DataAnalystAndTrainModel.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "a21d3203",
   "metadata": {
    "papermill": {
     "duration": 0.00909,
     "end_time": "2024-02-20T04:24:45.167333",
     "exception": false,
     "start_time": "2024-02-20T04:24:45.158243",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## Import Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "a6a8542c",
   "metadata": {
    "_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19",
    "_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5",
    "execution": {
     "iopub.execute_input": "2024-02-20T04:24:45.187336Z",
     "iopub.status.busy": "2024-02-20T04:24:45.186813Z",
     "iopub.status.idle": "2024-02-20T04:24:48.132814Z",
     "shell.execute_reply": "2024-02-20T04:24:48.131725Z"
    },
    "papermill": {
     "duration": 2.959157,
     "end_time": "2024-02-20T04:24:48.135682",
     "exception": false,
     "start_time": "2024-02-20T04:24:45.176525",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "import os\n",
    "# data analysis and wrangling\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import random as rnd\n",
    "\n",
    "# visualization\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "\n",
    "# Algoritmos de aprendizaje automático\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.svm import SVC, LinearSVC\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "from sklearn.linear_model import Perceptron\n",
    "from sklearn.linear_model import SGDClassifier\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.ensemble import GradientBoostingClassifier\n",
    "from sklearn.ensemble import AdaBoostClassifier\n",
    "from sklearn.neural_network import MLPClassifier"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fdd19cac",
   "metadata": {
    "papermill": {
     "duration": 0.008113,
     "end_time": "2024-02-20T04:24:48.152138",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.144025",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## Load data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "5c22601a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-02-20T04:24:48.171274Z",
     "iopub.status.busy": "2024-02-20T04:24:48.170764Z",
     "iopub.status.idle": "2024-02-20T04:24:48.223286Z",
     "shell.execute_reply": "2024-02-20T04:24:48.222181Z"
    },
    "papermill": {
     "duration": 0.065324,
     "end_time": "2024-02-20T04:24:48.225695",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.160371",
     "status": "completed"
    },
    "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>210</th>\n",
       "      <td>211</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Ali, Mr. Ahmed</td>\n",
       "      <td>male</td>\n",
       "      <td>24.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>SOTON/O.Q. 3101311</td>\n",
       "      <td>7.0500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>361</th>\n",
       "      <td>362</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>del Carlo, Mr. Sebastiano</td>\n",
       "      <td>male</td>\n",
       "      <td>29.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>SC/PARIS 2167</td>\n",
       "      <td>27.7208</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>510</th>\n",
       "      <td>511</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Daly, Mr. Eugene Patrick</td>\n",
       "      <td>male</td>\n",
       "      <td>29.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>382651</td>\n",
       "      <td>7.7500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>339</th>\n",
       "      <td>340</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Blackwell, Mr. Stephen Weart</td>\n",
       "      <td>male</td>\n",
       "      <td>45.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>113784</td>\n",
       "      <td>35.5000</td>\n",
       "      <td>T</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>674</th>\n",
       "      <td>675</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>Watson, Mr. Ennis Hastings</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>239856</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Survived  Pclass                          Name   Sex   Age  \\\n",
       "210          211         0       3                Ali, Mr. Ahmed  male  24.0   \n",
       "361          362         0       2     del Carlo, Mr. Sebastiano  male  29.0   \n",
       "510          511         1       3      Daly, Mr. Eugene Patrick  male  29.0   \n",
       "339          340         0       1  Blackwell, Mr. Stephen Weart  male  45.0   \n",
