estimacion_general.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "74c14f41",
   "metadata": {},
   "source": [
    "# Estimaciones en una encuesta\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "1446e56b",
   "metadata": {},
   "outputs": [],
   "source": [
    "# ---------- # Importación de bibliotecas # ------------------ #\n",
    "import os\n",
    "import sys\n",
    "import pandas as pd\n",
    "\n",
    "# ---------- # Importación de funciones # ------------------ #\n",
    "from modulos.func_analisis import *\n",
    "from modulos.func_transformacion import *"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0e40ec83",
   "metadata": {},
   "source": [
    "Dentro del script `func_analisis` se encuentran las funciones `proporciones`, `proporciones_des`, `prevalencias`, `prevalencias_des` y `tabulados_prevalencias`. Todas estas funciones se pueden utilizar para generar estimaciones a partir de los datos de cualquier encuesta con un muestreo probabilístico estratificado. \n",
    "\n",
    "A grandes razgos las funciones requieren como argumentos el nombre de las varibles donde se almacena la información del ponderador o factor de expansión, la unidad primaria de muestreo, el estrato, las preguntas que se desean analizar y el dataframe donde están dichas variables. \n",
    "\n",
    "Para usarlas, sólo es necesario definir correctamente sus argumentos. Los pasos que se recomienda seguir son:\n",
    "1. Identificar las variables de interés en la base de datos asociada a la encuesta.\n",
    "2. Homologar el tipo de datos de las variables de interés.\n",
    "3. Estructurar un dataframe con las variables de interés.\n",
    "4. Generar la estimación a partir de las respuestas a las preguntas seleccionadas.\n",
    "\n",
    "A continuación se ejemplifica cómo se pueden generar estimaciones de alguna pregunta de interés con los datos de la Encuesta Nacional de Consumo de Drogas, Alcohol y Tabaco, ENCODAT 2016-2017."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "53616342",
   "metadata": {},
   "outputs": [],
   "source": [
    "# ------------------ # Carga de las bases de datos # ------------------ #\n",
    "h=pd.read_csv(os.path.join('datos','originales','ENCODAT_2016_2017_Hogar','ENCODAT_2016_2017_Hogar.csv'), sep=';', low_memory=False)\n",
    "bb=pd.read_csv(os.path.join('datos','originales','ENCODAT_2016_2017_Individual','ENCODAT_2016_2017_Individual.csv'), sep=';', low_memory=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8f846b1a",
   "metadata": {},
   "source": [
    "## 1. Identificación de variables\n",
    "En los argumentos de las funciones para hacer estimaciones, es necesario indicar el nombre de las variables que almacenan el factor de expansión, la unidad primaria de muestreo, el estrato y las preguntas de interés. Por ello, el primer paso es identificar si se tienen dichas variables y cuál es su nombre o clave.\n",
    "\n",
    "En el caso de la ENCODAT:\n",
    "- el factor de expansión está dentro de las variables `ponde_ss` y `ponde_hh`\n",
    "- la unidad primaria de muestreo es la variable `code_upm`\n",
    "- el estrato está en la variable `estrato`\n",
    "\n",
    "Las preguntas de interés dependerán de la información que se desee estimar. \n",
    "\n",
    "Para este ejemplo, se eligieron dos preguntas:\n",
    "_____\n",
    "`ds8` **¿Actualmente estudia?**\n",
    "1. No, nunca ha asistido a la escuela\n",
    "2. No, pero si fue a la escuela\n",
    "3. Sí\n",
    "____\n",
    " \n",
    "`ds9` **¿Cuál fue el último grado que ha completado o completó en la escuela?**\n",
    "1. Primaria incompleta (1 a 5 años)\n",
    "2. Primaria completa (6 años)\n",
    "3. Secundaria incompleta (1 a 2 años)\n",
    "4. Secundaria completa o equivalente (3 años)\n",
    "5. Bachillerato incompleto (1 a 2 años)\n",
    "6. Bachillerato completo o equivalente (aprox. 3 años)\n",
    "7. Estudios Universitarios incompletos (1 a 3 años)\n",
    "8. Estudios  Universitarios completos (4 a 5 años)\n",
    "9. Estudios de Posgrado (2 a 4 años)\n",
    "99) No contesta"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "0910530c",
   "metadata": {},
   "outputs": [],
   "source": [
    "# ---------- # Selección de preguntas # ------------------ #\n",
    "\n",
    "#escribir aqui los códigos de las preguntas de interés\n",
    "clv_preg = ['ds8','ds9']"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8d4770f0",
   "metadata": {},
   "source": [
    "## 2. Homologación de datos\n",
    "\n",
    "Las variables que requieren las funciones de `func_analisis` deben ser datos de tipo numérico, por ello para empezar a hacer estimaciones es necesario hacer una pequeña exploración a las bases de datos y en caso de ser necesario cambiar los datos, codificarlos o corregirlos.\n",
    "\n",
    "Siguiendo con el ejemplo de la ENCODAT, en la siguientes celdas se hace una pequeña exploración a las bases de datos y se homologan los datos a formato numérico.\n",
    "\n",
    "### 2.1 Preparativos de las variables asociadas a la muestra"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "c0a71b05",
   "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>estrato</th>\n",
       "      <th>code_upm</th>\n",
       "      <th>ponde_hh</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>01_12</td>\n",
       "      <td>170,475477457288</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3</td>\n",
       "      <td>01_12</td>\n",
       "      <td>170,475477457288</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>01_12</td>\n",
       "      <td>170,475477457288</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>01_12</td>\n",
       "      <td>170,475477457288</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3</td>\n",
       "      <td>01_12</td>\n",
