modelos.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 🤖 Creación de los modelos - Factores de anemia\n",
    "\n",
    "- Miguel Angel Vélez Suarez\n",
    "- Samuel Pérez Hurtado\n",
    "\n",
    "1. Importar los datos preparados\n",
    "2. División 70-30\n",
    "3. Aprendizaje de los modelos y evaluación\n",
    "4. Hiperparametrización de los 3 mejores modelos\n",
    "5. Guardar el mejor modelo"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Importamos librerías básicas\n",
    "import pandas as pd # manipulacion dataframes\n",
    "import numpy as np  # matrices y vectores\n",
    "import matplotlib.pyplot as plt #gráfica\n",
    "import pickle # guardar modelos"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 1. Importar los datos"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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>Age in 5-year groups</th>\n",
       "      <th>Type of place of residence</th>\n",
       "      <th>Wealth index combined</th>\n",
       "      <th>Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)</th>\n",
       "      <th>Anemia level</th>\n",
       "      <th>Have mosquito bed net for sleeping (from household questionnaire)</th>\n",
       "      <th>Smokes cigarettes</th>\n",
       "      <th>When child put to breast</th>\n",
       "      <th>Had fever in last two weeks</th>\n",
       "      <th>Taking iron pills, sprinkles or syrup</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>25-29</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Richest</td>\n",
       "      <td>95.0</td>\n",
       "      <td>Moderate</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>105.000000</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>30-34</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Richest</td>\n",
       "      <td>113.0</td>\n",
       "      <td>Mild</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>51.335329</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>35-39</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Richest</td>\n",
       "      <td>121.0</td>\n",
       "      <td>Not anemic</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>35-39</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Richest</td>\n",
       "      <td>121.0</td>\n",
       "      <td>Not anemic</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>51.335329</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>20-24</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Richest</td>\n",
       "      <td>108.0</td>\n",
       "      <td>Moderate</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Age in 5-year groups Type of place of residence Wealth index combined  \\\n",
       "0                25-29                      Urban               Richest   \n",
       "1                30-34                      Urban               Richest   \n",
       "2                35-39                      Urban               Richest   \n",
       "3                35-39                      Urban               Richest   \n",
       "4                20-24                      Urban               Richest   \n",
       "\n",
       "   Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)  \\\n",
       "0                                               95.0                       \n",
       "1                                              113.0                       \n",
       "2                                              121.0                       \n",
       "3                                              121.0                       \n",
       "4                                              108.0                       \n",
       "\n",
       "  Anemia level  \\\n",
       "0     Moderate   \n",
       "1         Mild   \n",
       "2   Not anemic   \n",
       "3   Not anemic   \n",
       "4     Moderate   \n",
       "\n",
       "  Have mosquito bed net for sleeping (from household questionnaire)  \\\n",
       "0                                                Yes                  \n",
       "1                                                Yes                  \n",
       "2                                                Yes                  \n",
       "3                                                Yes                  \n",
       "4                                                Yes                  \n",
       "\n",
       "  Smokes cigarettes  When child put to breast Had fever in last two weeks  \\\n",
       "0                No                105.000000                          No   \n",
       "1                No                 51.335329                          No   \n",
       "2                No                  0.000000                          No   \n",
       "3                No                 51.335329                          No   \n",
       "4                No                  0.000000                          No   \n",
       "\n",
       "  Taking iron pills, sprinkles or syrup  \n",
       "0                                    No  \n",
       "1                                    No  \n",
       "2                                   Yes  \n",
       "3                                    No  \n",
       "4                                   Yes  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = pd.read_csv('data/datos_preparados.csv')\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 13136 entries, 0 to 13135\n",
      "Data columns (total 10 columns):\n",
      " #   Column                                                                 Non-Null Count  Dtype  \n",
      "---  ------                                                                 --------------  -----  \n",
      " 0   Age in 5-year groups                                                   13136 non-null  object \n",
      " 1   Type of place of residence                                             13136 non-null  object \n",
      " 2   Wealth index combined                                                  13136 non-null  object \n",
      " 3   Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)  13136 non-null  float64\n",
      " 4   Anemia level                                                           13136 non-null  object \n",
      " 5   Have mosquito bed net for sleeping (from household questionnaire)      13136 non-null  object \n",
      " 6   Smokes cigarettes                                                      13136 non-null  object \n",
      " 7   When child put to breast                                               13136 non-null  float64\n",
      " 8   Had fever in last two weeks                                            13136 non-null  object \n",
      " 9   Taking iron pills, sprinkles or syrup                                  13136 non-null  object \n",
      "dtypes: float64(2), object(8)\n",
      "memory usage: 1.0+ MB\n"
     ]
    }
   ],
   "source": [
    "data.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>Age in 5-year groups</th>\n",
       "      <th>Type of place of residence</th>\n",
       "      <th>Wealth index combined</th>\n",
       "      <th>Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)</th>\n",
       "      <th>Anemia level</th>\n",
       "      <th>Have mosquito bed net for sleeping (from household questionnaire)</th>\n",
       "      <th>Smokes cigarettes</th>\n",
       "      <th>When child put to breast</th>\n",
       "      <th>Had fever in last two weeks</th>\n",
       "      <th>Taking iron pills, sprinkles or syrup</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>25-29</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Richest</td>\n",
       "      <td>95.0</td>\n",
       "      <td>1</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>105.000000</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>30-34</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Richest</td>\n",
       "      <td>113.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>51.335329</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>35-39</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Richest</td>\n",
       "      <td>121.0</td>\n",
       "      <td>2</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>35-39</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Richest</td>\n",
       "      <td>121.0</td>\n",
       "      <td>2</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>51.335329</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>20-24</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Richest</td>\n",
       "      <td>108.0</td>\n",
       "      <td>1</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Age in 5-year groups Type of place of residence Wealth index combined  \\\n",
       "0                25-29                      Urban               Richest   \n",
       "1                30-34                      Urban               Richest   \n",
       "2                35-39                      Urban               Richest   \n",
       "3                35-39                      Urban               Richest   \n",
       "4                20-24                      Urban               Richest   \n",
       "\n",
       "   Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)  \\\n",
       "0                                               95.0                       \n",
       "1                                              113.0                       \n",
       "2                                              121.0                       \n",
       "3                                              121.0                       \n",
       "4                                              108.0                       \n",
       "\n",
       "   Anemia level  \\\n",
       "0             1   \n",
       "1             0   \n",
       "2             2   \n",
       "3             2   \n",
       "4             1   \n",
       "\n",
       "  Have mosquito bed net for sleeping (from household questionnaire)  \\\n",
       "0                                                Yes                  \n",
       "1                                                Yes                  \n",
       "2                                                Yes                  \n",
       "3                                                Yes                  \n",
       "4                                                Yes                  \n",
       "\n",
       "  Smokes cigarettes  When child put to breast Had fever in last two weeks  \\\n",
       "0                No                105.000000                          No   \n",
       "1                No                 51.335329                          No   \n",
       "2                No                  0.000000                          No   \n",
       "3                No                 51.335329                          No   \n",
       "4                No                  0.000000                          No   \n",
       "\n",
       "  Taking iron pills, sprinkles or syrup  \n",
       "0                                    No  \n",
       "1                                    No  \n",
       "2                                   Yes  \n",
       "3                                    No  \n",
       "4                                   Yes  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Encoder: Transformación de categorías a números (sólo para la variable objetivo)\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "\n",
    "labelencoder = LabelEncoder()\n",
    "data[\"Anemia level\"] = labelencoder.fit_transform(data[\"Anemia level\"])\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 2. División 70-30"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='Anemia level'>"
      ]
     },
     "execution_count": 5,
     "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": [
    "#División 70-30\n",
    "from sklearn.model_selection import train_test_split\n",
    "X = data.drop(\"Anemia level\", axis = 1) # Variables predictoras\n",
    "Y = data['Anemia level'] #Variable objetivo\n",
    "X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.3, stratify=Y) #Muestreo estratificado\n",
    "Y_train.value_counts().plot(kind='bar')# Objetivo del 70%"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2.1. Balanceo del 70%"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Se instala la librería imblearn para balancear los datos\n",
    "# !pip install imblearn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Index: 9195 entries, 1298 to 12331\n",
      "Data columns (total 9 columns):\n",
      " #   Column                                                                 Non-Null Count  Dtype  \n",
      "---  ------                                                                 --------------  -----  \n",
      " 0   Age in 5-year groups                                                   9195 non-null   object \n",
      " 1   Type of place of residence                                             9195 non-null   object \n",
      " 2   Wealth index combined                                                  9195 non-null   object \n",
      " 3   Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)  9195 non-null   float64\n",
      " 4   Have mosquito bed net for sleeping (from household questionnaire)      9195 non-null   object \n",
      " 5   Smokes cigarettes                                                      9195 non-null   object \n",
      " 6   When child put to breast                                               9195 non-null   float64\n",
      " 7   Had fever in last two weeks                                            9195 non-null   object \n",
      " 8   Taking iron pills, sprinkles or syrup                                  9195 non-null   object \n",
      "dtypes: float64(2), object(7)\n",
      "memory usage: 718.4+ KB\n"
     ]
    }
   ],
   "source": [
    "X_train.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "from imblearn.over_sampling import SMOTENC\n",
    "\n",
    "# Identificar las columnas categóricas y numéricas\n",
    "categorical_cols = ['Age in 5-year groups', 'Type of place of residence', 'Wealth index combined', \n",
    "                    'Have mosquito bed net for sleeping (from household questionnaire)', 'Smokes cigarettes', \n",
    "                    'Had fever in last two weeks', 'Taking iron pills, sprinkles or syrup']\n",
    "numerical_cols = ['Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)', 'When child put to breast']\n",
    "\n",
    "# Crear una lista de booleanos para indicar si una columna es categórica (True) o no (False)\n",
    "categorical_features = [True if col in categorical_cols else False for col in X_train.columns]\n",
    "\n",
    "# Usar SMOTENC para balancear las variables categóricas y numéricas\n",
    "sm = SMOTENC(categorical_features=categorical_features, random_state=42, k_neighbors=2)\n",
    "X_train, Y_train = sm.fit_resample(X_train, Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='Anemia level'>"
      ]
     },
     "execution_count": 9,
     "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": [
    "Y_train.value_counts().plot(kind='bar')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='Anemia level'>"
      ]
     },
     "execution_count": 10,
     "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": [
    "Y_test.value_counts().plot(kind='bar')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2.2. Dummies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train = pd.get_dummies(X_train, drop_first=True, dtype='int64')\n",
    "X_test = pd.get_dummies(X_test, drop_first=True, dtype='int64')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "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>Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)</th>\n",
       "      <th>When child put to breast</th>\n",
       "      <th>Age in 5-year groups_20-24</th>\n",
       "      <th>Age in 5-year groups_25-29</th>\n",
       "      <th>Age in 5-year groups_30-34</th>\n",
       "      <th>Age in 5-year groups_35-39</th>\n",
       "      <th>Age in 5-year groups_40-44</th>\n",
       "      <th>Age in 5-year groups_45-49</th>\n",
       "      <th>Type of place of residence_Urban</th>\n",
       "      <th>Wealth index combined_Poorer</th>\n",
       "      <th>Wealth index combined_Poorest</th>\n",
       "      <th>Wealth index combined_Richer</th>\n",
       "      <th>Wealth index combined_Richest</th>\n",
       "      <th>Have mosquito bed net for sleeping (from household questionnaire)_Yes</th>\n",
       "      <th>Smokes cigarettes_Yes</th>\n",
       "      <th>Had fever in last two weeks_No</th>\n",
       "      <th>Had fever in last two weeks_Yes</th>\n",
       "      <th>Taking iron pills, sprinkles or syrup_No</th>\n",
       "      <th>Taking iron pills, sprinkles or syrup_Yes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>118.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>118.0</td>\n",
       "      <td>51.335329</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>123.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>103.0</td>\n",
       "      <td>51.335329</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>133.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)  \\\n",
       "0                                              118.0                       \n",
       "1                                              118.0                       \n",
       "2                                              123.0                       \n",
       "3                                              103.0                       \n",
       "4                                              133.0                       \n",
       "\n",
       "   When child put to breast  Age in 5-year groups_20-24  \\\n",
       "0                  0.000000                           0   \n",
       "1                 51.335329                           0   \n",
       "2                  0.000000                           1   \n",
       "3                 51.335329                           0   \n",
