1391 lines
68 KiB
Plaintext
1391 lines
68 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 19,
|
||
"id": "2a7ae8ac-8304-4a26-8eac-63eedff991e2",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Collecting matplotlib\n",
|
||
" Downloading matplotlib-3.7.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (11.6 MB)\n",
|
||
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m11.6/11.6 MB\u001b[0m \u001b[31m19.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
|
||
"\u001b[?25hCollecting pyparsing>=2.3.1\n",
|
||
" Downloading pyparsing-3.0.9-py3-none-any.whl (98 kB)\n",
|
||
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m98.3/98.3 KB\u001b[0m \u001b[31m39.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
||
"\u001b[?25hCollecting contourpy>=1.0.1\n",
|
||
" Downloading contourpy-1.0.7-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (300 kB)\n",
|
||
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m300.3/300.3 KB\u001b[0m \u001b[31m56.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
||
"\u001b[?25hCollecting fonttools>=4.22.0\n",
|
||
" Downloading fonttools-4.39.3-py3-none-any.whl (1.0 MB)\n",
|
||
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.0/1.0 MB\u001b[0m \u001b[31m36.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
||
"\u001b[?25hCollecting cycler>=0.10\n",
|
||
" Downloading cycler-0.11.0-py3-none-any.whl (6.4 kB)\n",
|
||
"Requirement already satisfied: numpy>=1.20 in /opt/jupyterhub/lib/python3.10/site-packages (from matplotlib) (1.24.3)\n",
|
||
"Collecting pillow>=6.2.0\n",
|
||
" Downloading Pillow-9.5.0-cp310-cp310-manylinux_2_28_x86_64.whl (3.4 MB)\n",
|
||
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.4/3.4 MB\u001b[0m \u001b[31m37.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
|
||
"\u001b[?25hRequirement already satisfied: python-dateutil>=2.7 in /opt/jupyterhub/lib/python3.10/site-packages (from matplotlib) (2.8.2)\n",
|
||
"Requirement already satisfied: packaging>=20.0 in /opt/jupyterhub/lib/python3.10/site-packages (from matplotlib) (23.1)\n",
|
||
"Collecting kiwisolver>=1.0.1\n",
|
||
" Downloading kiwisolver-1.4.4-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (1.6 MB)\n",
|
||
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m50.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
||
"\u001b[?25hRequirement already satisfied: six>=1.5 in /opt/jupyterhub/lib/python3.10/site-packages (from python-dateutil>=2.7->matplotlib) (1.16.0)\n",
|
||
"Installing collected packages: pyparsing, pillow, kiwisolver, fonttools, cycler, contourpy, matplotlib\n",
|
||
"Successfully installed contourpy-1.0.7 cycler-0.11.0 fonttools-4.39.3 kiwisolver-1.4.4 matplotlib-3.7.1 pillow-9.5.0 pyparsing-3.0.9\n",
|
||
"Note: you may need to restart the kernel to use updated packages.\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"pip install matplotlib"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 3,
|
||
"id": "d686eef9-708c-437d-b4ff-9eb69fe207dd",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Collecting pandas\n",
|
||
" Downloading pandas-2.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (12.3 MB)\n",
|
||
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.3/12.3 MB\u001b[0m \u001b[31m20.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
|
||
"\u001b[?25hCollecting numpy>=1.21.0\n",
|
||
" Downloading numpy-1.24.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (17.3 MB)\n",
|
||
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m17.3/17.3 MB\u001b[0m \u001b[31m45.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
|
||
"\u001b[?25hRequirement already satisfied: python-dateutil>=2.8.2 in /opt/jupyterhub/lib/python3.10/site-packages (from pandas) (2.8.2)\n",
|
||
"Collecting pytz>=2020.1\n",
|
||
" Downloading pytz-2023.3-py2.py3-none-any.whl (502 kB)\n",
|
||
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m502.3/502.3 KB\u001b[0m \u001b[31m92.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
||
"\u001b[?25hCollecting tzdata>=2022.1\n",
|
||
" Downloading tzdata-2023.3-py2.py3-none-any.whl (341 kB)\n",
|
||
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m341.8/341.8 KB\u001b[0m \u001b[31m73.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
||
"\u001b[?25hRequirement already satisfied: six>=1.5 in /opt/jupyterhub/lib/python3.10/site-packages (from python-dateutil>=2.8.2->pandas) (1.16.0)\n",
|
||
"Installing collected packages: pytz, tzdata, numpy, pandas\n",
|
||
"Successfully installed numpy-1.24.3 pandas-2.0.1 pytz-2023.3 tzdata-2023.3\n",
|
||
"Note: you may need to restart the kernel to use updated packages.\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"pip install pandas"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 31,
|
||
"id": "142ecefe-9ba4-4963-94cc-227cffeb675a",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"url = \"https://pixees.fr/informatiquelycee/n_site/asset/titanic.csv\""
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 32,
|
||
"id": "66cf541f-6352-42ea-8ea9-983da560943b",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import pandas as pd\n",