       "      <td>170,475477457288</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   estrato code_upm          ponde_hh\n",
       "0        3    01_12  170,475477457288\n",
       "1        3    01_12  170,475477457288\n",
       "2        3    01_12  170,475477457288\n",
       "3        3    01_12  170,475477457288\n",
       "4        3    01_12  170,475477457288"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "h[['estrato','code_upm','ponde_hh']].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "11624b7d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "estrato      int64\n",
       "code_upm    object\n",
       "ponde_hh    object\n",
       "dtype: object"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "h[['estrato','code_upm','ponde_hh']].dtypes"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c00e9ae1",
   "metadata": {},
   "source": [
    "Con las dos celdas anteriores se puede ver que la variable estrato ya tiene formato numérico, así que no vamos a hacerle ningún procesamiento. Sin embargo, las variables `code_upm` y `ponde_hh` sí necesitan homologarse a formato numérico, además la variable `ponde_hh` tiene más información que sólo el ponderador.\n",
    "\n",
    "En la siguiente celda se hacen las adecuaciones correspondientes para solucionar los problemas anteriores:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "4bf8f92e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Homologación de codigos de las unidades primarias de muestreo para que sean sólo numéricos\n",
    "h.insert(0,'upm',h['code_upm'].str.replace('_','').astype(int))\n",
    "\n",
    "# Ahora bien, en el caso muy específico de esta base de datos,\n",
    "#el factor de expansión son los primeros dígitos separados por la coma en la variable 'ponde_hh'\n",
    "#así que se genera una nueva variable sólo con el ponderador en formato numérico\n",
    "h.insert(0,'factor_exp',h['ponde_hh'].str.partition(',')[0].astype(int))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e589fe54",
   "metadata": {},
   "source": [
    "De igual forma, en la base 'bb', la variable \"ponde_ss\" tiene más información que sólo el ponderador, así que se corrige:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "8782e5b6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    263,004588042305\n",
       "1    779,543148763914\n",
       "2    263,004588042305\n",
       "3     281,00343231265\n",
       "4    421,505148468975\n",
       "Name: ponde_ss, dtype: object"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bb['ponde_ss'].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "84d69f48",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Se genera una nueva variable sólo con el ponderador en formato numérico\n",
    "bb.insert(0,'factor_exp',bb['ponde_ss'].str.partition(',')[0].astype(int))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "22ee1879",
   "metadata": {},
   "source": [
    "### 2.2 Preparativos de las variables asociadas a las preguntas\n",
    "En el caso de la ENCODAT las respuestas a preguntas se codifican mediante claves, sin embargo no siempre están homologadas para que efectivamente sean sólo datos numéricos. En la siguiente celda podemos ver como una de las preguntas seleccionadas (`ds9`) tiene datos de distintos tipos, no sólo numéricos."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "ccccff16",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ds8     int64\n",
       "ds9    object\n",
       "dtype: object"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# ---------- # Revisión del tipo de respuestas de las preguntas seleccionadas # ------------------ #\n",
    "bb[clv_preg].dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "628c3378",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['4', '6', '5', '1', '3', '2', '7', '9', '8', ' ', '99'],\n",
       "      dtype=object)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bb.ds9.unique()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2a19889c",
   "metadata": {},
   "source": [
    "En una inspección más detallada (en la celda anterior) podemos ver que hay dos problemas con el tipo de datos almacenados en la variable `ds9`:\n",
    "- el primero es que hay espacios vacíos\n",
    "- el segundo es que todas las claves son cadenas de caracteres.\n",
    "\n",
    "Para solucionar ambos problemas se hace lo siguiente:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "3320b5ce",
   "metadata": {},
   "outputs": [],
   "source": [
    "# ---------- # Homologación de los datos de las preguntas seleccionadas # ------------------ #\n",
    "#pregunta con problemas\n",
    "clave_pregunta = 'ds9'\n",
    "\n",
    "#para solucionar el primer problema es necesario asignar una clave numérica a los datos vacíos\n",
    "#en este caso se elige asignar el 0 para los espacios vacíos\n",
    "bb[clave_pregunta]=bb[clave_pregunta].replace(' ',0)\n",
    "\n",
    "#para solucionar el segundo problema se cambia el tipo de dato, de cadena de caracteres a numérico\n",
    "bb[clave_pregunta]=bb[clave_pregunta].astype(int)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "267c7e50",
   "metadata": {},
   "source": [
    "NOTA: la homologación y estructuración de una base de datos es de las partes más complejas del análisis de datos porque los datos pueden tener infinidad de variaciones o problemas, cada uno con su solución particular.\n",
    "\n",
    "Sin embargo, una forma general de abordar esto es inspeccionar las respuestas y homologar la forma en la que se escriben dichas respuestas. "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5c1573d5",
   "metadata": {},
   "source": [
    "## 3. Estructuración del dataframe\n",
    "\n",
    "La información de la ENCODAT está distribuida en dos bases de datos (nombradas en este cuaderno como `bb` y `h`), por ello en este caso la estructuración del dataframe requiere unir dichas bases. \n",
