <td>95</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Галина</td>\n",
" <td>24</td>\n",
" <td>82</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Имя Возраст Баллы\n",
"0 Анна 21 89\n",
"1 Борис 22 76\n",
"2 Виктор 23 95\n",
"3 Галина 24 82"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pandas as pd\n",
"\n",
"# Создадим DataFrame\n",
"data = {\n",
" \"Имя\": [\"Анна\", \"Борис\", \"Виктор\", \"Галина\"],\n",
" \"Возраст\": [21, 22, 23, 24],\n",
" \"Баллы\": [89, 76, 95, 82]\n",
"}\n",
"df = pd.DataFrame(data)\n",
"\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"
]
},
{
"cell_type": "markdown",
"id": "e2b6ea08-81e6-4e0d-a9b6-be6559349c7e",
"metadata": {},
"source": [
"добавил df в конце кода"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "b1361266-d103-4766-9337-c9afe7c1873f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"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",
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 4 entries, 0 to 3\n",
"Data columns (total 3 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 Имя 4 non-null object\n",
" 1 Возраст 4 non-null int64 \n",
" 2 Баллы 4 non-null int64 \n",
"dtypes: int64(2), object(1)\n",
"memory usage: 228.0+ bytes\n",
"None\n",
" Возраст Баллы\n",
"count 4.000000 4.000000\n",
"mean 22.500000 85.500000\n",
"std 1.290994 8.266398\n",
"min 21.000000 76.000000\n",
"25% 21.750000 80.500000\n",
"50% 22.500000 85.500000\n",
"75% 23.250000 90.500000\n",
"max 24.000000 95.000000\n",
"Имя 0\n",
"Возраст 0\n",
"Баллы 0\n",
"dtype: int64\n",
" Имя Возраст Баллы Баллы с коэффициентом\n",
"0 Анна 21 89 97.9\n",
"1 Борис 22 76 83.6\n",
"2 Виктор 23 95 104.5\n",
"3 Галина 24 82 90.2\n"
]
}
],
"source": [
"import pandas as pd\n",
"\n",
"# Создадим DataFrame\n",
"data = {\n",
" \"Имя\": [\"Анна\", \"Борис\", \"Виктор\", \"Галина\"],\n",
" \"Возраст\": [21, 22, 23, 24],\n",
" \"Баллы\": [89, 76, 95, 82]\n",
"}\n",
"df = pd.DataFrame(data)\n",
"\n",
"print(\"Первый взгляд на данные:\")\n",
"print(df.head())\n",
"print(df.info())\n",
"print(df.describe())\n",
"print(df.isnull().sum())\n",
"\n",
"# Добавляем новый столбец с вычисляемыми значениями\n",
"df[\"Баллы с коэффициентом\"] = df[\"Баллы\"] * 1.1\n",
"\n",
"print(df)"
]
},
{
"cell_type": "markdown",
"id": "5d658850-1ef4-41cc-81c2-afda9213bd6d",
"metadata": {},
"source": [
"добавил новый столбец с вычисляемыми значениями"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d27ebb99-d8b7-44b6-9d6f-59062c18eb81",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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",
"version": "3.13.2"
}
},
"nbformat": 4,
"nbformat_minor": 5
}