|
||
"data = pd.io.parsers.read_csv(url)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 33,
|
||
"id": "c235943b-283e-4e95-97fc-e9d4bf2cbf03",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"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>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 "
|
||
]
|
||
},
|
||
"execution_count": 33,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"data.head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 34,
|
||
"id": "b4d51fb4-57e2-4a0a-a7db-8fd6a7a48b35",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"<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"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"data.info()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 35,
|
||
"id": "1cb2c436-40f9-406d-96fa-bacd4961c39e",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"Index(['PassengerId', 'Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp',\n",
|
||
" 'Parch', 'Ticket', 'Fare', 'Cabin', 'Embarked'],\n",
|
||
" dtype='object')"
|
||
]
|
||
},
|
||
"execution_count": 35,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"data.columns"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 36,
|
||
"id": "7f8c19fa-ebf1-4138-aad7-922cda8b9c8f",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"data = data.drop(['Name', 'PassengerId', 'SibSp', 'Parch', 'Ticket', 'Fare', 'Cabin', 'Embarked'], axis=1)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 37,
|
||
"id": "7d0eb444-da4e-40f4-887e-5e85f91713e5",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"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>Survived</th>\n",
|
||
" <th>Pclass</th>\n",
|
||
" <th>Sex</th>\n",
|
||
" <th>Age</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>886</th>\n",
|
||
" <td>0</td>\n",
|
||
" <td>2</td>\n",
|
||
" <td>male</td>\n",
|
||
" <td>27.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>887</th>\n",
|
||
" <td>1</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>female</td>\n",
|
||
" <td>19.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>888</th>\n",
|
||
" <td>0</td>\n",
|
||
" <td>3</td>\n",
|
||
" <td>female</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>889</th>\n",
|
||
" <td>1</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>male</td>\n",
|
||
" <td>26.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>890</th>\n",
|
||
" <td>0</td>\n",
|
||
" <td>3</td>\n",
|
||
" <td>male</td>\n",
|
||
" <td>32.0</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" Survived Pclass Sex Age\n",
|
||
"886 0 2 male 27.0\n",
|
||
"887 1 1 female 19.0\n",
|
||
"888 0 3 female NaN\n",
|
||
"889 1 1 male 26.0\n",
|
||
"890 0 3 male 32.0"
|
||
]
|
||
},
|
||
"execution_count": 37,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"data.tail()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 38,
|
||
"id": "d111faf3-636f-473f-aeb4-594db31b0058",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"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>Survived</th>\n",
|
||
" <th>Pclass</th>\n",
|
||
" <th>Sex</th>\n",
|
||
" <th>Age</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>0</td>\n",
|
||
" <td>3</td>\n",
|
||
" <td>male</td>\n",
|
||
" <td>22.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>1</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>female</td>\n",
|
||
" <td>38.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>1</td>\n",
|
||
" <td>3</td>\n",
|
||
" <td>female</td>\n",
|
||
" <td>26.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>1</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>female</td>\n",
|
||
" <td>35.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>0</td>\n",
|
||
" <td>3</td>\n",
|
||
" <td>male</td>\n",
|
||
" <td>35.0</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" Survived Pclass Sex Age\n",
|
||
"0 0 3 male 22.0\n",
|
||
"1 1 1 female 38.0\n",
|
||
"2 1 3 female 26.0\n",
|
||
"3 1 1 female 35.0\n",
|
||
"4 0 3 male 35.0"
|
||
]
|
||
},
|
||
"execution_count": 38,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"data.head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 39,
|
||
"id": "6e4a366a-fecd-4882-a47e-f0c1dec09a3a",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"data = data.dropna(axis=0)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 40,
|
||
"id": "84b2e1f7-158b-4ccd-af2c-6512b0d69fd7",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
" Survived Pclass Sex Age\n",
|
||
"0 0 3 male 22.0\n",
|
||
"1 1 1 female 38.0\n",
|
||
"2 1 3 female 26.0\n",
|
||
"3 1 1 female 35.0\n",
|
||
"4 0 3 male 35.0\n",
|
||
".. ... ... ... ...\n",
|
||
"885 0 3 female 39.0\n",
|
||
"886 0 2 male 27.0\n",
|
||
"887 1 1 female 19.0\n",
|
||
"889 1 1 male 26.0\n",
|
||
"890 0 3 male 32.0\n",
|
||
"\n",
|
||
"[714 rows x 4 columns]\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"print(data)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 41,
|
||
"id": "7b6d896e-6181-4b5c-95f8-5cdd5d57eb4f",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"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>Survived</th>\n",
|
||