    "\n",
    "Ahora bien, cada base puede necesitar sus adecuaciones particulares para estructurar el Dataframe que requieren las funciones del script`func_analisis`.\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "b5e4eef7",
   "metadata": {},
   "outputs": [],
   "source": [
    "# ---------- # Creación de dataframe para funciones # ------------------ #\n",
    "\n",
    "# Creación de variable 'id_hogar' para unir la base \"bb\" con la base \"h\"\n",
    "bb.insert(0,'id_hogar',bb['id_pers'].str[:20])\n",
    "\n",
    "# Unión de las bases en un solo dataframe mediante el id_hogar\n",
    "b=bb.merge(h[['id_hogar','estrato','upm','code_upm','est_var']],on='id_hogar',how='left')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3a0df558",
   "metadata": {},
   "source": [
    "## 4. Estimación\n",
    "\n",
    "### 4.1 ¿Con qué proporción se mencionó cada respuesta de la pregunta seleccionada?\n",
    "Para saber con que proporción se mencionó cada respuesta de las preguntas seleccionadas se puede utilizar la función `proporciones`. Para utilizarla, basta llamar a la función y dar los siguientes argumentos:\n",
    "- `b` dataframe con la base de datos.\n",
    "- `clave_preg` cadena de caracteres con el nombre de la variable en la que están las respuestas de la pregunta para la que se desea estimar las proporciones.\n",
    "- `alp` valor entre 0 y 1 para definir el nivel de significancia del intervalo (el valor predeterminado es 0.95).\n",
    "- `ponderador` cadena de caracteres con el nombre de la variable donde está el factor de expansión de cada registro en la base de datos (el valor predeterminado es \"factor_exp\").\n",
    "- `estrato` cadena de caracteres con el nombre de la variable donde están la información de los estratos de la encuesta (el valor predeterminado es \"estrato\").\n",
    "- `upm` cadena de caracteres con el nombre de la variable donde está la información de las unidades primarias de la encuesta (el valor predeterminado es \"upm\").\n",
    "\n",
    "Al ejecutar la celda, la función genera estimaciones puntuales, su respectivo intervalo de confianza, el coeficiente de variación y el error estándar:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "d233668d",
   "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>clave_respuesta</th>\n",
       "      <th>estimacion</th>\n",
       "      <th>ic_inf</th>\n",
       "      <th>ic_sup</th>\n",
       "      <th>poblacion</th>\n",
       "      <th>error_std</th>\n",
       "      <th>cv</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>2.235656</td>\n",
       "      <td>1.998388</td>\n",
       "      <td>2.472924</td>\n",
       "      <td>1905531</td>\n",
       "      <td>0.121057</td>\n",
       "      <td>5.414847</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>7.543581</td>\n",
       "      <td>7.150328</td>\n",
       "      <td>7.936835</td>\n",
       "      <td>6429670</td>\n",
       "      <td>0.200643</td>\n",
       "      <td>2.659790</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>15.188253</td>\n",
       "      <td>14.563453</td>\n",
       "      <td>15.813053</td>\n",
       "      <td>12945503</td>\n",
       "      <td>0.318781</td>\n",
       "      <td>2.098869</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>10.088452</td>\n",
       "      <td>9.668178</td>\n",
       "      <td>10.508726</td>\n",
       "      <td>8598756</td>\n",
       "      <td>0.214429</td>\n",
       "      <td>2.125493</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>25.132433</td>\n",
       "      <td>24.390835</td>\n",
       "      <td>25.874031</td>\n",
       "      <td>21421291</td>\n",
       "      <td>0.378373</td>\n",
       "      <td>1.505518</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>5</td>\n",
       "      <td>8.865000</td>\n",
       "      <td>8.431773</td>\n",
       "      <td>9.298226</td>\n",
       "      <td>7555963</td>\n",
       "      <td>0.221038</td>\n",
       "      <td>2.493378</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>6</td>\n",
       "      <td>16.721276</td>\n",
       "      <td>15.973866</td>\n",
       "      <td>17.468685</td>\n",
       "      <td>14252154</td>\n",
       "      <td>0.381339</td>\n",
       "      <td>2.280559</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>7</td>\n",
       "      <td>5.092753</td>\n",
       "      <td>4.575115</td>\n",
       "      <td>5.610390</td>\n",
       "      <td>4340739</td>\n",
       "      <td>0.264106</td>\n",
       "      <td>5.185910</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>8</td>\n",
       "      <td>8.088889</td>\n",
       "      <td>7.508010</td>\n",
       "      <td>8.669769</td>\n",
       "      <td>6894456</td>\n",
       "      <td>0.296373</td>\n",
       "      <td>3.663948</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>9</td>\n",
       "      <td>0.884170</td>\n",
       "      <td>0.742965</td>\n",
       "      <td>1.025374</td>\n",
       "      <td>753610</td>\n",
       "      <td>0.072045</td>\n",
       "      <td>8.148282</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>99</td>\n",
       "      <td>0.159538</td>\n",
       "      <td>0.109230</td>\n",
       "      <td>0.209846</td>\n",
       "      <td>135980</td>\n",
       "      <td>0.025668</td>\n",
       "      <td>16.088959</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    clave_respuesta  estimacion     ic_inf     ic_sup  poblacion  error_std  \\\n",
       "0                 0    2.235656   1.998388   2.472924    1905531   0.121057   \n",
       "1                 1    7.543581   7.150328   7.936835    6429670   0.200643   \n",
       "2                 2   15.188253  14.563453  15.813053   12945503   0.318781   \n",
       "3                 3   10.088452   9.668178  10.508726    8598756   0.214429   \n",