       "674          675         0       2    Watson, Mr. Ennis Hastings  male   NaN   \n",
       "\n",
       "     SibSp  Parch              Ticket     Fare Cabin Embarked  \n",
       "210      0      0  SOTON/O.Q. 3101311   7.0500   NaN        S  \n",
       "361      1      0       SC/PARIS 2167  27.7208   NaN        C  \n",
       "510      0      0              382651   7.7500   NaN        Q  \n",
       "339      0      0              113784  35.5000     T        S  \n",
       "674      0      0              239856   0.0000   NaN        S  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train = pd.read_csv(\"/kaggle/input/titanic/train.csv\")\n",
    "df_train.sample(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "80dd0b31",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-02-20T04:24:48.244338Z",
     "iopub.status.busy": "2024-02-20T04:24:48.243929Z",
     "iopub.status.idle": "2024-02-20T04:24:48.270714Z",
     "shell.execute_reply": "2024-02-20T04:24:48.269328Z"
    },
    "papermill": {
     "duration": 0.039222,
     "end_time": "2024-02-20T04:24:48.273432",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.234210",
     "status": "completed"
    },
    "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>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>374</th>\n",
       "      <td>1266</td>\n",
       "      <td>1</td>\n",
       "      <td>Dodge, Mrs. Washington (Ruth Vidaver)</td>\n",
       "      <td>female</td>\n",
       "      <td>54.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>33638</td>\n",
       "      <td>81.8583</td>\n",
       "      <td>A34</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>86</th>\n",
       "      <td>978</td>\n",
       "      <td>3</td>\n",
       "      <td>Barry, Miss. Julia</td>\n",
       "      <td>female</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>330844</td>\n",
       "      <td>7.8792</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>138</th>\n",
       "      <td>1030</td>\n",
       "      <td>3</td>\n",
       "      <td>Drapkin, Miss. Jennie</td>\n",
       "      <td>female</td>\n",
       "      <td>23.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>SOTON/OQ 392083</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>164</th>\n",
       "      <td>1056</td>\n",
       "      <td>2</td>\n",
       "      <td>Peruschitz, Rev. Joseph Maria</td>\n",
       "      <td>male</td>\n",
       "      <td>41.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>237393</td>\n",
       "      <td>13.0000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>232</th>\n",
       "      <td>1124</td>\n",
       "      <td>3</td>\n",
       "      <td>Wiklund, Mr. Karl Johan</td>\n",
       "      <td>male</td>\n",
       "      <td>21.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3101266</td>\n",
       "      <td>6.4958</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Pclass                                   Name     Sex   Age  \\\n",
       "374         1266       1  Dodge, Mrs. Washington (Ruth Vidaver)  female  54.0   \n",
       "86           978       3                     Barry, Miss. Julia  female  27.0   \n",
       "138         1030       3                  Drapkin, Miss. Jennie  female  23.0   \n",
       "164         1056       2          Peruschitz, Rev. Joseph Maria    male  41.0   \n",
       "232         1124       3                Wiklund, Mr. Karl Johan    male  21.0   \n",
       "\n",
       "     SibSp  Parch           Ticket     Fare Cabin Embarked  \n",
       "374      1      1            33638  81.8583   A34        S  \n",
       "86       0      0           330844   7.8792   NaN        Q  \n",
       "138      0      0  SOTON/OQ 392083   8.0500   NaN        S  \n",
       "164      0      0           237393  13.0000   NaN        S  \n",
       "232      1      0          3101266   6.4958   NaN        S  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_test = pd.read_csv(\"/kaggle/input/titanic/test.csv\")\n",
    "df_test.sample(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "26fc4ed1",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-02-20T04:24:48.294597Z",
     "iopub.status.busy": "2024-02-20T04:24:48.294141Z",
     "iopub.status.idle": "2024-02-20T04:24:48.326684Z",
     "shell.execute_reply": "2024-02-20T04:24:48.324706Z"
    },
    "papermill": {
     "duration": 0.046818,
     "end_time": "2024-02-20T04:24:48.329461",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.282643",
     "status": "completed"
    },
    "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",
      "\n",