" <th>Pclass</th>\n",
|
||
" <th>Age</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>count</th>\n",
|
||
" <td>714.000000</td>\n",
|
||
" <td>714.000000</td>\n",
|
||
" <td>714.000000</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>mean</th>\n",
|
||
" <td>0.406162</td>\n",
|
||
" <td>2.236695</td>\n",
|
||
" <td>29.699118</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>std</th>\n",
|
||
" <td>0.491460</td>\n",
|
||
" <td>0.838250</td>\n",
|
||
" <td>14.526497</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>min</th>\n",
|
||
" <td>0.000000</td>\n",
|
||
" <td>1.000000</td>\n",
|
||
" <td>0.420000</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>25%</th>\n",
|
||
" <td>0.000000</td>\n",
|
||
" <td>1.000000</td>\n",
|
||
" <td>20.125000</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>50%</th>\n",
|
||
" <td>0.000000</td>\n",
|
||
" <td>2.000000</td>\n",
|
||
" <td>28.000000</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>75%</th>\n",
|
||
" <td>1.000000</td>\n",
|
||
" <td>3.000000</td>\n",
|
||
" <td>38.000000</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>max</th>\n",
|
||
" <td>1.000000</td>\n",
|
||
" <td>3.000000</td>\n",
|
||
" <td>80.000000</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" Survived Pclass Age\n",
|
||
"count 714.000000 714.000000 714.000000\n",
|
||
"mean 0.406162 2.236695 29.699118\n",
|
||
"std 0.491460 0.838250 14.526497\n",
|
||
"min 0.000000 1.000000 0.420000\n",
|
||
"25% 0.000000 1.000000 20.125000\n",
|
||
"50% 0.000000 2.000000 28.000000\n",
|
||
"75% 1.000000 3.000000 38.000000\n",
|
||
"max 1.000000 3.000000 80.000000"
|
||
]
|
||
},
|
||
"execution_count": 41,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"data.describe()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 42,
|
||
"id": "0851d3d0-9cb4-424f-b9da-32482e58f4ed",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"Pclass\n",
|
||
"3 355\n",
|
||
"1 186\n",
|
||
"2 173\n",
|
||
"Name: count, dtype: int64"
|
||
]
|
||
},
|
||
"execution_count": 42,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"data['Pclass'].value_counts()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 43,
|
||
"id": "6f6bbbb4-ab72-4d49-9a4d-4aedfaa596bd",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import matplotlib as plt"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 44,
|
||
"id": "100db300-eb44-45c6-9e13-01b515d7408f",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"<Axes: xlabel='Pclass'>"
|
||
]
|
||
},
|
||
"execution_count": 44,
|
||
"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['Pclass'].value_counts().plot.bar()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 45,
|
||
"id": "b77929c9-cafb-4ead-b6f3-1d84084fc6dd",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"<Axes: >"
|
||
]
|
||
},
|
||
"execution_count": 45,
|
||
"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['Age'].hist()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 46,
|
||
"id": "d2f480dd-d7bc-4669-ac68-70871b9fdf83",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"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>Survived</th>\n",
|
||
" <th>Pclass</th>\n",
|
||
" <th>Age</th>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>Sex</th>\n",
|
||
" <th></th>\n",
|
||
" <th></th>\n",
|
||
" <th></th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>female</th>\n",
|
||
" <td>0.754789</td>\n",
|
||
" <td>2.065134</td>\n",
|
||
" <td>27.915709</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>male</th>\n",
|
||
" <td>0.205298</td>\n",
|
||
" <td>2.335541</td>\n",
|
||
" <td>30.726645</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" Survived Pclass Age\n",
|
||
"Sex \n",
|
||
"female 0.754789 2.065134 27.915709\n",
|
||
"male 0.205298 2.335541 30.726645"
|
||
]
|
||
},
|
||
"execution_count": 46,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"data.groupby(['Sex']).mean()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 52,
|
||
"id": "84bef046-7ee8-461c-b166-87ff1271fcb9",
|
||
"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>Survived</th>\n",
|
||
" <th>Pclass</th>\n",
|
||
" <th>Sex</th>\n",
|
||
" <th>Age</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>0</td>\n",
|
||
" <td>3</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>22.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>1</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>38.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>1</td>\n",
|
||
" <td>3</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>26.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>1</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>35.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>0</td>\n",
|
||
" <td>3</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>35.0</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" Survived Pclass Sex Age\n",
|
||
"0 0 3 0 22.0\n",
|
||
"1 1 1 1 38.0\n",
|
||
"2 1 3 1 26.0\n",
|
||
"3 1 1 1 35.0\n",
|
||
"4 0 3 0 35.0"
|
||
]
|
||
},
|
||
"execution_count": 52,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"data['Sex'].replace(['male', 'female'], [0, 1], inplace = True)\n",