       "4                 4   25.132433  24.390835  25.874031   21421291   0.378373   \n",
       "5                 5    8.865000   8.431773   9.298226    7555963   0.221038   \n",
       "6                 6   16.721276  15.973866  17.468685   14252154   0.381339   \n",
       "7                 7    5.092753   4.575115   5.610390    4340739   0.264106   \n",
       "8                 8    8.088889   7.508010   8.669769    6894456   0.296373   \n",
       "9                 9    0.884170   0.742965   1.025374     753610   0.072045   \n",
       "10               99    0.159538   0.109230   0.209846     135980   0.025668   \n",
       "\n",
       "           cv  \n",
       "0    5.414847  \n",
       "1    2.659790  \n",
       "2    2.098869  \n",
       "3    2.125493  \n",
       "4    1.505518  \n",
       "5    2.493378  \n",
       "6    2.280559  \n",
       "7    5.185910  \n",
       "8    3.663948  \n",
       "9    8.148282  \n",
       "10  16.088959  "
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "proporciones(b = b, \n",
    "             clave_preg = 'ds9', \n",
    "             alp = 0.95, \n",
    "             ponderador = 'factor_exp', \n",
    "             estrato= 'estrato', \n",
    "             upm = 'upm')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "09f0bd23",
   "metadata": {},
   "source": [
    "La columna `estimación` del dataframe que genera la función `proporciones` describe con que proporción la población (estimada por la encuesta) eligió las respuestas.\n",
    "\n",
    "Por ejemplo, en la ENCODAT se estima que el 15.18% de la población tiene la primaria completa (respuesta que corresponde a la clave 2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "20392fc6",
   "metadata": {},
   "source": [
    "### 4.2 ¿Con qué proporción se mencionó cada respuesta de la pregunta seleccionada? \n",
    "### Desagregado por otra variable\n",
    "\n",
    "Si se desea saber con qué proporción se mencionó cada respuesta en subconjuntos definidos por otra pregunta, se puede utilizar la función `proporciones_des`.\n",
    "\n",
    "La función utiliza los mismos argumentos que `proporciones` e incluye uno más: \n",
    "`var_des` lista con el(los) nombre(s) de la(s) variable(s) con respecto a la cual se quieren crear los subconjuntos.\n",
    "\n",
    "Para mostrar concretamente lo que hace la función, aplicaremos la función `proporciones_des` para la pregunta `ds9` (nivel de escolaridad) y desagregaremos las respuestas de acuerdo con la pregunta `ds8` (actualmente estudia), es decir, podremos saber la proporción de las personas que estudian actualmente con base en su escolaridad:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "b137e5b2",
   "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>ds8</th>\n",
       "      <th>estimacion</th>\n",
       "      <th>clave_respuesta</th>\n",
       "      <th>ic_inf</th>\n",
       "      <th>ic_sup</th>\n",
       "      <th>poblacion</th>\n",
       "      <th>error_std</th>\n",
       "      <th>cv</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>1</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>0</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>1905531</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>2</td>\n",
       "      <td>0.189053</td>\n",
       "      <td>99</td>\n",
       "      <td>0.125219</td>\n",
       "      <td>0.252888</td>\n",
       "      <td>121116</td>\n",
       "      <td>0.032569</td>\n",
       "      <td>17.227454</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>2</td>\n",
       "      <td>0.847453</td>\n",
       "      <td>9</td>\n",
       "      <td>0.697067</td>\n",
       "      <td>0.997839</td>\n",
       "      <td>542916</td>\n",
       "      <td>0.076729</td>\n",
       "      <td>9.054086</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>2</td>\n",
       "      <td>9.649621</td>\n",
       "      <td>8</td>\n",
       "      <td>8.947750</td>\n",
       "      <td>10.351492</td>\n",
       "      <td>6181975</td>\n",
       "      <td>0.358104</td>\n",
       "      <td>3.711067</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2</td>\n",
       "      <td>3.029559</td>\n",
       "      <td>7</td>\n",
       "      <td>2.680650</td>\n",
       "      <td>3.378469</td>\n",
       "      <td>1940870</td>\n",
       "      <td>0.178018</td>\n",
       "      <td>5.876052</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2</td>\n",
       "      <td>9.071511</td>\n",
       "      <td>1</td>\n",
       "      <td>8.579950</td>\n",
       "      <td>9.563072</td>\n",
       "      <td>5811612</td>\n",
       "      <td>0.250801</td>\n",
       "      <td>2.764709</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2</td>\n",
       "      <td>6.528307</td>\n",
       "      <td>5</td>\n",
       "      <td>6.091566</td>\n",
       "      <td>6.965049</td>\n",
       "      <td>4182323</td>\n",
       "      <td>0.222831</td>\n",
       "      <td>3.413312</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2</td>\n",
       "      <td>29.471576</td>\n",
       "      <td>4</td>\n",
       "      <td>28.597480</td>\n",
       "      <td>30.345672</td>\n",
       "      <td>18880798</td>\n",
       "      <td>0.445976</td>\n",
       "      <td>1.513239</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>6.347032</td>\n",
       "      <td>3</td>\n",
       "      <td>5.953384</td>\n",
       "      <td>6.740680</td>\n",
       "      <td>4066190</td>\n",
       "      <td>0.200844</td>\n",
       "      <td>3.164382</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>16.656890</td>\n",
       "      <td>2</td>\n",
       "      <td>15.909295</td>\n",
       "      <td>17.404485</td>\n",
       "      <td>10671142</td>\n",