      " ================================================== \n",
      "\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 418 entries, 0 to 417\n",
      "Data columns (total 11 columns):\n",
      " #   Column       Non-Null Count  Dtype  \n",
      "---  ------       --------------  -----  \n",
      " 0   PassengerId  418 non-null    int64  \n",
      " 1   Pclass       418 non-null    int64  \n",
      " 2   Name         418 non-null    object \n",
      " 3   Sex          418 non-null    object \n",
      " 4   Age          332 non-null    float64\n",
      " 5   SibSp        418 non-null    int64  \n",
      " 6   Parch        418 non-null    int64  \n",
      " 7   Ticket       418 non-null    object \n",
      " 8   Fare         417 non-null    float64\n",
      " 9   Cabin        91 non-null     object \n",
      " 10  Embarked     418 non-null    object \n",
      "dtypes: float64(2), int64(4), object(5)\n",
      "memory usage: 36.0+ KB\n"
     ]
    }
   ],
   "source": [
    "df_train.info()\n",
    "print(\"\\n\",'='*50,\"\\n\")\n",
    "df_test.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "0a7a4955",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-02-20T04:24:48.349925Z",
     "iopub.status.busy": "2024-02-20T04:24:48.349190Z",
     "iopub.status.idle": "2024-02-20T04:24:48.357433Z",
     "shell.execute_reply": "2024-02-20T04:24:48.356618Z"
    },
    "papermill": {
     "duration": 0.020823,
     "end_time": "2024-02-20T04:24:48.359642",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.338819",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "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"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "7483b325",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-02-20T04:24:48.380182Z",
     "iopub.status.busy": "2024-02-20T04:24:48.379450Z",
     "iopub.status.idle": "2024-02-20T04:24:48.414612Z",
     "shell.execute_reply": "2024-02-20T04:24:48.413453Z"
    },
    "papermill": {
     "duration": 0.048313,
     "end_time": "2024-02-20T04:24:48.417172",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.368859",
     "status": "completed"
    },
    "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>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  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "d3789ed0",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-02-20T04:24:48.438597Z",
     "iopub.status.busy": "2024-02-20T04:24:48.437806Z",
     "iopub.status.idle": "2024-02-20T04:24:48.459319Z",
     "shell.execute_reply": "2024-02-20T04:24:48.458183Z"
    },
    "papermill": {
     "duration": 0.035039,
     "end_time": "2024-02-20T04:24:48.461912",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.426873",
     "status": "completed"
    },
    "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>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>891</td>\n",
       "      <td>891</td>\n",
       "      <td>891</td>\n",
       "      <td>204</td>\n",
       "      <td>889</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unique</th>\n",
       "      <td>891</td>\n",
       "      <td>2</td>\n",
       "      <td>681</td>\n",
       "      <td>147</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>top</th>\n",
       "      <td>Braund, Mr. Owen Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>347082</td>\n",
       "      <td>B96 B98</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>freq</th>\n",
       "      <td>1</td>\n",
       "      <td>577</td>\n",
       "      <td>7</td>\n",
       "      <td>4</td>\n",
       "      <td>644</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                           Name   Sex  Ticket    Cabin Embarked\n",
       "count                       891   891     891      204      889\n",
       "unique                      891     2     681      147        3\n",
       "top     Braund, Mr. Owen Harris  male  347082  B96 B98        S\n",
       "freq                          1   577       7        4      644"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.describe(include=['O'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "22f869b8",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-02-20T04:24:48.483332Z",
     "iopub.status.busy": "2024-02-20T04:24:48.482965Z",
     "iopub.status.idle": "2024-02-20T04:24:48.499487Z",
     "shell.execute_reply": "2024-02-20T04:24:48.498210Z"
    },
    "papermill": {
     "duration": 0.030072,
     "end_time": "2024-02-20T04:24:48.501825",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.471753",
     "status": "completed"