|
||
"data.head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 55,
|
||
"id": "32d318f6-b55f-453e-ad18-373300eafcbf",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Collecting sklearn\n",
|
||
" Downloading sklearn-0.0.post5.tar.gz (3.7 kB)\n",
|
||
" Preparing metadata (setup.py) ... \u001b[?25ldone\n",
|
||
"\u001b[?25hBuilding wheels for collected packages: sklearn\n",
|
||
" Building wheel for sklearn (setup.py) ... \u001b[?25ldone\n",
|
||
"\u001b[?25h Created wheel for sklearn: filename=sklearn-0.0.post5-py3-none-any.whl size=2359 sha256=27bbea85f6603a3901da4612f859fed8f5ab0b3ab0ea81e2b102edf3f244042c\n",
|
||
" Stored in directory: /home/sbah/.cache/pip/wheels/38/1f/8d/4f812c590e074c1e928f5cec67bf5053b71f38e2648739403a\n",
|
||
"Successfully built sklearn\n",
|
||
"Installing collected packages: sklearn\n",
|
||
"Successfully installed sklearn-0.0.post5\n",
|
||
"Note: you may need to restart the kernel to use updated packages.\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"pip install sklearn"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 60,
|
||
"id": "4f796b2c-23c1-4871-8cc8-2717d5cbd9b5",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Collecting scikit-learn\n",
|
||
" Downloading scikit_learn-1.2.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (9.6 MB)\n",
|
||
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.6/9.6 MB\u001b[0m \u001b[31m15.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
|
||
"\u001b[?25hRequirement already satisfied: numpy>=1.17.3 in /opt/jupyterhub/lib/python3.10/site-packages (from scikit-learn) (1.24.3)\n",
|
||
"Collecting scipy>=1.3.2\n",
|
||
" Downloading scipy-1.10.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (34.4 MB)\n",
|
||
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m34.4/34.4 MB\u001b[0m \u001b[31m38.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
|
||
"\u001b[?25hCollecting threadpoolctl>=2.0.0\n",
|
||
" Downloading threadpoolctl-3.1.0-py3-none-any.whl (14 kB)\n",
|
||
"Collecting joblib>=1.1.1\n",
|
||
" Downloading joblib-1.2.0-py3-none-any.whl (297 kB)\n",
|
||
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m298.0/298.0 KB\u001b[0m \u001b[31m64.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
||
"\u001b[?25hInstalling collected packages: threadpoolctl, scipy, joblib, scikit-learn\n",
|
||
"Successfully installed joblib-1.2.0 scikit-learn-1.2.2 scipy-1.10.1 threadpoolctl-3.1.0\n",
|
||
"Note: you may need to restart the kernel to use updated packages.\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"pip install scikit-learn"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 63,
|
||
"id": "794fd998-9c17-4394-b5cb-733f3a7579fa",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"from sklearn.neighbors import KNeighborsClassifier"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 64,
|
||
"id": "0b731dc4-79e2-4192-a999-01c16462e941",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"model = KNeighborsClassifier()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 66,
|
||
"id": "9b32b8c9-49a4-4d67-b34a-0634bba52a12",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
" Y = data['Survived']"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 69,
|
||
"id": "2266c002-40b8-4d33-806b-9eea57f89ce1",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"X = data.drop('Survived',axis=1)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 70,
|
||
"id": "d9cc1284-1df6-4453-9f85-c7144ea86ad8",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"0 0\n",
|
||
"1 1\n",
|
||
"2 1\n",
|
||
"3 1\n",
|
||
"4 0\n",
|
||
" ..\n",
|
||
"885 0\n",
|
||
"886 0\n",
|
||
"887 1\n",
|
||
"889 1\n",
|
||
"890 0\n",
|
||
"Name: Survived, Length: 714, dtype: int64"
|
||
]
|
||
},
|
||
"execution_count": 70,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"Y"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 71,
|
||
"id": "1c3d641d-f9f5-4308-897d-670e870f3ba7",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"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>Pclass</th>\n",
|
||
" <th>Sex</th>\n",
|
||
" <th>Age</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>3</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>22.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>1</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>38.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>3</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>26.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>1</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>35.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>3</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>35.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>...</th>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>885</th>\n",
|
||
" <td>3</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>39.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>886</th>\n",
|
||
" <td>2</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>27.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>887</th>\n",