       "      <td>0.381433</td>\n",
       "      <td>2.289942</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2</td>\n",
       "      <td>18.208996</td>\n",
       "      <td>6</td>\n",
       "      <td>17.380667</td>\n",
       "      <td>19.037325</td>\n",
       "      <td>11665490</td>\n",
       "      <td>0.422625</td>\n",
       "      <td>2.320966</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>3</td>\n",
       "      <td>0.077161</td>\n",
       "      <td>99</td>\n",
       "      <td>0.008292</td>\n",
       "      <td>0.146030</td>\n",
       "      <td>14864</td>\n",
       "      <td>0.035138</td>\n",
       "      <td>45.538564</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>3</td>\n",
       "      <td>11.806466</td>\n",
       "      <td>2</td>\n",
       "      <td>10.857523</td>\n",
       "      <td>12.755409</td>\n",
       "      <td>2274361</td>\n",
       "      <td>0.484163</td>\n",
       "      <td>4.100832</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>3</td>\n",
       "      <td>23.529064</td>\n",
       "      <td>3</td>\n",
       "      <td>22.198407</td>\n",
       "      <td>24.859722</td>\n",
       "      <td>4532566</td>\n",
       "      <td>0.678919</td>\n",
       "      <td>2.885449</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>3</td>\n",
       "      <td>13.187987</td>\n",
       "      <td>4</td>\n",
       "      <td>12.219551</td>\n",
       "      <td>14.156424</td>\n",
       "      <td>2540493</td>\n",
       "      <td>0.494109</td>\n",
       "      <td>3.746661</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>3</td>\n",
       "      <td>17.512948</td>\n",
       "      <td>5</td>\n",
       "      <td>16.269652</td>\n",
       "      <td>18.756243</td>\n",
       "      <td>3373640</td>\n",
       "      <td>0.634346</td>\n",
       "      <td>3.622155</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>3</td>\n",
       "      <td>13.427666</td>\n",
       "      <td>6</td>\n",
       "      <td>11.910553</td>\n",
       "      <td>14.944779</td>\n",
       "      <td>2586664</td>\n",
       "      <td>0.774051</td>\n",
       "      <td>5.764601</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>3</td>\n",
       "      <td>12.457992</td>\n",
       "      <td>7</td>\n",
       "      <td>10.698441</td>\n",
       "      <td>14.217543</td>\n",
       "      <td>2399869</td>\n",
       "      <td>0.897747</td>\n",
       "      <td>7.206190</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>3</td>\n",
       "      <td>3.698570</td>\n",
       "      <td>8</td>\n",
       "      <td>2.954423</td>\n",
       "      <td>4.442717</td>\n",
       "      <td>712481</td>\n",
       "      <td>0.379674</td>\n",
       "      <td>10.265420</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>3</td>\n",
       "      <td>1.093736</td>\n",
       "      <td>9</td>\n",
       "      <td>0.743792</td>\n",
       "      <td>1.443680</td>\n",
       "      <td>210694</td>\n",
       "      <td>0.178546</td>\n",
       "      <td>16.324422</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>3</td>\n",
       "      <td>3.208409</td>\n",
       "      <td>1</td>\n",
       "      <td>2.659650</td>\n",
       "      <td>3.757169</td>\n",
       "      <td>618058</td>\n",
       "      <td>0.279984</td>\n",
       "      <td>8.726582</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    ds8  estimacion  clave_respuesta      ic_inf      ic_sup  poblacion  \\\n",
       "20    1  100.000000                0  100.000000  100.000000    1905531   \n",
       "9     2    0.189053               99    0.125219    0.252888     121116   \n",
       "8     2    0.847453                9    0.697067    0.997839     542916   \n",
       "7     2    9.649621                8    8.947750   10.351492    6181975   \n",
       "6     2    3.029559                7    2.680650    3.378469    1940870   \n",
       "0     2    9.071511                1    8.579950    9.563072    5811612   \n",
       "4     2    6.528307                5    6.091566    6.965049    4182323   \n",
       "3     2   29.471576                4   28.597480   30.345672   18880798   \n",
       "2     2    6.347032                3    5.953384    6.740680    4066190   \n",
       "1     2   16.656890                2   15.909295   17.404485   10671142   \n",
       "5     2   18.208996                6   17.380667   19.037325   11665490   \n",
       "19    3    0.077161               99    0.008292    0.146030      14864   \n",
       "11    3   11.806466                2   10.857523   12.755409    2274361   \n",
       "12    3   23.529064                3   22.198407   24.859722    4532566   \n",
       "13    3   13.187987                4   12.219551   14.156424    2540493   \n",
       "14    3   17.512948                5   16.269652   18.756243    3373640   \n",
       "15    3   13.427666                6   11.910553   14.944779    2586664   \n",
       "16    3   12.457992                7   10.698441   14.217543    2399869   \n",
       "17    3    3.698570                8    2.954423    4.442717     712481   \n",
       "18    3    1.093736                9    0.743792    1.443680     210694   \n",
       "10    3    3.208409                1    2.659650    3.757169     618058   \n",
       "\n",
       "    error_std         cv  \n",
       "20   0.000000   0.000000  \n",
       "9    0.032569  17.227454  \n",
       "8    0.076729   9.054086  \n",
       "7    0.358104   3.711067  \n",
       "6    0.178018   5.876052  \n",
       "0    0.250801   2.764709  \n",
       "4    0.222831   3.413312  \n",
       "3    0.445976   1.513239  \n",
       "2    0.200844   3.164382  \n",
       "1    0.381433   2.289942  \n",
       "5    0.422625   2.320966  \n",
       "19   0.035138  45.538564  \n",