       "4                  0.000000                           0   \n",
       "\n",
       "   Age in 5-year groups_25-29  Age in 5-year groups_30-34  \\\n",
       "0                           0                           0   \n",
       "1                           1                           0   \n",
       "2                           0                           0   \n",
       "3                           0                           1   \n",
       "4                           0                           0   \n",
       "\n",
       "   Age in 5-year groups_35-39  Age in 5-year groups_40-44  \\\n",
       "0                           0                           0   \n",
       "1                           0                           0   \n",
       "2                           0                           0   \n",
       "3                           0                           0   \n",
       "4                           1                           0   \n",
       "\n",
       "   Age in 5-year groups_45-49  Type of place of residence_Urban  \\\n",
       "0                           1                                 0   \n",
       "1                           0                                 0   \n",
       "2                           0                                 1   \n",
       "3                           0                                 1   \n",
       "4                           0                                 1   \n",
       "\n",
       "   Wealth index combined_Poorer  Wealth index combined_Poorest  \\\n",
       "0                             0                              0   \n",
       "1                             0                              1   \n",
       "2                             1                              0   \n",
       "3                             0                              0   \n",
       "4                             0                              0   \n",
       "\n",
       "   Wealth index combined_Richer  Wealth index combined_Richest  \\\n",
       "0                             1                              0   \n",
       "1                             0                              0   \n",
       "2                             0                              0   \n",
       "3                             1                              0   \n",
       "4                             1                              0   \n",
       "\n",
       "   Have mosquito bed net for sleeping (from household questionnaire)_Yes  \\\n",
       "0                                                  1                       \n",
       "1                                                  1                       \n",
       "2                                                  1                       \n",
       "3                                                  1                       \n",
       "4                                                  0                       \n",
       "\n",
       "   Smokes cigarettes_Yes  Had fever in last two weeks_No  \\\n",
       "0                      0                               1   \n",
       "1                      0                               1   \n",
       "2                      0                               0   \n",
       "3                      0                               1   \n",
       "4                      0                               1   \n",
       "\n",
       "   Had fever in last two weeks_Yes  Taking iron pills, sprinkles or syrup_No  \\\n",
       "0                                0                                         1   \n",
       "1                                0                                         1   \n",
       "2                                0                                         1   \n",
       "3                                0                                         0   \n",
       "4                                0                                         1   \n",
       "\n",
       "   Taking iron pills, sprinkles or syrup_Yes  \n",
       "0                                          0  \n",
       "1                                          0  \n",
       "2                                          0  \n",
       "3                                          1  \n",
       "4                                          0  "
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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>Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)</th>\n",
       "      <th>When child put to breast</th>\n",
       "      <th>Age in 5-year groups_20-24</th>\n",
       "      <th>Age in 5-year groups_25-29</th>\n",
       "      <th>Age in 5-year groups_30-34</th>\n",
       "      <th>Age in 5-year groups_35-39</th>\n",
       "      <th>Age in 5-year groups_40-44</th>\n",
       "      <th>Age in 5-year groups_45-49</th>\n",
       "      <th>Type of place of residence_Urban</th>\n",
       "      <th>Wealth index combined_Poorer</th>\n",
       "      <th>Wealth index combined_Poorest</th>\n",
       "      <th>Wealth index combined_Richer</th>\n",
       "      <th>Wealth index combined_Richest</th>\n",
       "      <th>Have mosquito bed net for sleeping (from household questionnaire)_Yes</th>\n",
       "      <th>Smokes cigarettes_Yes</th>\n",
       "      <th>Had fever in last two weeks_No</th>\n",
       "      <th>Had fever in last two weeks_Yes</th>\n",
       "      <th>Taking iron pills, sprinkles or syrup_No</th>\n",
       "      <th>Taking iron pills, sprinkles or syrup_Yes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>5397</th>\n",
       "      <td>122.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>836</th>\n",
       "      <td>113.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8032</th>\n",
       "      <td>102.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3785</th>\n",
       "      <td>104.0</td>\n",
       "      <td>60.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5685</th>\n",
       "      <td>129.0</td>\n",
       "      <td>105.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)  \\\n",
       "5397                                              122.0                       \n",
       "836                                               113.0                       \n",
       "8032                                              102.0                       \n",
       "3785                                              104.0                       \n",
       "5685                                              129.0                       \n",
       "\n",
       "      When child put to breast  Age in 5-year groups_20-24  \\\n",
       "5397                       0.0                           1   \n",
       "836                        0.0                           0   \n",
       "8032                       0.0                           0   \n",
       "3785                      60.0                           1   \n",
       "5685                     105.0                           0   \n",
       "\n",
       "      Age in 5-year groups_25-29  Age in 5-year groups_30-34  \\\n",
       "5397                           0                           0   \n",
       "836                            1                           0   \n",
       "8032                           0                           0   \n",
       "3785                           0                           0   \n",
       "5685                           1                           0   \n",
       "\n",
       "      Age in 5-year groups_35-39  Age in 5-year groups_40-44  \\\n",
       "5397                           0                           0   \n",
       "836                            0                           0   \n",
       "8032                           0                           0   \n",
       "3785                           0                           0   \n",
       "5685                           0                           0   \n",
       "\n",
       "      Age in 5-year groups_45-49  Type of place of residence_Urban  \\\n",
       "5397                           0                                 1   \n",
       "836                            0                                 0   \n",
       "8032                           1                                 0   \n",
       "3785                           0                                 0   \n",
       "5685                           0                                 0   \n",
       "\n",
       "      Wealth index combined_Poorer  Wealth index combined_Poorest  \\\n",
       "5397                             0                              1   \n",
       "836                              0                              0   \n",
       "8032                             0                              0   \n",
       "3785                             1                              0   \n",
       "5685                             1                              0   \n",
       "\n",
       "      Wealth index combined_Richer  Wealth index combined_Richest  \\\n",
       "5397                             0                              0   \n",
       "836                              1                              0   \n",
       "8032                             0                              1   \n",
       "3785                             0                              0   \n",
       "5685                             0                              0   \n",
       "\n",
       "      Have mosquito bed net for sleeping (from household questionnaire)_Yes  \\\n",
       "5397                                                  0                       \n",
       "836                                                   1                       \n",
       "8032                                                  1                       \n",
       "3785                                                  1                       \n",
       "5685                                                  1                       \n",
       "\n",
       "      Smokes cigarettes_Yes  Had fever in last two weeks_No  \\\n",
       "5397                      0                               1   \n",
       "836                       0                               1   \n",
       "8032                      0                               1   \n",
       "3785                      0                               1   \n",
       "5685                      0                               1   \n",
       "\n",
       "      Had fever in last two weeks_Yes  \\\n",
       "5397                                0   \n",
       "836                                 0   \n",
       "8032                                0   \n",
       "3785                                0   \n",
       "5685                                0   \n",
       "\n",
       "      Taking iron pills, sprinkles or syrup_No  \\\n",
       "5397                                         1   \n",
       "836                                          1   \n",
       "8032                                         1   \n",
       "3785                                         1   \n",
       "5685                                         1   \n",
       "\n",
       "      Taking iron pills, sprinkles or syrup_Yes  \n",
       "5397                                          0  \n",
       "836                                           0  \n",
       "8032                                          0  \n",
       "3785                                          0  \n",
       "5685                                          0  "
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_test.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 3. Aprendizaje de los modelos y evaluación\n",
    "\n",
    "- Árbol de decisión\n",
    "- KNN\n",
    "- Redes neuronales\n",
    "- SVM\n",
    "- Random Forest\n",
    "- XGBoost\n",
    "- Stacking"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import accuracy_score, classification_report, confusion_matrix, recall_score, precision_score, f1_score\n",
    "import seaborn as sns\n",
    "\n",
    "def evaluacion_modelos(model, X_test, y_test):\n",
    "\n",
    "    y_test_pred = model.predict(X_test)  #Estas son las salidas generadas por el modelo (TEÓRICAS)\n",
    "\n",
    "    print(\"******* Resultados de evaluación*******\")\n",
    "\n",
    "    clf_report = pd.DataFrame(classification_report(y_test,y_test_pred,output_dict=True))\n",
    "\n",
    "    conf = confusion_matrix(y_test, y_test_pred)\n",
    "    sns.heatmap(conf, annot=True, fmt='d')\n",
    "    \n",
    "    precision = precision_score(y_test, y_test_pred, average='weighted')\n",
    "    sensibilidad = recall_score(y_test, y_test_pred, average='weighted')\n",
    "    exactitud = accuracy_score(y_test, y_test_pred)\n",
    "    f1score = f1_score(y_test, y_test_pred, average='weighted')\n",
    "\n",
    "    print(f\"Precisión: {precision}\")\n",
    "    print(f\"Sensibilidad: {sensibilidad}\")\n",
    "    print(f\"Exactitud: {exactitud}\")\n",
    "    print(f\"F1_Score: {f1score}\")\n",
    "\n",
    "    print(clf_report)\n",
    "    \n",
    "    return precision, sensibilidad, exactitud, f1score"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 3.1. Árbol de decisión"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "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>fit_time</th>\n",
       "      <th>score_time</th>\n",
       "      <th>test_f1_weighted</th>\n",
       "      <th>test_accuracy</th>\n",
       "      <th>test_precision_weighted</th>\n",
       "      <th>test_recall_weighted</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.029727</td>\n",
       "      <td>0.013072</td>\n",
       "      <td>0.944228</td>\n",
       "      <td>0.943813</td>\n",
       "      <td>0.946150</td>\n",
       "      <td>0.943813</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.023132</td>\n",
       "      <td>0.007321</td>\n",
       "      <td>0.944436</td>\n",
       "      <td>0.944482</td>\n",
       "      <td>0.946230</td>\n",
       "      <td>0.944482</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.020888</td>\n",
       "      <td>0.007123</td>\n",
       "      <td>0.926755</td>\n",
       "      <td>0.926421</td>\n",
       "      <td>0.930049</td>\n",
       "      <td>0.926421</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.019542</td>\n",
       "      <td>0.007129</td>\n",
       "      <td>0.947117</td>\n",
       "      <td>0.947157</td>\n",
       "      <td>0.949019</td>\n",
       "      <td>0.947157</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.020109</td>\n",
       "      <td>0.007301</td>\n",
       "      <td>0.945680</td>\n",
       "      <td>0.945783</td>\n",
       "      <td>0.947416</td>\n",
       "      <td>0.945783</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.025303</td>\n",
       "      <td>0.007447</td>\n",
       "      <td>0.940229</td>\n",
       "      <td>0.940428</td>\n",
       "      <td>0.942613</td>\n",
       "      <td>0.940428</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0.025260</td>\n",
       "      <td>0.009270</td>\n",
       "      <td>0.945927</td>\n",
       "      <td>0.945783</td>\n",
       "      <td>0.947456</td>\n",
       "      <td>0.945783</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0.024573</td>\n",
       "      <td>0.010777</td>\n",
       "      <td>0.951400</td>\n",
       "      <td>0.951138</td>\n",
       "      <td>0.952952</td>\n",
       "      <td>0.951138</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0.024630</td>\n",
       "      <td>0.012621</td>\n",
       "      <td>0.962583</td>\n",
       "      <td>0.962517</td>\n",
       "      <td>0.963164</td>\n",
       "      <td>0.962517</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0.023160</td>\n",
       "      <td>0.007206</td>\n",
       "      <td>0.957100</td>\n",
       "      <td>0.957162</td>\n",
       "      <td>0.958438</td>\n",
       "      <td>0.957162</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   fit_time  score_time  test_f1_weighted  test_accuracy  \\\n",
       "0  0.029727    0.013072          0.944228       0.943813   \n",
       "1  0.023132    0.007321          0.944436       0.944482   \n",
       "2  0.020888    0.007123          0.926755       0.926421   \n",
       "3  0.019542    0.007129          0.947117       0.947157   \n",
       "4  0.020109    0.007301          0.945680       0.945783   \n",
       "5  0.025303    0.007447          0.940229       0.940428   \n",
       "6  0.025260    0.009270          0.945927       0.945783   \n",
       "7  0.024573    0.010777          0.951400       0.951138   \n",
       "8  0.024630    0.012621          0.962583       0.962517   \n",
       "9  0.023160    0.007206          0.957100       0.957162   \n",
       "\n",
       "   test_precision_weighted  test_recall_weighted  \n",
       "0                 0.946150              0.943813  \n",
       "1                 0.946230              0.944482  \n",
       "2                 0.930049              0.926421  \n",
       "3                 0.949019              0.947157  \n",
       "4                 0.947416              0.945783  \n",
       "5                 0.942613              0.940428  \n",
       "6                 0.947456              0.945783  \n",
       "7                 0.952952              0.951138  \n",
       "8                 0.963164              0.962517  \n",
       "9                 0.958438              0.957162  "
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Creación del modelo con el conjunto de entrenamiento\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.model_selection import cross_validate\n",
    "modelTree = DecisionTreeClassifier(criterion='gini', min_samples_leaf=2, max_depth=10) #gini, entropy\n",
    "\n",
    "scores = cross_validate(modelTree, X_train, Y_train, cv=10, scoring=('f1_weighted', 'accuracy', 'precision_weighted', 'recall_weighted'), \n",
    "                        return_train_score=False, return_estimator=False)\n",