    },
    "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>Survived</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0.629630</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>0.472826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>0.242363</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Pclass  Survived\n",
       "0       1  0.629630\n",
       "1       2  0.472826\n",
       "2       3  0.242363"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train[['Pclass', 'Survived']].groupby(['Pclass'], as_index=False).mean().head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "18a40a30",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-02-20T04:24:48.525118Z",
     "iopub.status.busy": "2024-02-20T04:24:48.524717Z",
     "iopub.status.idle": "2024-02-20T04:24:48.534424Z",
     "shell.execute_reply": "2024-02-20T04:24:48.533411Z"
    },
    "papermill": {
     "duration": 0.024025,
     "end_time": "2024-02-20T04:24:48.536898",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.512873",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "df_train = df_train.drop_duplicates()\n",
    "df_train = df_train.dropna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "766abd22",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-02-20T04:24:48.559035Z",
     "iopub.status.busy": "2024-02-20T04:24:48.558649Z",
     "iopub.status.idle": "2024-02-20T04:24:48.570281Z",
     "shell.execute_reply": "2024-02-20T04:24:48.568883Z"
    },
    "papermill": {
     "duration": 0.026407,
     "end_time": "2024-02-20T04:24:48.573405",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.546998",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Index: 183 entries, 1 to 889\n",
      "Data columns (total 12 columns):\n",
      " #   Column       Non-Null Count  Dtype  \n",
      "---  ------       --------------  -----  \n",
      " 0   PassengerId  183 non-null    int64  \n",
      " 1   Survived     183 non-null    int64  \n",
      " 2   Pclass       183 non-null    int64  \n",
      " 3   Name         183 non-null    object \n",
      " 4   Sex          183 non-null    object \n",
      " 5   Age          183 non-null    float64\n",
      " 6   SibSp        183 non-null    int64  \n",
      " 7   Parch        183 non-null    int64  \n",
      " 8   Ticket       183 non-null    object \n",
      " 9   Fare         183 non-null    float64\n",
      " 10  Cabin        183 non-null    object \n",
      " 11  Embarked     183 non-null    object \n",
      "dtypes: float64(2), int64(5), object(5)\n",
      "memory usage: 18.6+ KB\n"
     ]
    }
   ],
   "source": [
    "df_train.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "81598526",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-02-20T04:24:48.595746Z",
     "iopub.status.busy": "2024-02-20T04:24:48.595310Z",
     "iopub.status.idle": "2024-02-20T04:24:48.608488Z",
     "shell.execute_reply": "2024-02-20T04:24:48.607062Z"
    },
    "papermill": {
     "duration": 0.027409,
     "end_time": "2024-02-20T04:24:48.611104",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.583695",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Before (183, 12) (418, 11)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "('After', (183, 8), (418, 7))"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "print(\"Before\", df_train.shape, df_test.shape)\n",
    "\n",
    "df_train = df_train.drop(['Ticket', 'Cabin','Name','PassengerId'], axis=1)\n",
    "df_test = df_test.drop(['Ticket', 'Cabin','Name','PassengerId'], axis=1)\n",
    "\n",
    "\"After\", df_train.shape, df_test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "9661f901",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-02-20T04:24:48.633573Z",
     "iopub.status.busy": "2024-02-20T04:24:48.633171Z",
     "iopub.status.idle": "2024-02-20T04:24:48.641108Z",
     "shell.execute_reply": "2024-02-20T04:24:48.639945Z"
    },
    "papermill": {
     "duration": 0.022039,
     "end_time": "2024-02-20T04:24:48.643399",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.621360",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "df_train['Sex'] = df_train['Sex'].map( {'female': 1, 'male': 0} ).astype(int)\n",
    "df_test['Sex'] = df_test['Sex'].map( {'female': 1, 'male': 0} ).astype(int)"
   ]
  },
  {
   "cell_type": "raw",
   "id": "1b850fa1",
   "metadata": {
    "papermill": {
     "duration": 0.012268,
     "end_time": "2024-02-20T04:24:48.666334",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.654066",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "rellenar datos faltantes en la variable edad"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "47daabe9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-02-20T04:24:48.689242Z",