       "11   0.484163   4.100832  \n",
       "12   0.678919   2.885449  \n",
       "13   0.494109   3.746661  \n",
       "14   0.634346   3.622155  \n",
       "15   0.774051   5.764601  \n",
       "16   0.897747   7.206190  \n",
       "17   0.379674  10.265420  \n",
       "18   0.178546  16.324422  \n",
       "10   0.279984   8.726582  "
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "estudiantes_por_escolaridad=proporciones_des(b = b,\n",
    "                 clave_preg = 'ds9',\n",
    "                 var_des = ['ds8'],\n",
    "                 alp = 0.95,\n",
    "                 ponderador = 'factor_exp',\n",
    "                 estrato= 'estrato',\n",
    "                 upm = 'upm')\n",
    "\n",
    "estudiantes_por_escolaridad"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6c6c6a7a",
   "metadata": {},
   "source": [
    "Puede ser un poco complicado recordar a qué corresponde cada clave de respuesta, por ello, renombraremos las claves del anterior dataframe, para que sea más clara la estructura que regresa la función `proporciones_des`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "94fa9a3d",
   "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>ds8</th>\n",
       "      <th>estimacion</th>\n",
       "      <th>clave_respuesta</th>\n",
       "      <th>ic_inf</th>\n",
       "      <th>ic_sup</th>\n",
       "      <th>poblacion</th>\n",
       "      <th>error_std</th>\n",
       "      <th>cv</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>No, nunca ha asistido a la escuela</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>Nunca ha asistido a la escuela</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>1905531</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>No, pero si fue a la escuela</td>\n",
       "      <td>16.656890</td>\n",
       "      <td>Primaria completa</td>\n",
       "      <td>15.909295</td>\n",
       "      <td>17.404485</td>\n",
       "      <td>10671142</td>\n",
       "      <td>0.381433</td>\n",
       "      <td>2.289942</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>No, pero si fue a la escuela</td>\n",
       "      <td>6.347032</td>\n",
       "      <td>Secundaria incompleta</td>\n",
       "      <td>5.953384</td>\n",
       "      <td>6.740680</td>\n",
       "      <td>4066190</td>\n",
       "      <td>0.200844</td>\n",
       "      <td>3.164382</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>No, pero si fue a la escuela</td>\n",
       "      <td>29.471576</td>\n",
       "      <td>Secundaria completa</td>\n",
       "      <td>28.597480</td>\n",
       "      <td>30.345672</td>\n",
       "      <td>18880798</td>\n",
       "      <td>0.445976</td>\n",
       "      <td>1.513239</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>No, pero si fue a la escuela</td>\n",
       "      <td>6.528307</td>\n",
       "      <td>Bachillerato incompleto</td>\n",
       "      <td>6.091566</td>\n",
       "      <td>6.965049</td>\n",
       "      <td>4182323</td>\n",
       "      <td>0.222831</td>\n",
       "      <td>3.413312</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>No, pero si fue a la escuela</td>\n",
       "      <td>18.208996</td>\n",
       "      <td>Bachillerato completo</td>\n",
       "      <td>17.380667</td>\n",
       "      <td>19.037325</td>\n",
       "      <td>11665490</td>\n",
       "      <td>0.422625</td>\n",
       "      <td>2.320966</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>No, pero si fue a la escuela</td>\n",
       "      <td>3.029559</td>\n",
       "      <td>Estudios Universitarios incompletos</td>\n",
       "      <td>2.680650</td>\n",
       "      <td>3.378469</td>\n",
       "      <td>1940870</td>\n",
       "      <td>0.178018</td>\n",
       "      <td>5.876052</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>No, pero si fue a la escuela</td>\n",
       "      <td>9.649621</td>\n",
       "      <td>Estudios  Universitarios completos</td>\n",
       "      <td>8.947750</td>\n",
       "      <td>10.351492</td>\n",
       "      <td>6181975</td>\n",
       "      <td>0.358104</td>\n",
       "      <td>3.711067</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>No, pero si fue a la escuela</td>\n",
       "      <td>0.847453</td>\n",
       "      <td>Estudios de Posgrado</td>\n",
       "      <td>0.697067</td>\n",
       "      <td>0.997839</td>\n",
       "      <td>542916</td>\n",
       "      <td>0.076729</td>\n",
       "      <td>9.054086</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>No, pero si fue a la escuela</td>\n",
       "      <td>0.189053</td>\n",
       "      <td>No contesta</td>\n",
       "      <td>0.125219</td>\n",
       "      <td>0.252888</td>\n",
       "      <td>121116</td>\n",
       "      <td>0.032569</td>\n",
       "      <td>17.227454</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>No, pero si fue a la escuela</td>\n",
       "      <td>9.071511</td>\n",
       "      <td>Primaria incompleta</td>\n",
       "      <td>8.579950</td>\n",
       "      <td>9.563072</td>\n",
       "      <td>5811612</td>\n",
       "      <td>0.250801</td>\n",
       "      <td>2.764709</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>Sí, actualmente estudia</td>\n",
       "      <td>1.093736</td>\n",
       "      <td>Estudios de Posgrado</td>\n",
       "      <td>0.743792</td>\n",
       "      <td>1.443680</td>\n",
       "      <td>210694</td>\n",
       "      <td>0.178546</td>\n",
       "      <td>16.324422</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>Sí, actualmente estudia</td>\n",
       "      <td>0.077161</td>\n",
       "      <td>No contesta</td>\n",
       "      <td>0.008292</td>\n",
       "      <td>0.146030</td>\n",
       "      <td>14864</td>\n",
       "      <td>0.035138</td>\n",