    "scores=pd.DataFrame(scores)\n",
    "scores"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Promedio F1 Score: 0.95\n",
      "Promedio Accuracy: 0.95\n",
      "Promedio Precision: 0.95\n",
      "Promedio Recall: 0.95\n"
     ]
    }
   ],
   "source": [
    "# Calcular los valores promedio de cada métrica\n",
    "promedio_f1 = scores['test_f1_weighted'].mean()\n",
    "promedio_accuracy = scores['test_accuracy'].mean()\n",
    "promedio_precision = scores['test_precision_weighted'].mean()\n",
    "promedio_recall = scores['test_recall_weighted'].mean()\n",
    "\n",
    "# Imprimir los valores promedio\n",
    "print(\"Promedio F1 Score: {:.2f}\".format(promedio_f1))\n",
    "print(\"Promedio Accuracy: {:.2f}\".format(promedio_accuracy))\n",
    "print(\"Promedio Precision: {:.2f}\".format(promedio_precision))\n",
    "print(\"Promedio Recall: {:.2f}\".format(promedio_recall))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>DecisionTreeClassifier(max_depth=10, min_samples_leaf=2)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">DecisionTreeClassifier</label><div class=\"sk-toggleable__content\"><pre>DecisionTreeClassifier(max_depth=10, min_samples_leaf=2)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "DecisionTreeClassifier(max_depth=10, min_samples_leaf=2)"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Entrenamiento del modelo con el 70%\n",
    "modelTree.fit(X_train, Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 600x800 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from sklearn.tree import plot_tree\n",
    "plt.figure(figsize=(6,8))\n",
    "plot_tree(modelTree, feature_names=X_train.columns.values, class_names=labelencoder.classes_, rounded=True, filled=True)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "******* Resultados de evaluación*******\n",
      "Precisión: 0.9296393671226859\n",
      "Sensibilidad: 0.9266683582846993\n",
      "Exactitud: 0.9266683582846993\n",
      "F1_Score: 0.9268874564373485\n",
      "                     0            1            2          3  accuracy  \\\n",
      "precision     0.893100     0.880394     0.996029   0.812500  0.926668   \n",
      "recall        0.852505     0.975671     0.940037   0.928571  0.926668   \n",
      "f1-score      0.872330     0.925587     0.967224   0.866667  0.926668   \n",
      "support    1078.000000  1192.000000  1601.000000  70.000000  0.926668   \n",
      "\n",
      "             macro avg  weighted avg  \n",
      "precision     0.895506      0.929639  \n",
      "recall        0.924196      0.926668  \n",
      "f1-score      0.907952      0.926887  \n",
      "support    3941.000000   3941.000000  \n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "precision, sensibilidad, exactitud, f1score = evaluacion_modelos(modelTree, X_test, Y_test)\n",
    "\n",
    "medidas = pd.DataFrame(index=['Precisión', 'Sensibilidad', 'Exactitud', 'F1_Score'])\n",
    "medidas['DecisionTree'] = [precision, sensibilidad, exactitud, f1score]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "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>DecisionTree</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Precisión</th>\n",
       "      <td>0.929639</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Sensibilidad</th>\n",
       "      <td>0.926668</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Exactitud</th>\n",
       "      <td>0.926668</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>F1_Score</th>\n",
       "      <td>0.926887</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              DecisionTree\n",
       "Precisión         0.929639\n",
       "Sensibilidad      0.926668\n",
       "Exactitud         0.926668\n",
       "F1_Score          0.926887"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "medidas"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 3.2. KNN"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "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>Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)</th>\n",
       "      <th>When child put to breast</th>\n",
       "      <th>Age in 5-year groups_20-24</th>\n",
       "      <th>Age in 5-year groups_25-29</th>\n",
       "      <th>Age in 5-year groups_30-34</th>\n",
       "      <th>Age in 5-year groups_35-39</th>\n",
       "      <th>Age in 5-year groups_40-44</th>\n",
       "      <th>Age in 5-year groups_45-49</th>\n",
       "      <th>Type of place of residence_Urban</th>\n",
       "      <th>Wealth index combined_Poorer</th>\n",
       "      <th>Wealth index combined_Poorest</th>\n",
       "      <th>Wealth index combined_Richer</th>\n",
       "      <th>Wealth index combined_Richest</th>\n",
       "      <th>Have mosquito bed net for sleeping (from household questionnaire)_Yes</th>\n",
       "      <th>Smokes cigarettes_Yes</th>\n",
       "      <th>Had fever in last two weeks_No</th>\n",
       "      <th>Had fever in last two weeks_Yes</th>\n",
       "      <th>Taking iron pills, sprinkles or syrup_No</th>\n",
       "      <th>Taking iron pills, sprinkles or syrup_Yes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.700000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.700000</td>\n",
       "      <td>0.230203</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.735714</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.592857</td>\n",
       "      <td>0.230203</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.807143</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)  \\\n",
       "0                                           0.700000                       \n",
       "1                                           0.700000                       \n",
       "2                                           0.735714                       \n",
       "3                                           0.592857                       \n",
       "4                                           0.807143                       \n",
       "\n",
       "   When child put to breast  Age in 5-year groups_20-24  \\\n",
       "0                  0.000000                           0   \n",
       "1                  0.230203                           0   \n",
       "2                  0.000000                           1   \n",
       "3                  0.230203                           0   \n",
       "4                  0.000000                           0   \n",
       "\n",
       "   Age in 5-year groups_25-29  Age in 5-year groups_30-34  \\\n",
       "0                           0                           0   \n",
       "1                           1                           0   \n",
       "2                           0                           0   \n",
       "3                           0                           1   \n",
       "4                           0                           0   \n",
       "\n",
       "   Age in 5-year groups_35-39  Age in 5-year groups_40-44  \\\n",
       "0                           0                           0   \n",
       "1                           0                           0   \n",
       "2                           0                           0   \n",
       "3                           0                           0   \n",
       "4                           1                           0   \n",
       "\n",
       "   Age in 5-year groups_45-49  Type of place of residence_Urban  \\\n",
       "0                           1                                 0   \n",
       "1                           0                                 0   \n",
       "2                           0                                 1   \n",
       "3                           0                                 1   \n",
       "4                           0                                 1   \n",
       "\n",
       "   Wealth index combined_Poorer  Wealth index combined_Poorest  \\\n",
       "0                             0                              0   \n",
       "1                             0                              1   \n",
       "2                             1                              0   \n",
       "3                             0                              0   \n",
       "4                             0                              0   \n",
       "\n",
       "   Wealth index combined_Richer  Wealth index combined_Richest  \\\n",
       "0                             1                              0   \n",
       "1                             0                              0   \n",
       "2                             0                              0   \n",
       "3                             1                              0   \n",
       "4                             1                              0   \n",
       "\n",
       "   Have mosquito bed net for sleeping (from household questionnaire)_Yes  \\\n",
       "0                                                  1                       \n",
       "1                                                  1                       \n",
       "2                                                  1                       \n",
       "3                                                  1                       \n",
       "4                                                  0                       \n",
       "\n",
       "   Smokes cigarettes_Yes  Had fever in last two weeks_No  \\\n",
       "0                      0                               1   \n",
       "1                      0                               1   \n",
       "2                      0                               0   \n",
       "3                      0                               1   \n",
       "4                      0                               1   \n",
       "\n",
       "   Had fever in last two weeks_Yes  Taking iron pills, sprinkles or syrup_No  \\\n",
       "0                                0                                         1   \n",
       "1                                0                                         1   \n",
       "2                                0                                         1   \n",
       "3                                0                                         0   \n",
       "4                                0                                         1   \n",
       "\n",
       "   Taking iron pills, sprinkles or syrup_Yes  \n",
       "0                                          0  \n",
       "1                                          0  \n",
       "2                                          0  \n",
       "3                                          1  \n",
       "4                                          0  "
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Normalizacion las variables numéricas (las dummies no se normalizan)\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "\n",
    "min_max_scaler = MinMaxScaler()\n",
    "min_max_scaler.fit(data[['Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)', 'When child put to breast']])\n",
    "\n",
    "#Se aplica la normalización al 70% y 30%\n",
    "X_train[['Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)', 'When child put to breast']]= min_max_scaler.transform(X_train[['Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)', 'When child put to breast']])\n",
    "X_test[['Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)', 'When child put to breast']]= min_max_scaler.transform(X_test[['Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)', 'When child put to breast']])\n",
    "X_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "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>fit_time</th>\n",
       "      <th>score_time</th>\n",
       "      <th>test_f1_weighted</th>\n",
       "      <th>test_accuracy</th>\n",
       "      <th>test_precision_weighted</th>\n",
       "      <th>test_recall_weighted</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.004719</td>\n",
       "      <td>0.135552</td>\n",
       "      <td>0.799144</td>\n",
       "      <td>0.797324</td>\n",
       "      <td>0.803236</td>\n",
       "      <td>0.797324</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.006355</td>\n",
       "      <td>0.098421</td>\n",
       "      <td>0.789560</td>\n",
       "      <td>0.787960</td>\n",
       "      <td>0.794089</td>\n",
       "      <td>0.787960</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.005664</td>\n",
       "      <td>0.096421</td>\n",
       "      <td>0.785073</td>\n",
       "      <td>0.783946</td>\n",
       "      <td>0.788209</td>\n",
       "      <td>0.783946</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.005635</td>\n",
       "      <td>0.097669</td>\n",
       "      <td>0.810653</td>\n",
       "      <td>0.809365</td>\n",
       "      <td>0.814043</td>\n",
       "      <td>0.809365</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.005550</td>\n",
       "      <td>0.097545</td>\n",
       "      <td>0.813866</td>\n",
       "      <td>0.812584</td>\n",
       "      <td>0.820996</td>\n",
       "      <td>0.812584</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.007275</td>\n",
       "      <td>0.100309</td>\n",
       "      <td>0.809586</td>\n",
       "      <td>0.807229</td>\n",
       "      <td>0.816159</td>\n",
       "      <td>0.807229</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0.005854</td>\n",
       "      <td>0.095223</td>\n",
       "      <td>0.817386</td>\n",
       "      <td>0.815261</td>\n",
       "      <td>0.827887</td>\n",
       "      <td>0.815261</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0.005567</td>\n",
       "      <td>0.096292</td>\n",
       "      <td>0.879175</td>\n",
       "      <td>0.878179</td>\n",
       "      <td>0.886156</td>\n",
       "      <td>0.878179</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0.005537</td>\n",
       "      <td>0.096976</td>\n",
       "      <td>0.909893</td>\n",
       "      <td>0.909639</td>\n",
       "      <td>0.915200</td>\n",
       "      <td>0.909639</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0.006086</td>\n",
       "      <td>0.105782</td>\n",
       "      <td>0.892128</td>\n",
       "      <td>0.892236</td>\n",
       "      <td>0.899358</td>\n",
       "      <td>0.892236</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   fit_time  score_time  test_f1_weighted  test_accuracy  \\\n",
       "0  0.004719    0.135552          0.799144       0.797324   \n",
       "1  0.006355    0.098421          0.789560       0.787960   \n",
       "2  0.005664    0.096421          0.785073       0.783946   \n",
       "3  0.005635    0.097669          0.810653       0.809365   \n",
       "4  0.005550    0.097545          0.813866       0.812584   \n",
       "5  0.007275    0.100309          0.809586       0.807229   \n",
       "6  0.005854    0.095223          0.817386       0.815261   \n",
       "7  0.005567    0.096292          0.879175       0.878179   \n",
       "8  0.005537    0.096976          0.909893       0.909639   \n",
       "9  0.006086    0.105782          0.892128       0.892236   \n",
       "\n",
       "   test_precision_weighted  test_recall_weighted  \n",
       "0                 0.803236              0.797324  \n",
       "1                 0.794089              0.787960  \n",
       "2                 0.788209              0.783946  \n",
       "3                 0.814043              0.809365  \n",
       "4                 0.820996              0.812584  \n",
       "5                 0.816159              0.807229  \n",
       "6                 0.827887              0.815261  \n",
       "7                 0.886156              0.878179  \n",
       "8                 0.915200              0.909639  \n",
       "9                 0.899358              0.892236  "
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Aprendizaje KNN con 70%\n",
    "from sklearn.neighbors  import KNeighborsClassifier\n",
    "modelKnn = KNeighborsClassifier(n_neighbors=3, metric='euclidean')#euclidean, minkowski\n",
    "\n",
    "scores = cross_validate(modelKnn, X_train, Y_train, cv=10, scoring=('f1_weighted', 'accuracy', 'precision_weighted', 'recall_weighted'), \n",
    "                        return_train_score=False, return_estimator=False)\n",
    "scores=pd.DataFrame(scores)\n",
    "scores"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Promedio F1 Score: 0.83\n",
      "Promedio Accuracy: 0.83\n",
      "Promedio Precision: 0.84\n",
      "Promedio Recall: 0.83\n"
     ]
    }
   ],
   "source": [
    "# Calcular los valores promedio de cada métrica\n",
    "promedio_f1 = scores['test_f1_weighted'].mean()\n",
    "promedio_accuracy = scores['test_accuracy'].mean()\n",
    "promedio_precision = scores['test_precision_weighted'].mean()\n",
    "promedio_recall = scores['test_recall_weighted'].mean()\n",
    "\n",
    "# Imprimir los valores promedio\n",
    "print(\"Promedio F1 Score: {:.2f}\".format(promedio_f1))\n",
    "print(\"Promedio Accuracy: {:.2f}\".format(promedio_accuracy))\n",
    "print(\"Promedio Precision: {:.2f}\".format(promedio_precision))\n",
    "print(\"Promedio Recall: {:.2f}\".format(promedio_recall))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-2 {color: black;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>KNeighborsClassifier(metric=&#x27;euclidean&#x27;, n_neighbors=3)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">KNeighborsClassifier</label><div class=\"sk-toggleable__content\"><pre>KNeighborsClassifier(metric=&#x27;euclidean&#x27;, n_neighbors=3)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "KNeighborsClassifier(metric='euclidean', n_neighbors=3)"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Entrenamiento del modelo con el 70%\n",
    "modelKnn.fit(X_train, Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "******* Resultados de evaluación*******\n",
      "Precisión: 0.7555355572651827\n",
      "Sensibilidad: 0.7343313879725958\n",
      "Exactitud: 0.7343313879725958\n",
      "F1_Score: 0.7407512178115307\n",