|
||
" <td>1</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>19.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>889</th>\n",
|
||
" <td>1</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>26.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>890</th>\n",
|
||
" <td>3</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>32.0</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"<p>714 rows × 3 columns</p>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" Pclass Sex Age\n",
|
||
"0 3 0 22.0\n",
|
||
"1 1 1 38.0\n",
|
||
"2 3 1 26.0\n",
|
||
"3 1 1 35.0\n",
|
||
"4 3 0 35.0\n",
|
||
".. ... ... ...\n",
|
||
"885 3 1 39.0\n",
|
||
"886 2 0 27.0\n",
|
||
"887 1 1 19.0\n",
|
||
"889 1 0 26.0\n",
|
||
"890 3 0 32.0\n",
|
||
"\n",
|
||
"[714 rows x 3 columns]"
|
||
]
|
||
},
|
||
"execution_count": 71,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"X"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 72,
|
||
"id": "13e2a59c-fa67-4eda-a476-901f6b16c7c8",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"0.8305322128851541"
|
||
]
|
||
},
|
||
"execution_count": 72,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"model.fit(X, Y)\n",
|
||
"model.score(X, Y)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 73,
|
||
"id": "83d889f6-bf26-45f6-bd7d-487cec9a5907",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"array([0, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0,\n",
|
||
" 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 1, 0, 0, 0, 1,\n",
|
||
" 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0,\n",
|
||
" 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0,\n",
|
||
" 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0,\n",
|
||
" 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0,\n",
|
||
" 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 1,\n",
|
||
" 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 1, 0, 1,\n",
|
||
" 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1,\n",
|
||
" 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 1,\n",
|
||
" 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1,\n",
|
||
" 0, 1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1,\n",
|
||
" 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0,\n",
|
||
" 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1,\n",
|
||
" 0, 1, 1, 1, 1, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 1,\n",
|
||
" 0, 1, 0, 1, 1, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0, 1, 0, 0, 1, 0, 1, 0,\n",
|
||
" 0, 0, 0, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 0,\n",
|
||
" 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1,\n",
|
||
" 1, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 1, 0,\n",
|
||
" 1, 0, 0, 1, 0, 0, 1, 0, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0,\n",
|
||
" 1, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 1, 0, 1, 1, 0,\n",
|
||
" 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 1, 1, 1, 0, 0,\n",
|
||
" 1, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 1, 0, 0, 0,\n",
|
||
" 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0,\n",
|
||
" 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0,\n",
|
||
" 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 1, 0,\n",
|
||
" 1, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0,\n",
|
||
" 1, 1, 0, 1, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0,\n",
|
||
" 1, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0,\n",
|
||
" 1, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 1, 0, 1,\n",
|
||
" 0, 1, 1, 1, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1,\n",
|
||
" 1, 0, 1, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0, 1,\n",
|
||
" 1, 0, 1, 0, 0, 0, 0, 1, 1, 0])"
|
||
]
|
||
},
|
||
"execution_count": 73,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"model.predict(X)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 81,
|
||
"id": "c09f26a4-c768-4e88-88b1-c3182e68269d",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"def survie(model, pclass=3, Sex=0, Age=26):\n",
|
||
" X = np.array([pclass, Sex, Age]).reshape(1, 3)\n",
|
||
" print(model.predict_proba(X))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 78,
|
||
"id": "bf549553-c0c8-4637-8183-24df40bef4f4",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import numpy as np"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 82,
|
||
"id": "a666e946-670b-4681-8f82-ef06fb47924c",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"[[0.6 0.4]]\n"
|
||
]
|
||
},
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"/opt/jupyterhub/lib/python3.10/site-packages/sklearn/base.py:439: UserWarning: X does not have valid feature names, but KNeighborsClassifier was fitted with feature names\n",
|
||
" warnings.warn(\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"survie(model)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "1637e7dd-54a3-4676-a8c9-f76a226d669d",
|
||
"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": "3.10.6"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 5
|
||
}
|