AIM-PIbd-31-Bakalskaya-E-D/lab_1/lab1.ipynb

420 lines
127 KiB
Plaintext
Raw Normal View History

2024-09-20 20:07:21 +04:00
{
"cells": [
2024-09-21 01:52:19 +04:00
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<p style=\"text-decoration: underline; text-align: center;\">Скриншот запущенного сваггера:</p>\n",
"\n",
"<img src=\"./image.png\" style=\"width: 1000px; \"></img>\n",
"\n"
]
},
2024-09-20 20:07:21 +04:00
{
"cell_type": "code",
2024-09-21 01:52:19 +04:00
"execution_count": 61,
2024-09-20 20:07:21 +04:00
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
2024-09-21 01:52:19 +04:00
"import matplotlib.pyplot as plt\n",
"data_base = pd.read_csv(\"csv/option4.csv\")\n",
"\n",
"# data_base.info\n",
"\n",
"# print(data_base.describe().transpose())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<p style=\"text-align: center;\"><i>Вызов функции для удобного просмотра столбцов и их значений во время выполнения лабы</i></p>"
]
},
{
"cell_type": "code",
"execution_count": 84,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<bound method DataFrame.info of id gender age hypertension heart_disease ever_married \\\n",
"0 9046 Male 67.0 0 1 Yes \n",
"1 51676 Female 61.0 0 0 Yes \n",
"2 31112 Male 80.0 0 1 Yes \n",
"3 60182 Female 49.0 0 0 Yes \n",
"4 1665 Female 79.0 1 0 Yes \n",
"... ... ... ... ... ... ... \n",
"5105 18234 Female 80.0 1 0 Yes \n",
"5106 44873 Female 81.0 0 0 Yes \n",
"5107 19723 Female 35.0 0 0 Yes \n",
"5108 37544 Male 51.0 0 0 Yes \n",
"5109 44679 Female 44.0 0 0 Yes \n",
"\n",
" work_type Residence_type avg_glucose_level bmi smoking_status \\\n",
"0 Private Urban 228.69 36.6 formerly smoked \n",
"1 Self-employed Rural 202.21 NaN never smoked \n",
"2 Private Rural 105.92 32.5 never smoked \n",
"3 Private Urban 171.23 34.4 smokes \n",
"4 Self-employed Rural 174.12 24.0 never smoked \n",
"... ... ... ... ... ... \n",
"5105 Private Urban 83.75 NaN never smoked \n",
"5106 Self-employed Urban 125.20 40.0 never smoked \n",
"5107 Self-employed Rural 82.99 30.6 never smoked \n",
"5108 Private Rural 166.29 25.6 formerly smoked \n",
"5109 Govt_job Urban 85.28 26.2 Unknown \n",
"\n",
" stroke \n",
"0 1 \n",
"1 1 \n",
"2 1 \n",
"3 1 \n",
"4 1 \n",
"... ... \n",
"5105 0 \n",
"5106 0 \n",
"5107 0 \n",
"5108 0 \n",
"5109 0 \n",
"\n",
"[5110 rows x 12 columns]>"
]
},
"execution_count": 84,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data_base.info"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<p style=\"text-align: center;\"><i>Вызов иной функции для удобного просмотра столбцов и их значений во время выполнения лабы</i></p>"
]
},
{
"cell_type": "code",
"execution_count": 85,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['id', 'gender', 'age', 'hypertension', 'heart_disease', 'ever_married',\n",
" 'work_type', 'Residence_type', 'avg_glucose_level', 'bmi',\n",
" 'smoking_status', 'stroke'],\n",
" dtype='object')"
]
},
"execution_count": 85,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data_base.columns"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<p style=\"text-align: center;\"><i>Тренируюсь со срезами...</i></p>"
2024-09-20 20:07:21 +04:00
]
},
{
"cell_type": "code",
2024-09-21 01:52:19 +04:00
"execution_count": 44,
2024-09-20 20:07:21 +04:00
"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>id</th>\n",
" <th>gender</th>\n",
" <th>age</th>\n",
" <th>hypertension</th>\n",
" <th>heart_disease</th>\n",
" <th>ever_married</th>\n",
" <th>work_type</th>\n",
" <th>Residence_type</th>\n",
" <th>avg_glucose_level</th>\n",
" <th>bmi</th>\n",
" <th>smoking_status</th>\n",
" <th>stroke</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
2024-09-21 01:52:19 +04:00
" <th>10</th>\n",
" <td>12109</td>\n",
2024-09-20 20:07:21 +04:00
" <td>Female</td>\n",
2024-09-21 01:52:19 +04:00
" <td>81.0</td>\n",
2024-09-20 20:07:21 +04:00
" <td>1</td>\n",
" <td>0</td>\n",
" <td>Yes</td>\n",
" <td>Private</td>\n",
" <td>Rural</td>\n",
2024-09-21 01:52:19 +04:00
" <td>80.43</td>\n",
" <td>29.7</td>\n",
2024-09-20 20:07:21 +04:00
" <td>never smoked</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
2024-09-21 01:52:19 +04:00
" <th>11</th>\n",