      "                     0            1            2          3  accuracy  \\\n",
      "precision     0.569948     0.767161     0.886540   0.419355  0.734331   \n",
      "recall        0.714286     0.693792     0.785759   0.557143  0.734331   \n",
      "f1-score      0.634006     0.728634     0.833113   0.478528  0.734331   \n",
      "support    1078.000000  1192.000000  1601.000000  70.000000  0.734331   \n",
      "\n",
      "             macro avg  weighted avg  \n",
      "precision     0.660751      0.755536  \n",
      "recall        0.687745      0.734331  \n",
      "f1-score      0.668570      0.740751  \n",
      "support    3941.000000   3941.000000  \n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "precision, sensibilidad, exactitud, f1score = evaluacion_modelos(modelKnn, X_test, Y_test)\n",
    "\n",
    "medidas['KNN'] = [precision, sensibilidad, exactitud, f1score]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 3.3. Redes neuronales"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "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>fit_time</th>\n",
       "      <th>score_time</th>\n",
       "      <th>test_f1_weighted</th>\n",
       "      <th>test_accuracy</th>\n",
       "      <th>test_precision_weighted</th>\n",
       "      <th>test_recall_weighted</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.097426</td>\n",
       "      <td>0.007539</td>\n",
       "      <td>0.893780</td>\n",
       "      <td>0.894314</td>\n",
       "      <td>0.894099</td>\n",
       "      <td>0.894314</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2.219413</td>\n",
       "      <td>0.007654</td>\n",
       "      <td>0.924781</td>\n",
       "      <td>0.925084</td>\n",
       "      <td>0.927945</td>\n",
       "      <td>0.925084</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.919716</td>\n",
       "      <td>0.007447</td>\n",
       "      <td>0.873872</td>\n",
       "      <td>0.874916</td>\n",
       "      <td>0.873805</td>\n",
       "      <td>0.874916</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.456375</td>\n",
       "      <td>0.007456</td>\n",
       "      <td>0.909211</td>\n",
       "      <td>0.910368</td>\n",
       "      <td>0.909426</td>\n",
       "      <td>0.910368</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.223540</td>\n",
       "      <td>0.007399</td>\n",
       "      <td>0.897735</td>\n",
       "      <td>0.896921</td>\n",
       "      <td>0.900593</td>\n",
       "      <td>0.896921</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>1.364926</td>\n",
       "      <td>0.007683</td>\n",
       "      <td>0.918917</td>\n",
       "      <td>0.919009</td>\n",
       "      <td>0.922530</td>\n",
       "      <td>0.919009</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0.938377</td>\n",
       "      <td>0.007679</td>\n",
       "      <td>0.910129</td>\n",
       "      <td>0.909639</td>\n",
       "      <td>0.911522</td>\n",
       "      <td>0.909639</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>1.660191</td>\n",
       "      <td>0.007401</td>\n",
       "      <td>0.933003</td>\n",
       "      <td>0.932396</td>\n",
       "      <td>0.936109</td>\n",
       "      <td>0.932396</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>1.191989</td>\n",
       "      <td>0.007353</td>\n",
       "      <td>0.897179</td>\n",
       "      <td>0.898260</td>\n",
       "      <td>0.898709</td>\n",
       "      <td>0.898260</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1.383487</td>\n",
       "      <td>0.007399</td>\n",
       "      <td>0.933247</td>\n",
       "      <td>0.933066</td>\n",
       "      <td>0.935851</td>\n",
       "      <td>0.933066</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   fit_time  score_time  test_f1_weighted  test_accuracy  \\\n",
       "0  1.097426    0.007539          0.893780       0.894314   \n",
       "1  2.219413    0.007654          0.924781       0.925084   \n",
       "2  0.919716    0.007447          0.873872       0.874916   \n",
       "3  0.456375    0.007456          0.909211       0.910368   \n",
       "4  1.223540    0.007399          0.897735       0.896921   \n",
       "5  1.364926    0.007683          0.918917       0.919009   \n",
       "6  0.938377    0.007679          0.910129       0.909639   \n",
       "7  1.660191    0.007401          0.933003       0.932396   \n",
       "8  1.191989    0.007353          0.897179       0.898260   \n",
       "9  1.383487    0.007399          0.933247       0.933066   \n",
       "\n",
       "   test_precision_weighted  test_recall_weighted  \n",
       "0                 0.894099              0.894314  \n",
       "1                 0.927945              0.925084  \n",
       "2                 0.873805              0.874916  \n",
       "3                 0.909426              0.910368  \n",
       "4                 0.900593              0.896921  \n",
       "5                 0.922530              0.919009  \n",
       "6                 0.911522              0.909639  \n",
       "7                 0.936109              0.932396  \n",
       "8                 0.898709              0.898260  \n",
       "9                 0.935851              0.933066  "
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Red Neuronal\n",
    "from sklearn.neural_network import MLPClassifier\n",
    "\n",
    "#Solo se configura capas ocultas, no se configura capa de entrada y de salida\n",
    "modelNN = MLPClassifier(activation=\"logistic\",hidden_layer_sizes=(5), learning_rate='constant',\n",
    "                        learning_rate_init=0.2, momentum= 0.3, max_iter=500, random_state=42)\n",
    "\n",
    "scores = cross_validate(modelNN, X_train, Y_train, cv=10, scoring=('f1_weighted', 'accuracy', 'precision_weighted', 'recall_weighted'), \n",
    "                        return_train_score=False, return_estimator=False)\n",
    "scores=pd.DataFrame(scores)\n",
    "scores"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Promedio F1 Score: 0.91\n",
      "Promedio Accuracy: 0.91\n",
      "Promedio Precision: 0.91\n",
      "Promedio Recall: 0.91\n"
     ]
    }
   ],
   "source": [
    "# Calcular los valores promedio de cada métrica\n",
    "promedio_f1 = scores['test_f1_weighted'].mean()\n",
    "promedio_accuracy = scores['test_accuracy'].mean()\n",
    "promedio_precision = scores['test_precision_weighted'].mean()\n",
    "promedio_recall = scores['test_recall_weighted'].mean()\n",
    "\n",
    "# Imprimir los valores promedio\n",
    "print(\"Promedio F1 Score: {:.2f}\".format(promedio_f1))\n",
    "print(\"Promedio Accuracy: {:.2f}\".format(promedio_accuracy))\n",
    "print(\"Promedio Precision: {:.2f}\".format(promedio_precision))\n",
    "print(\"Promedio Recall: {:.2f}\".format(promedio_recall))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-3 {color: black;}#sk-container-id-3 pre{padding: 0;}#sk-container-id-3 div.sk-toggleable {background-color: white;}#sk-container-id-3 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-3 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-3 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-3 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-3 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-3 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-3 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-3 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-3 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-3 div.sk-item {position: relative;z-index: 1;}#sk-container-id-3 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-3 div.sk-item::before, #sk-container-id-3 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-3 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-3 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-3 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-3 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-3 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-3 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-3 div.sk-label-container {text-align: center;}#sk-container-id-3 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-3 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MLPClassifier(activation=&#x27;logistic&#x27;, hidden_layer_sizes=5,\n",
       "              learning_rate_init=0.2, max_iter=500, momentum=0.3,\n",
       "              random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" checked><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MLPClassifier</label><div class=\"sk-toggleable__content\"><pre>MLPClassifier(activation=&#x27;logistic&#x27;, hidden_layer_sizes=5,\n",
       "              learning_rate_init=0.2, max_iter=500, momentum=0.3,\n",
       "              random_state=42)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "MLPClassifier(activation='logistic', hidden_layer_sizes=5,\n",
       "              learning_rate_init=0.2, max_iter=500, momentum=0.3,\n",
       "              random_state=42)"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Entrenamiento del modelo con el 70%\n",
    "modelNN.fit(X_train, Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "******* Resultados de evaluación*******\n",
      "Precisión: 0.8850494354525094\n",
      "Sensibilidad: 0.8723674194366912\n",
      "Exactitud: 0.8723674194366912\n",
      "F1_Score: 0.8756974850208586\n",
      "                     0            1            2          3  accuracy  \\\n",
      "precision     0.742424     0.876271     0.995757   0.698925  0.872367   \n",
      "recall        0.863636     0.867450     0.879450   0.928571  0.872367   \n",
      "f1-score      0.798456     0.871838     0.933997   0.797546  0.872367   \n",
      "support    1078.000000  1192.000000  1601.000000  70.000000  0.872367   \n",
      "\n",
      "             macro avg  weighted avg  \n",
      "precision     0.828344      0.885049  \n",
      "recall        0.884777      0.872367  \n",
      "f1-score      0.850459      0.875697  \n",
      "support    3941.000000   3941.000000  \n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "precision, sensibilidad, exactitud, f1score = evaluacion_modelos(modelNN, X_test, Y_test)\n",
    "\n",
    "medidas['Red Neuronal'] = [precision, sensibilidad, exactitud, f1score]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 3.4. SVM"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "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>fit_time</th>\n",
       "      <th>score_time</th>\n",
       "      <th>test_f1_weighted</th>\n",
       "      <th>test_accuracy</th>\n",
       "      <th>test_precision_weighted</th>\n",
       "      <th>test_recall_weighted</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.780733</td>\n",
       "      <td>0.192343</td>\n",
       "      <td>0.918130</td>\n",
       "      <td>0.917726</td>\n",
       "      <td>0.920101</td>\n",
       "      <td>0.917726</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.639544</td>\n",
       "      <td>0.173574</td>\n",
       "      <td>0.912712</td>\n",
       "      <td>0.912375</td>\n",
       "      <td>0.914947</td>\n",
       "      <td>0.912375</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.578646</td>\n",
       "      <td>0.173384</td>\n",
       "      <td>0.898534</td>\n",
       "      <td>0.897659</td>\n",
       "      <td>0.903596</td>\n",
       "      <td>0.897659</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.678546</td>\n",
       "      <td>0.185798</td>\n",
       "      <td>0.914821</td>\n",
       "      <td>0.914381</td>\n",
       "      <td>0.916686</td>\n",
       "      <td>0.914381</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.634530</td>\n",
       "      <td>0.174635</td>\n",
       "      <td>0.911405</td>\n",
       "      <td>0.910977</td>\n",
       "      <td>0.914255</td>\n",
       "      <td>0.910977</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>1.658348</td>\n",
       "      <td>0.187792</td>\n",
       "      <td>0.910255</td>\n",
       "      <td>0.909639</td>\n",
       "      <td>0.913315</td>\n",
       "      <td>0.909639</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>1.688736</td>\n",
       "      <td>0.176034</td>\n",
       "      <td>0.912936</td>\n",
       "      <td>0.911647</td>\n",
       "      <td>0.917891</td>\n",
       "      <td>0.911647</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>1.571752</td>\n",
       "      <td>0.186133</td>\n",
       "      <td>0.932840</td>\n",
       "      <td>0.932396</td>\n",
       "      <td>0.935383</td>\n",
       "      <td>0.932396</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>1.668626</td>\n",
       "      <td>0.175783</td>\n",
       "      <td>0.935307</td>\n",
       "      <td>0.935074</td>\n",
       "      <td>0.937686</td>\n",
       "      <td>0.935074</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1.635167</td>\n",
       "      <td>0.202546</td>\n",
       "      <td>0.930855</td>\n",
       "      <td>0.930388</td>\n",
       "      <td>0.933153</td>\n",
       "      <td>0.930388</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   fit_time  score_time  test_f1_weighted  test_accuracy  \\\n",
       "0  1.780733    0.192343          0.918130       0.917726   \n",
       "1  1.639544    0.173574          0.912712       0.912375   \n",
       "2  1.578646    0.173384          0.898534       0.897659   \n",
       "3  1.678546    0.185798          0.914821       0.914381   \n",
       "4  1.634530    0.174635          0.911405       0.910977   \n",
       "5  1.658348    0.187792          0.910255       0.909639   \n",
       "6  1.688736    0.176034          0.912936       0.911647   \n",
       "7  1.571752    0.186133          0.932840       0.932396   \n",
       "8  1.668626    0.175783          0.935307       0.935074   \n",
       "9  1.635167    0.202546          0.930855       0.930388   \n",
       "\n",
       "   test_precision_weighted  test_recall_weighted  \n",
       "0                 0.920101              0.917726  \n",
       "1                 0.914947              0.912375  \n",
       "2                 0.903596              0.897659  \n",
       "3                 0.916686              0.914381  \n",
       "4                 0.914255              0.910977  \n",
       "5                 0.913315              0.909639  \n",
       "6                 0.917891              0.911647  \n",
       "7                 0.935383              0.932396  \n",
       "8                 0.937686              0.935074  \n",
       "9                 0.933153              0.930388  "
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#SVM\n",
    "from sklearn.svm import SVC #Classifier\n",
    "modelSVM = SVC(kernel='linear') #'linear', 'poly', 'rbf', 'sigmoid', 'precomputed'\n",
    "\n",
    "scores = cross_validate(modelSVM, X_train, Y_train, cv=10, scoring=('f1_weighted', 'accuracy', 'precision_weighted', 'recall_weighted'), \n",
    "                        return_train_score=False, return_estimator=False)\n",
    "scores=pd.DataFrame(scores)\n",
    "scores"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Promedio F1 Score: 0.92\n",
      "Promedio Accuracy: 0.92\n",
      "Promedio Precision: 0.92\n",
      "Promedio Recall: 0.92\n"
     ]
    }
   ],
   "source": [
    "# Calcular los valores promedio de cada métrica\n",
    "promedio_f1 = scores['test_f1_weighted'].mean()\n",
    "promedio_accuracy = scores['test_accuracy'].mean()\n",
    "promedio_precision = scores['test_precision_weighted'].mean()\n",
    "promedio_recall = scores['test_recall_weighted'].mean()\n",
    "\n",
    "# Imprimir los valores promedio\n",
    "print(\"Promedio F1 Score: {:.2f}\".format(promedio_f1))\n",
    "print(\"Promedio Accuracy: {:.2f}\".format(promedio_accuracy))\n",
    "print(\"Promedio Precision: {:.2f}\".format(promedio_precision))\n",
    "print(\"Promedio Recall: {:.2f}\".format(promedio_recall))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-4 {color: black;}#sk-container-id-4 pre{padding: 0;}#sk-container-id-4 div.sk-toggleable {background-color: white;}#sk-container-id-4 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-4 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-4 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-4 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-4 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-4 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-4 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-4 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-4 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-4 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-4 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-4 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-4 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-4 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-4 div.sk-item {position: relative;z-index: 1;}#sk-container-id-4 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-4 div.sk-item::before, #sk-container-id-4 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-4 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-4 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-4 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-4 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-4 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-4 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-4 div.sk-label-container {text-align: center;}#sk-container-id-4 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-4 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-4\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>SVC(kernel=&#x27;linear&#x27;)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" checked><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SVC</label><div class=\"sk-toggleable__content\"><pre>SVC(kernel=&#x27;linear&#x27;)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "SVC(kernel='linear')"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Entrenamiento del modelo con el 70%\n",