       "      <td>45.538564</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Sí, actualmente estudia</td>\n",
       "      <td>11.806466</td>\n",
       "      <td>Primaria completa</td>\n",
       "      <td>10.857523</td>\n",
       "      <td>12.755409</td>\n",
       "      <td>2274361</td>\n",
       "      <td>0.484163</td>\n",
       "      <td>4.100832</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Sí, actualmente estudia</td>\n",
       "      <td>23.529064</td>\n",
       "      <td>Secundaria incompleta</td>\n",
       "      <td>22.198407</td>\n",
       "      <td>24.859722</td>\n",
       "      <td>4532566</td>\n",
       "      <td>0.678919</td>\n",
       "      <td>2.885449</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Sí, actualmente estudia</td>\n",
       "      <td>13.187987</td>\n",
       "      <td>Secundaria completa</td>\n",
       "      <td>12.219551</td>\n",
       "      <td>14.156424</td>\n",
       "      <td>2540493</td>\n",
       "      <td>0.494109</td>\n",
       "      <td>3.746661</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>Sí, actualmente estudia</td>\n",
       "      <td>17.512948</td>\n",
       "      <td>Bachillerato incompleto</td>\n",
       "      <td>16.269652</td>\n",
       "      <td>18.756243</td>\n",
       "      <td>3373640</td>\n",
       "      <td>0.634346</td>\n",
       "      <td>3.622155</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>Sí, actualmente estudia</td>\n",
       "      <td>13.427666</td>\n",
       "      <td>Bachillerato completo</td>\n",
       "      <td>11.910553</td>\n",
       "      <td>14.944779</td>\n",
       "      <td>2586664</td>\n",
       "      <td>0.774051</td>\n",
       "      <td>5.764601</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>Sí, actualmente estudia</td>\n",
       "      <td>12.457992</td>\n",
       "      <td>Estudios Universitarios incompletos</td>\n",
       "      <td>10.698441</td>\n",
       "      <td>14.217543</td>\n",
       "      <td>2399869</td>\n",
       "      <td>0.897747</td>\n",
       "      <td>7.206190</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>Sí, actualmente estudia</td>\n",
       "      <td>3.698570</td>\n",
       "      <td>Estudios  Universitarios completos</td>\n",
       "      <td>2.954423</td>\n",
       "      <td>4.442717</td>\n",
       "      <td>712481</td>\n",
       "      <td>0.379674</td>\n",
       "      <td>10.265420</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Sí, actualmente estudia</td>\n",
       "      <td>3.208409</td>\n",
       "      <td>Primaria incompleta</td>\n",
       "      <td>2.659650</td>\n",
       "      <td>3.757169</td>\n",
       "      <td>618058</td>\n",
       "      <td>0.279984</td>\n",
       "      <td>8.726582</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                   ds8  estimacion  \\\n",
       "20  No, nunca ha asistido a la escuela  100.000000   \n",
       "1         No, pero si fue a la escuela   16.656890   \n",
       "2         No, pero si fue a la escuela    6.347032   \n",
       "3         No, pero si fue a la escuela   29.471576   \n",
       "4         No, pero si fue a la escuela    6.528307   \n",
       "5         No, pero si fue a la escuela   18.208996   \n",
       "6         No, pero si fue a la escuela    3.029559   \n",
       "7         No, pero si fue a la escuela    9.649621   \n",
       "8         No, pero si fue a la escuela    0.847453   \n",
       "9         No, pero si fue a la escuela    0.189053   \n",
       "0         No, pero si fue a la escuela    9.071511   \n",
       "18             Sí, actualmente estudia    1.093736   \n",
       "19             Sí, actualmente estudia    0.077161   \n",
       "11             Sí, actualmente estudia   11.806466   \n",
       "12             Sí, actualmente estudia   23.529064   \n",
       "13             Sí, actualmente estudia   13.187987   \n",
       "14             Sí, actualmente estudia   17.512948   \n",
       "15             Sí, actualmente estudia   13.427666   \n",
       "16             Sí, actualmente estudia   12.457992   \n",
       "17             Sí, actualmente estudia    3.698570   \n",
       "10             Sí, actualmente estudia    3.208409   \n",
       "\n",
       "                        clave_respuesta      ic_inf      ic_sup  poblacion  \\\n",
       "20       Nunca ha asistido a la escuela  100.000000  100.000000    1905531   \n",
       "1                     Primaria completa   15.909295   17.404485   10671142   \n",
       "2                 Secundaria incompleta    5.953384    6.740680    4066190   \n",
       "3                   Secundaria completa   28.597480   30.345672   18880798   \n",
       "4               Bachillerato incompleto    6.091566    6.965049    4182323   \n",
       "5                 Bachillerato completo   17.380667   19.037325   11665490   \n",
       "6   Estudios Universitarios incompletos    2.680650    3.378469    1940870   \n",
       "7    Estudios  Universitarios completos    8.947750   10.351492    6181975   \n",
       "8                  Estudios de Posgrado    0.697067    0.997839     542916   \n",
       "9                           No contesta    0.125219    0.252888     121116   \n",
       "0                   Primaria incompleta    8.579950    9.563072    5811612   \n",
       "18                 Estudios de Posgrado    0.743792    1.443680     210694   \n",
       "19                          No contesta    0.008292    0.146030      14864   \n",
       "11                    Primaria completa   10.857523   12.755409    2274361   \n",
       "12                Secundaria incompleta   22.198407   24.859722    4532566   \n",
       "13                  Secundaria completa   12.219551   14.156424    2540493   \n",
       "14              Bachillerato incompleto   16.269652   18.756243    3373640   \n",