     "iopub.status.busy": "2024-02-20T04:24:48.688735Z",
     "iopub.status.idle": "2024-02-20T04:24:48.722399Z",
     "shell.execute_reply": "2024-02-20T04:24:48.721117Z"
    },
    "papermill": {
     "duration": 0.048135,
     "end_time": "2024-02-20T04:24:48.725113",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.676978",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "guess_ages = np.zeros((2,3))\n",
    "for dataset in [df_train,df_test]:\n",
    "    for i in range(0, 2):\n",
    "        for j in range(0, 3):\n",
    "            # clean nan ages\n",
    "            guess_df = dataset[(dataset['Sex'] == i) & \\\n",
    "                                  (dataset['Pclass'] == j+1)]['Age'].dropna()\n",
    "\n",
    "            # age_mean = guess_df.mean()\n",
    "            # age_std = guess_df.std()\n",
    "            # age_guess = rnd.uniform(age_mean - age_std, age_mean + age_std)\n",
    "\n",
    "            age_guess = guess_df.median()\n",
    "\n",
    "            # Convert random age float to nearest .5 age\n",
    "            guess_ages[i,j] = int( age_guess/0.5 + 0.5 ) * 0.5 # age mean for each category\n",
    "            \n",
    "    for i in range(0, 2):\n",
    "        for j in range(0, 3):\n",
    "            dataset.loc[ (dataset.Age.isnull()) & (dataset.Sex == i) & (dataset.Pclass == j+1),\\\n",
    "                    'Age'] = guess_ages[i,j]\n",
    "\n",
    "    dataset['Age'] = dataset['Age'].astype(int)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "f62648c6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-02-20T04:24:48.748224Z",
     "iopub.status.busy": "2024-02-20T04:24:48.747764Z",
     "iopub.status.idle": "2024-02-20T04:24:48.763802Z",
     "shell.execute_reply": "2024-02-20T04:24:48.762885Z"
    },
    "papermill": {
     "duration": 0.030333,
     "end_time": "2024-02-20T04:24:48.765906",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.735573",
     "status": "completed"
    },
    "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",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>662</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>47</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>25.5875</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>177</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>50</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>28.7125</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>332</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>38</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>153.4625</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>556</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>48</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>39.6000</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>462</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>47</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>38.5000</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Survived  Pclass  Sex  Age  SibSp  Parch      Fare Embarked\n",
       "662         0       1    0   47      0      0   25.5875        S\n",
       "177         0       1    1   50      0      0   28.7125        C\n",
       "332         0       1    0   38      0      1  153.4625        S\n",
       "556         1       1    1   48      1      0   39.6000        C\n",
       "462         0       1    0   47      0      0   38.5000        S"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.sample(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7c8148bb",
   "metadata": {
    "papermill": {
     "duration": 0.010274,
     "end_time": "2024-02-20T04:24:48.786971",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.776697",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "159c9085",
   "metadata": {
    "papermill": {
     "duration": 0.010121,
     "end_time": "2024-02-20T04:24:48.807758",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.797637",
     "status": "completed"
    },
    "tags": []
   },
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9ba32fa8",
   "metadata": {
    "papermill": {
     "duration": 0.010199,
     "end_time": "2024-02-20T04:24:48.828442",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.818243",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "4b902e05",
   "metadata": {
    "papermill": {
     "duration": 0.010328,