    "modelSVM.fit(X_train, Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "******* Resultados de evaluación*******\n",
      "Precisión: 0.8915223758380875\n",
      "Sensibilidad: 0.8817558995178889\n",
      "Exactitud: 0.8817558995178889\n",
      "F1_Score: 0.8845516607702515\n",
      "                     0            1            2          3  accuracy  \\\n",
      "precision     0.779374     0.874138     0.993239   0.588235  0.881756   \n",
      "recall        0.855288     0.850671     0.917552   1.000000  0.881756   \n",
      "f1-score      0.815568     0.862245     0.953896   0.740741  0.881756   \n",
      "support    1078.000000  1192.000000  1601.000000  70.000000  0.881756   \n",
      "\n",
      "             macro avg  weighted avg  \n",
      "precision     0.808747      0.891522  \n",
      "recall        0.905878      0.881756  \n",
      "f1-score      0.843113      0.884552  \n",
      "support    3941.000000   3941.000000  \n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "precision, sensibilidad, exactitud, f1score = evaluacion_modelos(modelSVM, X_test, Y_test)\n",
    "\n",
    "medidas['SVM'] = [precision, sensibilidad, exactitud, f1score]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 3.5. Random Forest"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "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>fit_time</th>\n",
       "      <th>score_time</th>\n",
       "      <th>test_f1_weighted</th>\n",
       "      <th>test_accuracy</th>\n",
       "      <th>test_precision_weighted</th>\n",
       "      <th>test_recall_weighted</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.685873</td>\n",
       "      <td>0.031853</td>\n",
       "      <td>0.952590</td>\n",
       "      <td>0.952508</td>\n",
       "      <td>0.954022</td>\n",
       "      <td>0.952508</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.616307</td>\n",
       "      <td>0.031845</td>\n",
       "      <td>0.947167</td>\n",
       "      <td>0.947157</td>\n",
       "      <td>0.948694</td>\n",
       "      <td>0.947157</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.606129</td>\n",
       "      <td>0.032879</td>\n",
       "      <td>0.931135</td>\n",
       "      <td>0.931104</td>\n",
       "      <td>0.934459</td>\n",
       "      <td>0.931104</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.612002</td>\n",
       "      <td>0.031157</td>\n",
       "      <td>0.953212</td>\n",
       "      <td>0.953177</td>\n",
       "      <td>0.954690</td>\n",
       "      <td>0.953177</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.633640</td>\n",
       "      <td>0.031258</td>\n",
       "      <td>0.950433</td>\n",
       "      <td>0.950469</td>\n",
       "      <td>0.951912</td>\n",
       "      <td>0.950469</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.613514</td>\n",
       "      <td>0.032039</td>\n",
       "      <td>0.948453</td>\n",
       "      <td>0.948461</td>\n",
       "      <td>0.950309</td>\n",
       "      <td>0.948461</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0.627126</td>\n",
       "      <td>0.031707</td>\n",
       "      <td>0.955164</td>\n",
       "      <td>0.955154</td>\n",
       "      <td>0.956681</td>\n",
       "      <td>0.955154</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0.602817</td>\n",
       "      <td>0.030996</td>\n",
       "      <td>0.960664</td>\n",
       "      <td>0.960509</td>\n",
       "      <td>0.961661</td>\n",
       "      <td>0.960509</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0.642092</td>\n",
       "      <td>0.033562</td>\n",
       "      <td>0.971895</td>\n",
       "      <td>0.971888</td>\n",
       "      <td>0.972393</td>\n",
       "      <td>0.971888</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0.626742</td>\n",
       "      <td>0.031195</td>\n",
       "      <td>0.964507</td>\n",
       "      <td>0.964525</td>\n",
       "      <td>0.965375</td>\n",
       "      <td>0.964525</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   fit_time  score_time  test_f1_weighted  test_accuracy  \\\n",
       "0  0.685873    0.031853          0.952590       0.952508   \n",
       "1  0.616307    0.031845          0.947167       0.947157   \n",
       "2  0.606129    0.032879          0.931135       0.931104   \n",
       "3  0.612002    0.031157          0.953212       0.953177   \n",
       "4  0.633640    0.031258          0.950433       0.950469   \n",
       "5  0.613514    0.032039          0.948453       0.948461   \n",
       "6  0.627126    0.031707          0.955164       0.955154   \n",
       "7  0.602817    0.030996          0.960664       0.960509   \n",
       "8  0.642092    0.033562          0.971895       0.971888   \n",
       "9  0.626742    0.031195          0.964507       0.964525   \n",
       "\n",
       "   test_precision_weighted  test_recall_weighted  \n",
       "0                 0.954022              0.952508  \n",
       "1                 0.948694              0.947157  \n",
       "2                 0.934459              0.931104  \n",
       "3                 0.954690              0.953177  \n",
       "4                 0.951912              0.950469  \n",
       "5                 0.950309              0.948461  \n",
       "6                 0.956681              0.955154  \n",
       "7                 0.961661              0.960509  \n",
       "8                 0.972393              0.971888  \n",
       "9                 0.965375              0.964525  "
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Random Forest\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "modelRF= RandomForestClassifier(n_estimators=100,  max_samples=0.8, criterion='gini',\n",
    "                                max_depth=None, min_samples_leaf=2)\n",
    "\n",
    "scores = cross_validate(modelRF, X_train, Y_train, cv=10, scoring=('f1_weighted', 'accuracy', 'precision_weighted', 'recall_weighted'), \n",
    "                        return_train_score=False, return_estimator=False)\n",
    "scores=pd.DataFrame(scores)\n",
    "scores"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Promedio F1 Score: 0.95\n",
      "Promedio Accuracy: 0.95\n",
      "Promedio Precision: 0.96\n",
      "Promedio Recall: 0.95\n"
     ]
    }
   ],
   "source": [
    "# Calcular los valores promedio de cada métrica\n",
    "promedio_f1 = scores['test_f1_weighted'].mean()\n",
    "promedio_accuracy = scores['test_accuracy'].mean()\n",
    "promedio_precision = scores['test_precision_weighted'].mean()\n",
    "promedio_recall = scores['test_recall_weighted'].mean()\n",
    "\n",
    "# Imprimir los valores promedio\n",
    "print(\"Promedio F1 Score: {:.2f}\".format(promedio_f1))\n",
    "print(\"Promedio Accuracy: {:.2f}\".format(promedio_accuracy))\n",
    "print(\"Promedio Precision: {:.2f}\".format(promedio_precision))\n",
    "print(\"Promedio Recall: {:.2f}\".format(promedio_recall))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-5 {color: black;}#sk-container-id-5 pre{padding: 0;}#sk-container-id-5 div.sk-toggleable {background-color: white;}#sk-container-id-5 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-5 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-5 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-5 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-5 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-5 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-5 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-5 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-5 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-5 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-5 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-5 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-5 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-5 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-5 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-5 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-5 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-5 div.sk-item {position: relative;z-index: 1;}#sk-container-id-5 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-5 div.sk-item::before, #sk-container-id-5 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-5 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-5 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-5 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-5 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-5 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-5 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-5 div.sk-label-container {text-align: center;}#sk-container-id-5 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-5 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-5\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier(max_samples=0.8, min_samples_leaf=2)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" checked><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier(max_samples=0.8, min_samples_leaf=2)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "RandomForestClassifier(max_samples=0.8, min_samples_leaf=2)"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Entrenamiento del modelo con el 70%\n",
    "modelRF.fit(X_train, Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "******* Resultados de evaluación*******\n",
      "Precisión: 0.9276845901238505\n",
      "Sensibilidad: 0.9243846739406242\n",
      "Exactitud: 0.9243846739406242\n",
      "F1_Score: 0.9247175057526315\n",
      "                     0            1            2          3  accuracy  \\\n",
      "precision     0.885770     0.877473     0.998673   0.804598  0.924385   \n",
      "recall        0.848794     0.967282     0.940037   1.000000  0.924385   \n",
      "f1-score      0.866888     0.920192     0.968468   0.891720  0.924385   \n",
      "support    1078.000000  1192.000000  1601.000000  70.000000  0.924385   \n",
      "\n",
      "             macro avg  weighted avg  \n",
      "precision     0.891628      0.927685  \n",
      "recall        0.939028      0.924385  \n",
      "f1-score      0.911817      0.924718  \n",
      "support    3941.000000   3941.000000  \n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "precision, sensibilidad, exactitud, f1score = evaluacion_modelos(modelRF, X_test, Y_test)\n",
    "\n",
    "medidas['Random Forest'] = [precision, sensibilidad, exactitud, f1score]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 3.6. XGBoost"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Se instala la librería xgboost\n",
    "# !pip install xgboost"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "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>fit_time</th>\n",
       "      <th>score_time</th>\n",
       "      <th>test_f1_weighted</th>\n",
       "      <th>test_accuracy</th>\n",
       "      <th>test_precision_weighted</th>\n",
       "      <th>test_recall_weighted</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.307120</td>\n",
       "      <td>0.013308</td>\n",
       "      <td>0.950472</td>\n",
       "      <td>0.950502</td>\n",
       "      <td>0.952545</td>\n",
       "      <td>0.950502</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.215778</td>\n",
       "      <td>0.012672</td>\n",
       "      <td>0.947065</td>\n",
       "      <td>0.947157</td>\n",
       "      <td>0.949458</td>\n",
       "      <td>0.947157</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.213046</td>\n",
       "      <td>0.012820</td>\n",
       "      <td>0.930311</td>\n",
       "      <td>0.930435</td>\n",
       "      <td>0.933591</td>\n",
       "      <td>0.930435</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.236907</td>\n",
       "      <td>0.013251</td>\n",
       "      <td>0.949058</td>\n",
       "      <td>0.949164</td>\n",
       "      <td>0.951619</td>\n",
       "      <td>0.949164</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.592135</td>\n",
       "      <td>0.012859</td>\n",
       "      <td>0.946392</td>\n",
       "      <td>0.946452</td>\n",
       "      <td>0.948273</td>\n",
       "      <td>0.946452</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.246458</td>\n",
       "      <td>0.013289</td>\n",
       "      <td>0.939651</td>\n",
       "      <td>0.939759</td>\n",
       "      <td>0.942280</td>\n",
       "      <td>0.939759</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0.233993</td>\n",
       "      <td>0.021974</td>\n",
       "      <td>0.951076</td>\n",
       "      <td>0.951138</td>\n",
       "      <td>0.953078</td>\n",
       "      <td>0.951138</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0.222746</td>\n",
       "      <td>0.012479</td>\n",
       "      <td>0.950400</td>\n",
       "      <td>0.950469</td>\n",
       "      <td>0.952396</td>\n",
       "      <td>0.950469</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0.215895</td>\n",
       "      <td>0.012690</td>\n",
       "      <td>0.960479</td>\n",
       "      <td>0.960509</td>\n",
       "      <td>0.961628</td>\n",
       "      <td>0.960509</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0.219626</td>\n",
       "      <td>0.012604</td>\n",
       "      <td>0.953092</td>\n",
       "      <td>0.953146</td>\n",
       "      <td>0.954838</td>\n",
       "      <td>0.953146</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   fit_time  score_time  test_f1_weighted  test_accuracy  \\\n",
       "0  0.307120    0.013308          0.950472       0.950502   \n",
       "1  0.215778    0.012672          0.947065       0.947157   \n",
       "2  0.213046    0.012820          0.930311       0.930435   \n",
       "3  0.236907    0.013251          0.949058       0.949164   \n",
       "4  0.592135    0.012859          0.946392       0.946452   \n",
       "5  0.246458    0.013289          0.939651       0.939759   \n",
       "6  0.233993    0.021974          0.951076       0.951138   \n",
       "7  0.222746    0.012479          0.950400       0.950469   \n",
       "8  0.215895    0.012690          0.960479       0.960509   \n",
       "9  0.219626    0.012604          0.953092       0.953146   \n",
       "\n",
       "   test_precision_weighted  test_recall_weighted  \n",
       "0                 0.952545              0.950502  \n",
       "1                 0.949458              0.947157  \n",
       "2                 0.933591              0.930435  \n",
       "3                 0.951619              0.949164  \n",
       "4                 0.948273              0.946452  \n",
       "5                 0.942280              0.939759  \n",
       "6                 0.953078              0.951138  \n",
       "7                 0.952396              0.950469  \n",
       "8                 0.961628              0.960509  \n",
       "9                 0.954838              0.953146  "
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from xgboost import XGBClassifier\n",
    "modelXGB = XGBClassifier(learning_rate=0.1, n_estimators=100, max_depth=3, random_state=42)\n",
    "\n",
    "scores = cross_validate(modelXGB, X_train, Y_train, cv=10, scoring=('f1_weighted', 'accuracy', 'precision_weighted', 'recall_weighted'), \n",
    "                        return_train_score=False, return_estimator=False)\n",
    "scores=pd.DataFrame(scores)\n",
    "scores"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Promedio F1 Score: 0.95\n",
      "Promedio Accuracy: 0.95\n",
      "Promedio Precision: 0.95\n",
      "Promedio Recall: 0.95\n"
     ]
    }
   ],
   "source": [
    "# Calcular los valores promedio de cada métrica\n",
    "promedio_f1 = scores['test_f1_weighted'].mean()\n",
    "promedio_accuracy = scores['test_accuracy'].mean()\n",
    "promedio_precision = scores['test_precision_weighted'].mean()\n",
    "promedio_recall = scores['test_recall_weighted'].mean()\n",
    "\n",
    "# Imprimir los valores promedio\n",
    "print(\"Promedio F1 Score: {:.2f}\".format(promedio_f1))\n",
    "print(\"Promedio Accuracy: {:.2f}\".format(promedio_accuracy))\n",
    "print(\"Promedio Precision: {:.2f}\".format(promedio_precision))\n",
    "print(\"Promedio Recall: {:.2f}\".format(promedio_recall))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-6 {color: black;}#sk-container-id-6 pre{padding: 0;}#sk-container-id-6 div.sk-toggleable {background-color: white;}#sk-container-id-6 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-6 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-6 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-6 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-6 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-6 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-6 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-6 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-6 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-6 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-6 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-6 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-6 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-6 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-6 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-6 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-6 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-6 div.sk-item {position: relative;z-index: 1;}#sk-container-id-6 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-6 div.sk-item::before, #sk-container-id-6 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-6 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-6 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-6 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-6 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-6 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-6 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-6 div.sk-label-container {text-align: center;}#sk-container-id-6 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-6 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-6\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