" <td>12095</td>\n",
2024-09-20 20:07:21 +04:00
" <td>Female</td>\n",
2024-09-21 01:52:19 +04:00
" <td>61.0</td>\n",
2024-09-20 20:07:21 +04:00
" <td>0</td>\n",
" <td>1</td>\n",
" <td>Yes</td>\n",
2024-09-21 01:52:19 +04:00
" <td>Govt_job</td>\n",
2024-09-20 20:07:21 +04:00
" <td>Rural</td>\n",
2024-09-21 01:52:19 +04:00
" <td>120.46</td>\n",
" <td>36.8</td>\n",
" <td>smokes</td>\n",
2024-09-20 20:07:21 +04:00
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
2024-09-21 01:52:19 +04:00
" id gender age hypertension heart_disease ever_married work_type \\\n",
"10 12109 Female 81.0 1 0 Yes Private \n",
"11 12095 Female 61.0 0 1 Yes Govt_job \n",
2024-09-20 20:07:21 +04:00
"\n",
2024-09-21 01:52:19 +04:00
" Residence_type avg_glucose_level bmi smoking_status stroke \n",
"10 Rural 80.43 29.7 never smoked 1 \n",
"11 Rural 120.46 36.8 smokes 1 "
]
},
"execution_count": 44,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data_base.loc[10:11]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<p style=\"text-align: center;\"><i>Все еще непонятной фигней занимаюсь...</i></p>"
]
},
{
"cell_type": "code",
"execution_count": 58,
"metadata": {},
"outputs": [],
"source": [
"new_data_base = data_base.sort_values(\"age\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<p style=\"text-align: center;\"><i>А тут уже что-то интересное.<br>Я отбираю количество (сколько раз встречается в таблице) каждое из значений колонки <b>\"статусурильщика\"</b> Потом с помощью функции plot отрисовываю круговую диаграмму</i></p>"
]
},
{
"cell_type": "code",
"execution_count": 83,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Text(0.5, 1.0, 'Диаграмма людей с разным статусaми курения')"
]
},
"execution_count": 83,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"smoking_status_count = data_base[\"smoking_status\"].value_counts().plot(kind='pie')\n",
"\n",
"# smoking_status_count.plot(kind='bar')\n",
"plt.title(\"Диаграмма людей с разным статусaми курения\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<p style=\"text-align: center;\"><i>Здесь я делаю то же самое, только теперь стилизую диаграмму (area) - подписываю <b>x</b> и <b>y</b> оси, добавляю <b>title</b></i></p>\n"
]
},
{
"cell_type": "code",
"execution_count": 82,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Text(0, 0.5, 'количество людей')"
]
},
"execution_count": 82,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"data_base[\"smoking_status\"].value_counts().plot(kind='area')\n",
"\n",
"# smoking_status_count.plot(kind='bar')\n",
"plt.title(\"Количество людей с разным статусaми курения\")\n",
"plt.xlabel(\"статусы курения\")\n",
"plt.ylabel(\"количество людей\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<p style=\"text-align: center;\"><i>Здесь не особо интересно - делаю гистограмму с разницой в количестве мужчин и женщин испытуемых</i></p>"
]
},
{
"cell_type": "code",
"execution_count": 90,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<Axes: xlabel='gender'>"
2024-09-20 20:07:21 +04:00
]
},
2024-09-21 01:52:19 +04:00
"execution_count": 90,
2024-09-20 20:07:21 +04:00
"metadata": {},
"output_type": "execute_result"
2024-09-21 01:52:19 +04:00
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"data_base[\"gender\"].value_counts().sort_values().plot(kind='bar')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<p style=\"text-align: center;\"><i>Здесь я беру данные по срезу (с 100-го челобрека по 300-го). И строю точечную диаграмму, которая отображает по иксам - курящий ли и насколько человек, а по игрекам - возраст</i></p>\n"
]
},
{
"cell_type": "code",
"execution_count": 107,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<Axes: xlabel='smoking_status', ylabel='age'>"
]
},
"execution_count": 107,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
2024-09-20 20:07:21 +04:00
}
],
"source": [
2024-09-21 01:52:19 +04:00
"data_base.loc[100:300].plot.scatter(x=\"smoking_status\", y=\"age\")"
2024-09-20 20:07:21 +04:00
]
}
],
"metadata": {
"kernelspec": {
"display_name": "venv",
"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": "3.12.6"
}
},
"nbformat": 4,
"nbformat_minor": 2
}