{
"cells": [
{
"cell_type": "code",
"execution_count": 37,
"id": "3347bb59-0e96-4dc9-9be6-fb447147d50e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Первые 5 строк данных:\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>PassengerId</th>\n",
" <th>Survived</th>\n",
" <th>Pclass</th>\n",
" <th>Name</th>\n",
" <th>Sex</th>\n",
" <th>Age</th>\n",
" <th>SibSp</th>\n",
" <th>Parch</th>\n",
" <th>Ticket</th>\n",
" <th>Fare</th>\n",
" <th>Cabin</th>\n",
" <th>Embarked</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>Braund, Mr. Owen Harris</td>\n",
" <td>male</td>\n",
" <td>22.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>A/5 21171</td>\n",
" <td>7.2500</td>\n",
" <td>NaN</td>\n",
" <td>S</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
" <td>female</td>\n",
" <td>38.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>PC 17599</td>\n",
" <td>71.2833</td>\n",
" <td>C85</td>\n",
" <td>C</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" <td>Heikkinen, Miss. Laina</td>\n",
" <td>female</td>\n",
" <td>26.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>STON/O2. 3101282</td>\n",
" <td>7.9250</td>\n",
" <td>NaN</td>\n",
" <td>S</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
" <td>female</td>\n",
" <td>35.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>113803</td>\n",
" <td>53.1000</td>\n",
" <td>C123</td>\n",
" <td>S</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>Allen, Mr. William Henry</td>\n",
" <td>male</td>\n",
" <td>35.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>373450</td>\n",
" <td>8.0500</td>\n",
" <td>NaN</td>\n",
" <td>S</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" PassengerId Survived Pclass \\\n",
"0 1 0 3 \n",
"1 2 1 1 \n",
"2 3 1 3 \n",
"3 4 1 1 \n",
"4 5 0 3 \n",
"\n",
" Name Sex Age SibSp \\\n",
"0 Braund, Mr. Owen Harris male 22.0 1 \n",
"1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1 \n",
"2 Heikkinen, Miss. Laina female 26.0 0 \n",
"3 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1 \n",
"4 Allen, Mr. William Henry male 35.0 0 \n",
"\n",
" Parch Ticket Fare Cabin Embarked \n",
"0 0 A/5 21171 7.2500 NaN S \n",
"1 0 PC 17599 71.2833 C85 C \n",
"2 0 STON/O2. 3101282 7.9250 NaN S \n",
"3 0 113803 53.1000 C123 S \n",
"4 0 373450 8.0500 NaN S "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import pandas as pd\n",
"from tqdm import tqdm \n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"df = pd.read_csv(\"train.csv\")\n",
"print(\"Первые 5 строк данных:\")\n",
"display(df.head())"
]
},
{
"cell_type": "code",
"execution_count": 38,
"id": "03484d47-e142-43ff-94a3-5b40e2a308e2",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Информация о датасете:\n",
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 891 entries, 0 to 890\n",
"Data columns (total 12 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 PassengerId 891 non-null int64 \n",
" 1 Survived 891 non-null int64 \n",
" 2 Pclass 891 non-null int64 \n",
" 3 Name 891 non-null object \n",
" 4 Sex 891 non-null object \n",
" 5 Age 714 non-null float64\n",
" 6 SibSp 891 non-null int64 \n",
" 7 Parch 891 non-null int64 \n",
" 8 Ticket 891 non-null object \n",
" 9 Fare 891 non-null float64\n",
" 10 Cabin 204 non-null object \n",
" 11 Embarked 889 non-null object \n",
"dtypes: float64(2), int64(5), object(5)\n",
"memory usage: 83.7+ KB\n"
]
},
{
"data": {
"text/plain": [
"None"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Описательная статистика:\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>PassengerId</th>\n",
" <th>Survived</th>\n",
" <th>Pclass</th>\n",
" <th>Age</th>\n",
" <th>SibSp</th>\n",
" <th>Parch</th>\n",
" <th>Fare</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>891.000000</td>\n",
" <td>891.000000</td>\n",
" <td>891.000000</td>\n",
" <td>714.000000</td>\n",
" <td>891.000000</td>\n",
" <td>891.000000</td>\n",
" <td>891.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>446.000000</td>\n",
" <td>0.383838</td>\n",
" <td>2.308642</td>\n",
" <td>29.699118</td>\n",
" <td>0.523008</td>\n",
" <td>0.381594</td>\n",
" <td>32.204208</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>257.353842</td>\n",
" <td>0.486592</td>\n",
" <td>0.836071</td>\n",
" <td>14.526497</td>\n",
" <td>1.102743</td>\n",
" <td>0.806057</td>\n",
" <td>49.693429</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>1.000000</td>\n",
" <td>0.000000</td>\n",
" <td>1.000000</td>\n",
" <td>0.420000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>223.500000</td>\n",
" <td>0.000000</td>\n",
" <td>2.000000</td>\n",
" <td>20.125000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>7.910400</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>446.000000</td>\n",
" <td>0.000000</td>\n",
" <td>3.000000</td>\n",
" <td>28.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>14.454200</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>668.500000</td>\n",
" <td>1.000000</td>\n",
" <td>3.000000</td>\n",
" <td>38.000000</td>\n",
" <td>1.000000</td>\n",
" <td>0.000000</td>\n",
" <td>31.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>891.000000</td>\n",
" <td>1.000000</td>\n",
" <td>3.000000</td>\n",
" <td>80.000000</td>\n",
" <td>8.000000</td>\n",
" <td>6.000000</td>\n",
" <td>512.329200</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" PassengerId Survived Pclass Age SibSp \\\n",
"count 891.000000 891.000000 891.000000 714.000000 891.000000 \n",
"mean 446.000000 0.383838 2.308642 29.699118 0.523008 \n",
"std 257.353842 0.486592 0.836071 14.526497 1.102743 \n",
"min 1.000000 0.000000 1.000000 0.420000 0.000000 \n",
"25% 223.500000 0.000000 2.000000 20.125000 0.000000 \n",
"50% 446.000000 0.000000 3.000000 28.000000 0.000000 \n",
"75% 668.500000 1.000000 3.000000 38.000000 1.000000 \n",
"max 891.000000 1.000000 3.000000 80.000000 8.000000 \n",
"\n",
" Parch Fare \n",
"count 891.000000 891.000000 \n",
"mean 0.381594 32.204208 \n",
"std 0.806057 49.693429 \n",
"min 0.000000 0.000000 \n",
"25% 0.000000 7.910400 \n",
"50% 0.000000 14.454200 \n",
"75% 0.000000 31.000000 \n",
"max 6.000000 512.329200 "
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Пропущенные значения:\n"
]
},
{
"data": {
"text/plain": [
"PassengerId 0\n",
"Survived 0\n",
"Pclass 0\n",
"Name 0\n",
"Sex 0\n",
"Age 177\n",
"SibSp 0\n",
"Parch 0\n",
"Ticket 0\n",
"Fare 0\n",
"Cabin 687\n",
"Embarked 2\n",
"dtype: int64"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"print(\"\\nИнформация о датасете:\")\n",
"display(df.info())\n",
"print(\"\\nОписательная статистика:\")\n",
"display(df.describe())\n",
"print(\"\\nПропущенные значения:\")\n",
"display(df.isnull().sum())"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f71e6a06-5a32-4b41-a043-b03b3f7e4a56",
"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": "3.13.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}