       "              colsample_bylevel=None, colsample_bynode=None,\n",
       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
       "              gamma=None, grow_policy=None, importance_type=None,\n",
       "              interaction_constraints=None, learning_rate=0.1, max_bin=None,\n",
       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
       "              max_delta_step=None, max_depth=3, max_leaves=None,\n",
       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
       "              multi_strategy=None, n_estimators=100, n_jobs=None,\n",
       "              num_parallel_tree=None, objective=&#x27;multi:softprob&#x27;, ...)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" checked><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">XGBClassifier</label><div class=\"sk-toggleable__content\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
       "              colsample_bylevel=None, colsample_bynode=None,\n",
       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
       "              gamma=None, grow_policy=None, importance_type=None,\n",
       "              interaction_constraints=None, learning_rate=0.1, max_bin=None,\n",
       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
       "              max_delta_step=None, max_depth=3, max_leaves=None,\n",
       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
       "              multi_strategy=None, n_estimators=100, n_jobs=None,\n",
       "              num_parallel_tree=None, objective=&#x27;multi:softprob&#x27;, ...)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
       "              colsample_bylevel=None, colsample_bynode=None,\n",
       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
       "              gamma=None, grow_policy=None, importance_type=None,\n",
       "              interaction_constraints=None, learning_rate=0.1, max_bin=None,\n",
       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
       "              max_delta_step=None, max_depth=3, max_leaves=None,\n",
       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
       "              multi_strategy=None, n_estimators=100, n_jobs=None,\n",
       "              num_parallel_tree=None, objective='multi:softprob', ...)"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Entrenamiento del modelo con el 70%\n",
    "modelXGB.fit(X_train, Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "******* Resultados de evaluación*******\n",
      "Precisión: 0.9298195700569701\n",
      "Sensibilidad: 0.9253996447602132\n",
      "Exactitud: 0.9253996447602132\n",
      "F1_Score: 0.9257886973802311\n",
      "                     0            1            2          3  accuracy  \\\n",
      "precision     0.902874     0.871642     1.000000   0.730337    0.9254   \n",
      "recall        0.845083     0.979866     0.938788   0.928571    0.9254   \n",
      "f1-score      0.873023     0.922591     0.968428   0.817610    0.9254   \n",
      "support    1078.000000  1192.000000  1601.000000  70.000000    0.9254   \n",
      "\n",
      "             macro avg  weighted avg  \n",
      "precision     0.876213      0.929820  \n",
      "recall        0.923077      0.925400  \n",
      "f1-score      0.895413      0.925789  \n",
      "support    3941.000000   3941.000000  \n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "precision, sensibilidad, exactitud, f1score = evaluacion_modelos(modelXGB, X_test, Y_test)\n",
    "\n",
    "medidas['XGBoost'] = [precision, sensibilidad, exactitud, f1score]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 3.7. Stacking"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "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>fit_time</th>\n",
       "      <th>score_time</th>\n",
       "      <th>test_f1_weighted</th>\n",
       "      <th>test_accuracy</th>\n",
       "      <th>test_precision_weighted</th>\n",
       "      <th>test_recall_weighted</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6.049219</td>\n",
       "      <td>0.148677</td>\n",
       "      <td>0.947936</td>\n",
       "      <td>0.947826</td>\n",
       "      <td>0.949301</td>\n",
       "      <td>0.947826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>7.032371</td>\n",
       "      <td>0.123111</td>\n",
       "      <td>0.942444</td>\n",
       "      <td>0.942475</td>\n",
       "      <td>0.943921</td>\n",
       "      <td>0.942475</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7.042439</td>\n",
       "      <td>0.130297</td>\n",
       "      <td>0.929914</td>\n",
       "      <td>0.929766</td>\n",
       "      <td>0.933060</td>\n",
       "      <td>0.929766</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>6.653214</td>\n",
       "      <td>0.097340</td>\n",
       "      <td>0.947778</td>\n",
       "      <td>0.947826</td>\n",
       "      <td>0.949679</td>\n",
       "      <td>0.947826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6.895399</td>\n",
       "      <td>0.147861</td>\n",
       "      <td>0.946409</td>\n",
       "      <td>0.946452</td>\n",
       "      <td>0.947987</td>\n",
       "      <td>0.946452</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6.258441</td>\n",
       "      <td>0.108552</td>\n",
       "      <td>0.943645</td>\n",
       "      <td>0.943775</td>\n",
       "      <td>0.945596</td>\n",
       "      <td>0.943775</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>7.184215</td>\n",
       "      <td>0.099283</td>\n",
       "      <td>0.949141</td>\n",
       "      <td>0.949130</td>\n",
       "      <td>0.950735</td>\n",
       "      <td>0.949130</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>6.625060</td>\n",
       "      <td>0.100077</td>\n",
       "      <td>0.952559</td>\n",
       "      <td>0.952477</td>\n",
       "      <td>0.953674</td>\n",
       "      <td>0.952477</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>7.547682</td>\n",
       "      <td>0.116984</td>\n",
       "      <td>0.964541</td>\n",
       "      <td>0.964525</td>\n",
       "      <td>0.965122</td>\n",
       "      <td>0.964525</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>8.117346</td>\n",
       "      <td>0.129329</td>\n",
       "      <td>0.960393</td>\n",
       "      <td>0.960509</td>\n",
       "      <td>0.961529</td>\n",
       "      <td>0.960509</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   fit_time  score_time  test_f1_weighted  test_accuracy  \\\n",
       "0  6.049219    0.148677          0.947936       0.947826   \n",
       "1  7.032371    0.123111          0.942444       0.942475   \n",
       "2  7.042439    0.130297          0.929914       0.929766   \n",
       "3  6.653214    0.097340          0.947778       0.947826   \n",
       "4  6.895399    0.147861          0.946409       0.946452   \n",
       "5  6.258441    0.108552          0.943645       0.943775   \n",
       "6  7.184215    0.099283          0.949141       0.949130   \n",
       "7  6.625060    0.100077          0.952559       0.952477   \n",
       "8  7.547682    0.116984          0.964541       0.964525   \n",
       "9  8.117346    0.129329          0.960393       0.960509   \n",
       "\n",
       "   test_precision_weighted  test_recall_weighted  \n",
       "0                 0.949301              0.947826  \n",
       "1                 0.943921              0.942475  \n",
       "2                 0.933060              0.929766  \n",
       "3                 0.949679              0.947826  \n",
       "4                 0.947987              0.946452  \n",
       "5                 0.945596              0.943775  \n",
       "6                 0.950735              0.949130  \n",
       "7                 0.953674              0.952477  \n",
       "8                 0.965122              0.964525  \n",
       "9                 0.961529              0.960509  "
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.ensemble import StackingClassifier\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "\n",
    "clasificadores= [('Tree', modelTree), ('KNN', modelKnn), ('RN', modelNN)]\n",
    "\n",
    "metodo_ensamblador= LogisticRegression(multi_class='ovr')\n",
    "\n",
    "modelStacking= StackingClassifier(estimators=clasificadores, final_estimator=metodo_ensamblador)\n",
    "\n",
    "scores = cross_validate(modelStacking, X_train, Y_train, cv=10, scoring=('f1_weighted', 'accuracy', 'precision_weighted', 'recall_weighted'), \n",
    "                        return_train_score=False, return_estimator=False)\n",
    "scores=pd.DataFrame(scores)\n",
    "scores"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Promedio F1 Score: 0.95\n",
      "Promedio Accuracy: 0.95\n",
      "Promedio Precision: 0.95\n",
      "Promedio Recall: 0.95\n"
     ]
    }
   ],
   "source": [
    "# Calcular los valores promedio de cada métrica\n",
    "promedio_f1 = scores['test_f1_weighted'].mean()\n",
    "promedio_accuracy = scores['test_accuracy'].mean()\n",
    "promedio_precision = scores['test_precision_weighted'].mean()\n",
    "promedio_recall = scores['test_recall_weighted'].mean()\n",
    "\n",
    "# Imprimir los valores promedio\n",
    "print(\"Promedio F1 Score: {:.2f}\".format(promedio_f1))\n",
    "print(\"Promedio Accuracy: {:.2f}\".format(promedio_accuracy))\n",
    "print(\"Promedio Precision: {:.2f}\".format(promedio_precision))\n",
    "print(\"Promedio Recall: {:.2f}\".format(promedio_recall))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-7 {color: black;}#sk-container-id-7 pre{padding: 0;}#sk-container-id-7 div.sk-toggleable {background-color: white;}#sk-container-id-7 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-7 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-7 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-7 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-7 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-7 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-7 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-7 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-7 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-7 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-7 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-7 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-7 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-7 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-7 div.sk-item {position: relative;z-index: 1;}#sk-container-id-7 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-7 div.sk-item::before, #sk-container-id-7 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-7 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-7 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-7 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-7 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-7 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-7 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-7 div.sk-label-container {text-align: center;}#sk-container-id-7 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-7 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-7\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>StackingClassifier(estimators=[(&#x27;Tree&#x27;,\n",
       "                                DecisionTreeClassifier(max_depth=10,\n",
       "                                                       min_samples_leaf=2)),\n",
       "                               (&#x27;KNN&#x27;,\n",
       "                                KNeighborsClassifier(metric=&#x27;euclidean&#x27;,\n",
       "                                                     n_neighbors=3)),\n",
       "                               (&#x27;RN&#x27;,\n",
       "                                MLPClassifier(activation=&#x27;logistic&#x27;,\n",
       "                                              hidden_layer_sizes=5,\n",
       "                                              learning_rate_init=0.2,\n",
       "                                              max_iter=500, momentum=0.3,\n",
       "                                              random_state=42))],\n",
       "                   final_estimator=LogisticRegression(multi_class=&#x27;ovr&#x27;))</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" ><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StackingClassifier</label><div class=\"sk-toggleable__content\"><pre>StackingClassifier(estimators=[(&#x27;Tree&#x27;,\n",
       "                                DecisionTreeClassifier(max_depth=10,\n",
       "                                                       min_samples_leaf=2)),\n",
       "                               (&#x27;KNN&#x27;,\n",
       "                                KNeighborsClassifier(metric=&#x27;euclidean&#x27;,\n",
       "                                                     n_neighbors=3)),\n",
       "                               (&#x27;RN&#x27;,\n",
       "                                MLPClassifier(activation=&#x27;logistic&#x27;,\n",
       "                                              hidden_layer_sizes=5,\n",
       "                                              learning_rate_init=0.2,\n",
       "                                              max_iter=500, momentum=0.3,\n",
       "                                              random_state=42))],\n",
       "                   final_estimator=LogisticRegression(multi_class=&#x27;ovr&#x27;))</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><label>Tree</label></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" ><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">DecisionTreeClassifier</label><div class=\"sk-toggleable__content\"><pre>DecisionTreeClassifier(max_depth=10, min_samples_leaf=2)</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><label>KNN</label></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-9\" type=\"checkbox\" ><label for=\"sk-estimator-id-9\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">KNeighborsClassifier</label><div class=\"sk-toggleable__content\"><pre>KNeighborsClassifier(metric=&#x27;euclidean&#x27;, n_neighbors=3)</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><label>RN</label></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-10\" type=\"checkbox\" ><label for=\"sk-estimator-id-10\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MLPClassifier</label><div class=\"sk-toggleable__content\"><pre>MLPClassifier(activation=&#x27;logistic&#x27;, hidden_layer_sizes=5,\n",
       "              learning_rate_init=0.2, max_iter=500, momentum=0.3,\n",
       "              random_state=42)</pre></div></div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><label>final_estimator</label></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-11\" type=\"checkbox\" ><label for=\"sk-estimator-id-11\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression(multi_class=&#x27;ovr&#x27;)</pre></div></div></div></div></div></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "StackingClassifier(estimators=[('Tree',\n",
       "                                DecisionTreeClassifier(max_depth=10,\n",
       "                                                       min_samples_leaf=2)),\n",
       "                               ('KNN',\n",
       "                                KNeighborsClassifier(metric='euclidean',\n",
       "                                                     n_neighbors=3)),\n",
       "                               ('RN',\n",
       "                                MLPClassifier(activation='logistic',\n",
       "                                              hidden_layer_sizes=5,\n",
       "                                              learning_rate_init=0.2,\n",
       "                                              max_iter=500, momentum=0.3,\n",
       "                                              random_state=42))],\n",
       "                   final_estimator=LogisticRegression(multi_class='ovr'))"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Entrenamiento del modelo con el 70%\n",
    "modelStacking.fit(X_train, Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "******* Resultados de evaluación*******\n",
      "Precisión: 0.926262200306422\n",
      "Sensibilidad: 0.9233697031210353\n",
      "Exactitud: 0.9233697031210353\n",
      "F1_Score: 0.9234407334098176\n",
      "                     0            1            2          3  accuracy  \\\n",
      "precision     0.892611     0.875094     0.992095   0.810127   0.92337   \n",
      "recall        0.840445     0.975671     0.940662   0.914286   0.92337   \n",
      "f1-score      0.865743     0.922650     0.965694   0.859060   0.92337   \n",
      "support    1078.000000  1192.000000  1601.000000  70.000000   0.92337   \n",
      "\n",
      "             macro avg  weighted avg  \n",
      "precision     0.892482      0.926262  \n",
      "recall        0.917766      0.923370  \n",
      "f1-score      0.903287      0.923441  \n",
      "support    3941.000000   3941.000000  \n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "precision, sensibilidad, exactitud, f1score = evaluacion_modelos(modelStacking, X_test, Y_test)\n",
    "\n",
    "medidas['Stacking'] = [precision, sensibilidad, exactitud, f1score]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 4. Hiperparametrización de los 3 mejores modelos"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "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>DecisionTree</th>\n",
       "      <th>KNN</th>\n",
       "      <th>Red Neuronal</th>\n",
       "      <th>SVM</th>\n",
       "      <th>Random Forest</th>\n",
       "      <th>XGBoost</th>\n",
       "      <th>Stacking</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Precisión</th>\n",
       "      <td>0.929639</td>\n",
       "      <td>0.755536</td>\n",
       "      <td>0.885049</td>\n",
       "      <td>0.891522</td>\n",