     "end_time": "2024-02-20T04:24:48.849296",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.838968",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## Train Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "d8a1deb1",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-02-20T04:24:48.872372Z",
     "iopub.status.busy": "2024-02-20T04:24:48.871936Z",
     "iopub.status.idle": "2024-02-20T04:24:48.885088Z",
     "shell.execute_reply": "2024-02-20T04:24:48.883405Z"
    },
    "papermill": {
     "duration": 0.027748,
     "end_time": "2024-02-20T04:24:48.887774",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.860026",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import accuracy_score\n",
    "X = df_train.drop('Survived', axis=1)\n",
    "X = pd.get_dummies(X)\n",
    "y = df_train['Survived']\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b5b9b5c7",
   "metadata": {
    "papermill": {
     "duration": 0.010203,
     "end_time": "2024-02-20T04:24:48.908753",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.898550",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "### Random Forest"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "7bac2c57",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-02-20T04:24:48.931528Z",
     "iopub.status.busy": "2024-02-20T04:24:48.931052Z",
     "iopub.status.idle": "2024-02-20T04:24:49.191414Z",
     "shell.execute_reply": "2024-02-20T04:24:49.188347Z"
    },
    "papermill": {
     "duration": 0.274885,
     "end_time": "2024-02-20T04:24:49.194122",
     "exception": false,
     "start_time": "2024-02-20T04:24:48.919237",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Precisión del modelo: 0.7297297297297297\n"
     ]
    }
   ],
   "source": [
    "model = RandomForestClassifier()\n",
    "model.fit(X_train, y_train)\n",
    "# Realizar predicciones en el conjunto de prueba\n",
    "y_pred = model.predict(X_test)\n",
    "\n",
    "# Calcular la precisión del modelo\n",
    "accuracy = accuracy_score(y_test, y_pred)\n",
    "print(\"Precisión del modelo:\", accuracy)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "ac26e553",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-02-20T04:24:49.217447Z",
     "iopub.status.busy": "2024-02-20T04:24:49.217061Z",
     "iopub.status.idle": "2024-02-20T04:24:49.447516Z",
     "shell.execute_reply": "2024-02-20T04:24:49.445957Z"
    },
    "papermill": {
     "duration": 0.247201,
     "end_time": "2024-02-20T04:24:49.452237",
     "exception": false,
     "start_time": "2024-02-20T04:24:49.205036",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Regresión Logística: Precisión del modelo = 0.73\n",
      "Support Vector Machine: Precisión del modelo = 0.62\n",
      "Naive Bayes: Precisión del modelo = 0.62\n",
      "Gradient Boosting: Precisión del modelo = 0.86\n",
      "Redes Neuronales: Precisión del modelo = 0.62\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n"
     ]
    }
   ],
   "source": [
    "models = {\n",
    "    \"Regresión Logística\": LogisticRegression(),\n",
    "    \"Support Vector Machine\": SVC(),\n",
    "    \"Naive Bayes\": GaussianNB(),\n",
    "    \"Gradient Boosting\": GradientBoostingClassifier(),\n",
    "    \"Redes Neuronales\": MLPClassifier()\n",
    "}\n",
    "\n",
    "# Entrenar y evaluar cada modelo\n",
    "for name, model in models.items():\n",
    "    model.fit(X_train, y_train)\n",
    "    y_pred = model.predict(X_test)\n",
    "    accuracy = accuracy_score(y_test, y_pred)\n",
    "    print(f\"{name}: Precisión del modelo = {accuracy:.2f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ba6ea9a3",
   "metadata": {
    "papermill": {
     "duration": 0.022267,
     "end_time": "2024-02-20T04:24:49.498447",
     "exception": false,
     "start_time": "2024-02-20T04:24:49.476180",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kaggle": {
   "accelerator": "none",
   "dataSources": [
    {
     "databundleVersionId": 26502,
     "sourceId": 3136,
     "sourceType": "competition"
    }
   ],
   "dockerImageVersionId": 30646,
   "isGpuEnabled": false,
   "isInternetEnabled": true,
   "language": "python",
   "sourceType": "notebook"
  },
  "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",
   "version": "3.10.13"
  },
  "papermill": {
   "default_parameters": {},
   "duration": 8.076448,
   "end_time": "2024-02-20T04:24:50.162009",
   "environment_variables": {},
   "exception": null,
   "input_path": "__notebook__.ipynb",
   "output_path": "__notebook__.ipynb",
   "parameters": {},
   "start_time": "2024-02-20T04:24:42.085561",
   "version": "2.5.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}