       "      <td>0.927685</td>\n",
       "      <td>0.929820</td>\n",
       "      <td>0.926262</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Sensibilidad</th>\n",
       "      <td>0.926668</td>\n",
       "      <td>0.734331</td>\n",
       "      <td>0.872367</td>\n",
       "      <td>0.881756</td>\n",
       "      <td>0.924385</td>\n",
       "      <td>0.925400</td>\n",
       "      <td>0.923370</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Exactitud</th>\n",
       "      <td>0.926668</td>\n",
       "      <td>0.734331</td>\n",
       "      <td>0.872367</td>\n",
       "      <td>0.881756</td>\n",
       "      <td>0.924385</td>\n",
       "      <td>0.925400</td>\n",
       "      <td>0.923370</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>F1_Score</th>\n",
       "      <td>0.926887</td>\n",
       "      <td>0.740751</td>\n",
       "      <td>0.875697</td>\n",
       "      <td>0.884552</td>\n",
       "      <td>0.924718</td>\n",
       "      <td>0.925789</td>\n",
       "      <td>0.923441</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              DecisionTree       KNN  Red Neuronal       SVM  Random Forest  \\\n",
       "Precisión         0.929639  0.755536      0.885049  0.891522       0.927685   \n",
       "Sensibilidad      0.926668  0.734331      0.872367  0.881756       0.924385   \n",
       "Exactitud         0.926668  0.734331      0.872367  0.881756       0.924385   \n",
       "F1_Score          0.926887  0.740751      0.875697  0.884552       0.924718   \n",
       "\n",
       "               XGBoost  Stacking  \n",
       "Precisión     0.929820  0.926262  \n",
       "Sensibilidad  0.925400  0.923370  \n",
       "Exactitud     0.925400  0.923370  \n",
       "F1_Score      0.925789  0.923441  "
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "medidas"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "La sensibilidad se centra en la capacidad del modelo para identificar positivos reales, es decir, casos de anemia. Es por esto que los mejores modelos se escogen a partir de esta métrica.\n",
    "\n",
    "**Los modelos escogidos son: XGBoost, Random Forest y Stacking**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [],
   "source": [
    "medidas_hiper = pd.DataFrame(index=['f1 de la CV'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4.1. XGBoost"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'learning_rate': 0.2, 'max_depth': 6, 'n_estimators': 100}\n",
      "              XGBoost\n",
      "f1 de la CV  0.949176\n"
     ]
    }
   ],
   "source": [
    "# XGBoost\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "\n",
    "modelXGB_base = XGBClassifier()\n",
    "\n",
    "# Definir los hiperparámetros\n",
    "learning_rate = [0.01, 0.1, 0.2]\n",
    "n_estimators = [50, 100, 200]\n",
    "max_depth = [2, 4, 6]\n",
    "\n",
    "# Grid\n",
    "param_grid = dict(learning_rate=learning_rate, n_estimators=n_estimators, max_depth=max_depth)\n",
    "grid = GridSearchCV(estimator=modelXGB_base, param_grid=param_grid, scoring='f1_macro', n_jobs=-1, cv=10)\n",
    "grid.fit(X_train, Y_train)\n",
    "\n",
    "# Mejor modelo\n",
    "modelXGB_Hiper = grid.best_estimator_\n",
    "\n",
    "# Medida de evaluación del mejor modelo\n",
    "medidas_hiper['XGBoost'] = grid.best_score_\n",
    "\n",
    "# Mejores parámetros\n",
    "print(grid.best_params_)\n",
    "\n",
    "print(medidas_hiper)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4.2. Random Forest"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'max_depth': 6, 'min_samples_split': 5, 'n_estimators': 200}\n",
      "              XGBoost  Random Forest\n",
      "f1 de la CV  0.949176       0.949888\n"
     ]
    }
   ],
   "source": [
    "# RandomForest\n",
    "modelRF_base = RandomForestClassifier()\n",
    "\n",
    "# Definir los hiperparámetros\n",
    "n_estimators = [50, 100, 200]\n",
    "max_depth = [2, 4, 6]\n",
    "min_samples_split = [2, 5, 10]\n",
    "\n",
    "# Grid\n",
    "param_grid = dict(n_estimators=n_estimators, max_depth=max_depth, min_samples_split=min_samples_split)\n",
    "grid = GridSearchCV(estimator=modelRF_base, param_grid=param_grid, scoring='f1_macro', n_jobs=-1, cv=10)\n",
    "grid.fit(X_train, Y_train)\n",
    "\n",
    "# Mejor modelo\n",
    "modelRF_Hiper = grid.best_estimator_\n",
    "\n",
    "# Medida de evaluación del mejor modelo\n",
    "medidas_hiper['Random Forest'] = grid.best_score_\n",
    "\n",
    "# Mejores parámetros\n",
    "print(grid.best_params_)\n",
    "\n",
    "print(medidas_hiper)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4.3. Stacking"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:698: UserWarning: Training interrupted by user.\n",
      "  warnings.warn(\"Training interrupted by user.\")\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/home/codespace/.local/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'final_estimator': MLPClassifier()}\n",
      "              XGBoost  Random Forest  Stacking\n",
      "f1 de la CV  0.949176       0.949888  0.944728\n"
     ]
    }
   ],
   "source": [
    "#Stacking\n",
    "base_classifiers = [\n",
    "    ('Tree', DecisionTreeClassifier()),\n",
    "    ('KNN', KNeighborsClassifier()),\n",
    "    ('RN', MLPClassifier())\n",
    "]\n",
    "\n",
    "# Definir los clasificadores finales\n",
    "final_classifiers = [\n",
    "    LogisticRegression(multi_class='ovr'),\n",
    "    DecisionTreeClassifier(),\n",
    "    KNeighborsClassifier(),\n",
    "    MLPClassifier()\n",
    "]\n",
    "\n",
    "# Definir los hiperparámetros\n",
    "param_grid = {\n",
    "    'final_estimator': final_classifiers\n",
    "}\n",
    "\n",
    "# Crear el modelo\n",
    "stacking = StackingClassifier(estimators=base_classifiers)\n",
    "\n",
    "# Crear el grid\n",
    "grid = GridSearchCV(stacking, param_grid)\n",
    "\n",
    "grid.fit(X_train, Y_train)\n",
    "\n",
    "# Mejor modelo\n",
    "modelStacking_Hiper = grid.best_estimator_\n",
    "\n",
    "# Medida de evaluación del mejor modelo\n",
    "medidas_hiper['Stacking'] = grid.best_score_\n",
    "\n",
    "# Mejores parámetros\n",
    "print(grid.best_params_)\n",
    "\n",
    "print(medidas_hiper)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 5. Guardar el mejor modelo"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "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>Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)</th>\n",
       "      <th>When child put to breast</th>\n",
       "      <th>Age in 5-year groups_20-24</th>\n",
       "      <th>Age in 5-year groups_25-29</th>\n",
       "      <th>Age in 5-year groups_30-34</th>\n",
       "      <th>Age in 5-year groups_35-39</th>\n",
       "      <th>Age in 5-year groups_40-44</th>\n",
       "      <th>Age in 5-year groups_45-49</th>\n",
       "      <th>Type of place of residence_Urban</th>\n",
       "      <th>Wealth index combined_Poorer</th>\n",
       "      <th>Wealth index combined_Poorest</th>\n",
       "      <th>Wealth index combined_Richer</th>\n",
       "      <th>Wealth index combined_Richest</th>\n",
       "      <th>Have mosquito bed net for sleeping (from household questionnaire)_Yes</th>\n",
       "      <th>Smokes cigarettes_Yes</th>\n",
       "      <th>Had fever in last two weeks_No</th>\n",
       "      <th>Had fever in last two weeks_Yes</th>\n",
       "      <th>Taking iron pills, sprinkles or syrup_No</th>\n",
       "      <th>Taking iron pills, sprinkles or syrup_Yes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>95.0</td>\n",
       "      <td>105.000000</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>113.0</td>\n",
       "      <td>51.335329</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>121.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>121.0</td>\n",
       "      <td>51.335329</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>108.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13131</th>\n",
       "      <td>120.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13132</th>\n",
       "      <td>120.0</td>\n",
       "      <td>51.335329</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13133</th>\n",
       "      <td>120.0</td>\n",
       "      <td>60.000000</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13134</th>\n",
       "      <td>149.0</td>\n",
       "      <td>60.000000</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13135</th>\n",
       "      <td>123.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>13136 rows × 19 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)  \\\n",
       "0                                                   95.0                       \n",
       "1                                                  113.0                       \n",
       "2                                                  121.0                       \n",
       "3                                                  121.0                       \n",
       "4                                                  108.0                       \n",
       "...                                                  ...                       \n",
       "13131                                              120.0                       \n",
       "13132                                              120.0                       \n",
       "13133                                              120.0                       \n",
       "13134                                              149.0                       \n",
       "13135                                              123.0                       \n",
       "\n",
       "       When child put to breast  Age in 5-year groups_20-24  \\\n",
       "0                    105.000000                           0   \n",
       "1                     51.335329                           0   \n",
       "2                      0.000000                           0   \n",
       "3                     51.335329                           0   \n",
       "4                      0.000000                           1   \n",
       "...                         ...                         ...   \n",
       "13131                  0.000000                           0   \n",
       "13132                 51.335329                           0   \n",
       "13133                 60.000000                           0   \n",
       "13134                 60.000000                           0   \n",
       "13135                  0.000000                           1   \n",
       "\n",
       "       Age in 5-year groups_25-29  Age in 5-year groups_30-34  \\\n",
       "0                               1                           0   \n",
       "1                               0                           1   \n",
       "2                               0                           0   \n",
       "3                               0                           0   \n",
       "4                               0                           0   \n",
       "...                           ...                         ...   \n",
       "13131                           0                           0   \n",
       "13132                           0                           0   \n",
       "13133                           1                           0   \n",
       "13134                           1                           0   \n",
       "13135                           0                           0   \n",
       "\n",
       "       Age in 5-year groups_35-39  Age in 5-year groups_40-44  \\\n",
       "0                               0                           0   \n",
       "1                               0                           0   \n",
       "2                               1                           0   \n",
       "3                               1                           0   \n",
       "4                               0                           0   \n",
       "...                           ...                         ...   \n",
       "13131                           1                           0   \n",
       "13132                           1                           0   \n",
       "13133                           0                           0   \n",
       "13134                           0                           0   \n",
       "13135                           0                           0   \n",
       "\n",
       "       Age in 5-year groups_45-49  Type of place of residence_Urban  \\\n",
       "0                               0                                 1   \n",
       "1                               0                                 1   \n",
       "2                               0                                 1   \n",
       "3                               0                                 1   \n",
       "4                               0                                 1   \n",
       "...                           ...                               ...   \n",
       "13131                           0                                 0   \n",
       "13132                           0                                 0   \n",
       "13133                           0                                 0   \n",
       "13134                           0                                 0   \n",
       "13135                           0                                 0   \n",
       "\n",
       "       Wealth index combined_Poorer  Wealth index combined_Poorest  \\\n",
       "0                                 0                              0   \n",
       "1                                 0                              0   \n",
       "2                                 0                              0   \n",
       "3                                 0                              0   \n",
       "4                                 0                              0   \n",
       "...                             ...                            ...   \n",
       "13131                             0                              0   \n",
       "13132                             0                              0   \n",
       "13133                             0                              0   \n",
       "13134                             0                              0   \n",
       "13135                             0                              0   \n",
       "\n",
       "       Wealth index combined_Richer  Wealth index combined_Richest  \\\n",
       "0                                 0                              1   \n",
       "1                                 0                              1   \n",
       "2                                 0                              1   \n",
       "3                                 0                              1   \n",
       "4                                 0                              1   \n",
       "...                             ...                            ...   \n",
       "13131                             1                              0   \n",
       "13132                             1                              0   \n",
       "13133                             1                              0   \n",
       "13134                             1                              0   \n",
       "13135                             1                              0   \n",
       "\n",
       "       Have mosquito bed net for sleeping (from household questionnaire)_Yes  \\\n",
       "0                                                      1                       \n",
       "1                                                      1                       \n",
       "2                                                      1                       \n",
       "3                                                      1                       \n",
       "4                                                      1                       \n",
       "...                                                  ...                       \n",
       "13131                                                  1                       \n",
       "13132                                                  1                       \n",
       "13133                                                  1                       \n",
       "13134                                                  1                       \n",
       "13135                                                  1                       \n",
       "\n",
       "       Smokes cigarettes_Yes  Had fever in last two weeks_No  \\\n",
       "0                          0                               1   \n",
       "1                          0                               1   \n",
       "2                          0                               1   \n",
       "3                          0                               1   \n",
       "4                          0                               1   \n",
       "...                      ...                             ...   \n",
       "13131                      0                               1   \n",
       "13132                      0                               1   \n",
       "13133                      0                               1   \n",
       "13134                      0                               1   \n",
       "13135                      0                               1   \n",
       "\n",
       "       Had fever in last two weeks_Yes  \\\n",
       "0                                    0   \n",
       "1                                    0   \n",
       "2                                    0   \n",
       "3                                    0   \n",
       "4                                    0   \n",
       "...                                ...   \n",
       "13131                                0   \n",
       "13132                                0   \n",
       "13133                                0   \n",
       "13134                                0   \n",
       "13135                                0   \n",
       "\n",
       "       Taking iron pills, sprinkles or syrup_No  \\\n",
       "0                                             1   \n",
       "1                                             1   \n",
       "2                                             0   \n",
       "3                                             1   \n",
       "4                                             0   \n",
       "...                                         ...   \n",
       "13131                                         0   \n",
       "13132                                         0   \n",
       "13133                                         1   \n",
       "13134                                         1   \n",
       "13135                                         0   \n",
       "\n",
       "       Taking iron pills, sprinkles or syrup_Yes  \n",
       "0                                              0  \n",
       "1                                              0  \n",
       "2                                              1  \n",
       "3                                              0  \n",
       "4                                              1  \n",
       "...                                          ...  \n",
       "13131                                          1  \n",
       "13132                                          1  \n",
       "13133                                          0  \n",
       "13134                                          0  \n",
       "13135                                          1  \n",
       "\n",
       "[13136 rows x 19 columns]"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X = pd.get_dummies(X, drop_first=True, dtype='int64')\n",
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "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>Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)</th>\n",
       "      <th>When child put to breast</th>\n",
       "      <th>Age in 5-year groups_20-24</th>\n",
       "      <th>Age in 5-year groups_25-29</th>\n",
       "      <th>Age in 5-year groups_30-34</th>\n",
       "      <th>Age in 5-year groups_35-39</th>\n",
       "      <th>Age in 5-year groups_40-44</th>\n",
       "      <th>Age in 5-year groups_45-49</th>\n",
       "      <th>Type of place of residence_Urban</th>\n",
       "      <th>Wealth index combined_Poorer</th>\n",
       "      <th>Wealth index combined_Poorest</th>\n",
       "      <th>Wealth index combined_Richer</th>\n",
       "      <th>Wealth index combined_Richest</th>\n",
       "      <th>Have mosquito bed net for sleeping (from household questionnaire)_Yes</th>\n",
       "      <th>Smokes cigarettes_Yes</th>\n",
       "      <th>Had fever in last two weeks_No</th>\n",
       "      <th>Had fever in last two weeks_Yes</th>\n",
       "      <th>Taking iron pills, sprinkles or syrup_No</th>\n",
       "      <th>Taking iron pills, sprinkles or syrup_Yes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.535714</td>\n",
       "      <td>0.470852</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.664286</td>\n",
       "      <td>0.230203</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.721429</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.721429</td>\n",
       "      <td>0.230203</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.628571</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13131</th>\n",
       "      <td>0.714286</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13132</th>\n",
       "      <td>0.714286</td>\n",
       "      <td>0.230203</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13133</th>\n",
       "      <td>0.714286</td>\n",
       "      <td>0.269058</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13134</th>\n",
       "      <td>0.921429</td>\n",
       "      <td>0.269058</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13135</th>\n",
       "      <td>0.735714</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>13136 rows × 19 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)  \\\n",
       "0                                               0.535714                       \n",
       "1                                               0.664286                       \n",
       "2                                               0.721429                       \n",
       "3                                               0.721429                       \n",
       "4                                               0.628571                       \n",
       "...                                                  ...                       \n",
       "13131                                           0.714286                       \n",
       "13132                                           0.714286                       \n",
       "13133                                           0.714286                       \n",
       "13134                                           0.921429                       \n",
       "13135                                           0.735714                       \n",
       "\n",
       "       When child put to breast  Age in 5-year groups_20-24  \\\n",
       "0                      0.470852                           0   \n",
       "1                      0.230203                           0   \n",
       "2                      0.000000                           0   \n",
       "3                      0.230203                           0   \n",
       "4                      0.000000                           1   \n",
       "...                         ...                         ...   \n",
       "13131                  0.000000                           0   \n",
       "13132                  0.230203                           0   \n",
       "13133                  0.269058                           0   \n",
       "13134                  0.269058                           0   \n",
       "13135                  0.000000                           1   \n",
       "\n",
       "       Age in 5-year groups_25-29  Age in 5-year groups_30-34  \\\n",
       "0                               1                           0   \n",
       "1                               0                           1   \n",
       "2                               0                           0   \n",
       "3                               0                           0   \n",
       "4                               0                           0   \n",
       "...                           ...                         ...   \n",
       "13131                           0                           0   \n",
       "13132                           0                           0   \n",
       "13133                           1                           0   \n",
       "13134                           1                           0   \n",
       "13135                           0                           0   \n",
       "\n",
       "       Age in 5-year groups_35-39  Age in 5-year groups_40-44  \\\n",
       "0                               0                           0   \n",
       "1                               0                           0   \n",
       "2                               1                           0   \n",
       "3                               1                           0   \n",
       "4                               0                           0   \n",
       "...                           ...                         ...   \n",
       "13131                           1                           0   \n",
       "13132                           1                           0   \n",
       "13133                           0                           0   \n",
       "13134                           0                           0   \n",
       "13135                           0                           0   \n",
       "\n",
       "       Age in 5-year groups_45-49  Type of place of residence_Urban  \\\n",
       "0                               0                                 1   \n",
       "1                               0                                 1   \n",
       "2                               0                                 1   \n",
       "3                               0                                 1   \n",
       "4                               0                                 1   \n",
       "...                           ...                               ...   \n",
       "13131                           0                                 0   \n",
       "13132                           0                                 0   \n",
       "13133                           0                                 0   \n",
       "13134                           0                                 0   \n",
       "13135                           0                                 0   \n",
       "\n",
       "       Wealth index combined_Poorer  Wealth index combined_Poorest  \\\n",
       "0                                 0                              0   \n",
       "1                                 0                              0   \n",
       "2                                 0                              0   \n",
       "3                                 0                              0   \n",
       "4                                 0                              0   \n",
       "...                             ...                            ...   \n",
       "13131                             0                              0   \n",
       "13132                             0                              0   \n",
       "13133                             0                              0   \n",
       "13134                             0                              0   \n",
       "13135                             0                              0   \n",
       "\n",
       "       Wealth index combined_Richer  Wealth index combined_Richest  \\\n",
       "0                                 0                              1   \n",
       "1                                 0                              1   \n",
       "2                                 0                              1   \n",
       "3                                 0                              1   \n",
       "4                                 0                              1   \n",
       "...                             ...                            ...   \n",
       "13131                             1                              0   \n",
       "13132                             1                              0   \n",
       "13133                             1                              0   \n",
       "13134                             1                              0   \n",
       "13135                             1                              0   \n",
       "\n",
       "       Have mosquito bed net for sleeping (from household questionnaire)_Yes  \\\n",
       "0                                                      1                       \n",
       "1                                                      1                       \n",
       "2                                                      1                       \n",
       "3                                                      1                       \n",
       "4                                                      1                       \n",
       "...                                                  ...                       \n",
       "13131                                                  1                       \n",
       "13132                                                  1                       \n",
       "13133                                                  1                       \n",
       "13134                                                  1                       \n",
       "13135                                                  1                       \n",
       "\n",
       "       Smokes cigarettes_Yes  Had fever in last two weeks_No  \\\n",
       "0                          0                               1   \n",
       "1                          0                               1   \n",
       "2                          0                               1   \n",
       "3                          0                               1   \n",
       "4                          0                               1   \n",
       "...                      ...                             ...   \n",
       "13131                      0                               1   \n",
       "13132                      0                               1   \n",
       "13133                      0                               1   \n",
       "13134                      0                               1   \n",
       "13135                      0                               1   \n",
       "\n",
       "       Had fever in last two weeks_Yes  \\\n",
       "0                                    0   \n",
       "1                                    0   \n",
       "2                                    0   \n",
       "3                                    0   \n",
       "4                                    0   \n",
       "...                                ...   \n",
       "13131                                0   \n",
       "13132                                0   \n",
       "13133                                0   \n",
       "13134                                0   \n",
       "13135                                0   \n",
       "\n",
       "       Taking iron pills, sprinkles or syrup_No  \\\n",
       "0                                             1   \n",
       "1                                             1   \n",
       "2                                             0   \n",
       "3                                             1   \n",
       "4                                             0   \n",
       "...                                         ...   \n",
       "13131                                         0   \n",
       "13132                                         0   \n",
       "13133                                         1   \n",
       "13134                                         1   \n",
       "13135                                         0   \n",
       "\n",
       "       Taking iron pills, sprinkles or syrup_Yes  \n",
       "0                                              0  \n",
       "1                                              0  \n",
       "2                                              1  \n",
       "3                                              0  \n",
       "4                                              1  \n",
       "...                                          ...  \n",
       "13131                                          1  \n",
       "13132                                          1  \n",
       "13133                                          0  \n",
       "13134                                          0  \n",
       "13135                                          1  \n",
       "\n",
       "[13136 rows x 19 columns]"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X[['Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)', 'When child put to breast']]= min_max_scaler.transform(X[['Hemoglobin level adjusted for altitude and smoking (g/dl - 1 decimal)', 'When child put to breast']])\n",
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-8 {color: black;}#sk-container-id-8 pre{padding: 0;}#sk-container-id-8 div.sk-toggleable {background-color: white;}#sk-container-id-8 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-8 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-8 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-8 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-8 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-8 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-8 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-8 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-8 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-8 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-8 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-8 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-8 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-8 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-8 div.sk-item {position: relative;z-index: 1;}#sk-container-id-8 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-8 div.sk-item::before, #sk-container-id-8 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-8 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-8 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-8 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-8 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-8 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-8 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-8 div.sk-label-container {text-align: center;}#sk-container-id-8 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-8 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-8\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier(max_depth=6, min_samples_split=5, n_estimators=200)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-12\" type=\"checkbox\" checked><label for=\"sk-estimator-id-12\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier(max_depth=6, min_samples_split=5, n_estimators=200)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "RandomForestClassifier(max_depth=6, min_samples_split=5, n_estimators=200)"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Se entrena el modelo con el 100% de los datos\n",
    "modelRF_Hiper.fit(X, Y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [],
   "source": [
    "filename = 'data/modelo-hiperparametrizado.pkl'\n",
    "variables= X.columns._values\n",
    "pickle.dump([modelRF_Hiper,labelencoder,variables,min_max_scaler], open(filename, 'wb')) #write"
   ]
  }
 ],
 "metadata": {
  "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": "3.10.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}