       "15                Bachillerato completo   11.910553   14.944779    2586664   \n",
       "16  Estudios Universitarios incompletos   10.698441   14.217543    2399869   \n",
       "17   Estudios  Universitarios completos    2.954423    4.442717     712481   \n",
       "10                  Primaria incompleta    2.659650    3.757169     618058   \n",
       "\n",
       "    error_std         cv  \n",
       "20   0.000000   0.000000  \n",
       "1    0.381433   2.289942  \n",
       "2    0.200844   3.164382  \n",
       "3    0.445976   1.513239  \n",
       "4    0.222831   3.413312  \n",
       "5    0.422625   2.320966  \n",
       "6    0.178018   5.876052  \n",
       "7    0.358104   3.711067  \n",
       "8    0.076729   9.054086  \n",
       "9    0.032569  17.227454  \n",
       "0    0.250801   2.764709  \n",
       "18   0.178546  16.324422  \n",
       "19   0.035138  45.538564  \n",
       "11   0.484163   4.100832  \n",
       "12   0.678919   2.885449  \n",
       "13   0.494109   3.746661  \n",
       "14   0.634346   3.622155  \n",
       "15   0.774051   5.764601  \n",
       "16   0.897747   7.206190  \n",
       "17   0.379674  10.265420  \n",
       "10   0.279984   8.726582  "
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "estudiantes_por_escolaridad.replace({'ds8':\n",
    "                                    {1:'No, nunca ha asistido a la escuela',\n",
    "                                     2:'No, pero si fue a la escuela',\n",
    "                                     3:'Sí, actualmente estudia'},\n",
    "                                   'clave_respuesta':\n",
    "                                    {1:'Primaria incompleta', \n",
    "                                    2:'Primaria completa',\n",
    "                                    3:'Secundaria incompleta',\n",
    "                                    4:'Secundaria completa',\n",
    "                                    5:'Bachillerato incompleto',\n",
    "                                    6:'Bachillerato completo',\n",
    "                                    7:'Estudios Universitarios incompletos',\n",
    "                                    8:'Estudios  Universitarios completos',\n",
    "                                    9:'Estudios de Posgrado',\n",
    "                                    99:'No contesta',\n",
    "                                    0:'Nunca ha asistido a la escuela',}}, inplace=True)\n",
    "\n",
    "estudiantes_por_escolaridad.sort_values('ds8')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8901286e",
   "metadata": {},
   "source": [
    "Entonces, a partir de las estimaciones anteriores podemos decir que del total de personas que tienen estudios universitarios completos, el 9.64% actualmente no estudia y el 3.69% sigue estudiando."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "be1b174c",
   "metadata": {},
   "source": [
    "### 4.3 ¿Con qué proporción se mencionaron ciertas respuesta de la pregunta seleccionada? \n",
    "\n",
    "En ocasiones se desea calcular el porcentaje de selección de cierto conjunto de respuestas, para estos casos se puede utilizar la función `prevalencias`. \n",
    "\n",
    "Los argumentos de la función son los siguientes:\n",
    "- `b` dataframe con la base de datos.\n",
    "- `lista_vars` lista con los nombres de las variables para las que se desea calcular prevalencia.\n",
    "- `dicc`diccionario con la clasificación de las claves de respuesta.\n",
    "- `alp` valor entre 0 y 1 para definir el nivel de significancia del intervalo (el valor predeterminado es 0.95).\n",
    "- `ponderador` cadena de caracteres con el nombre de la variable donde está el factor de expansión de cada registro en la base de datos (el valor predeterminado es \"factor_exp\").\n",
    "- `estrato` cadena de caracteres con el nombre de la variable donde están la información de los estratos de la encuesta (el valor predeterminado es \"estrato\").\n",
    "- `upm` cadena de caracteres con el nombre de la variable donde está la información de las unidades primarias de la encuesta (el valor predeterminado es \"upm\").\n",
    "\n",
    "Como se puede notar los argumentos son casi los mismos que las funciones `proporciones` y `proporciones_des`. El único argumento nuevo es `dicc`, que tiene como objetivo recategorizar las respuestas a las preguntas de la lista de variables 'lista_vars' de la siguiente manera: \n",
    "- 1 si el evento ocurrió\n",
    "- 0 si el evento no ocurrió\n",
    "\n",
    "Para que sea más claro, creemos un ejemplo. Supóngase que se desea obtener la proporción de las personas que actualmente no estudian a partir de la pregunta `ds8`. \n",
    "\n",
    "Existen dos posibles respuestas que indican que alguien no estudia: `1`: \"No, nunca ha asistido a la escuela\" y `2` \"No, pero si fue a la escuela\". \n",
    "\n",
    "El argumento dicc sirve para indicar qué respuestas se desean considerar para calcular la proporción de un evento. En este caso el *evento* es que alguien no estudie, por lo tanto:\n",
    "- las respuestas con claves `1` y `2`se renombran como `1`porque indican que el evento ocurre.\n",
    "- las respuestas con clave `3` se renombran como `0` porque indican que el evento no ocurre.\n",
    "\n",
    "Es decir, para este caso específico el argumento `dicc` es:\n",
    "{1:1, 2:1, 3:0}.\n",
    "\n",
    "Veámos que produce la función una vez que son claros todos los argumentos que requiere:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "261ac5a5",
   "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>estimacion</th>\n",
       "      <th>ic_inf</th>\n",
       "      <th>ic_sup</th>\n",
       "      <th>poblacion</th>\n",
       "      <th>error_std</th>\n",
       "      <th>cv</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>77.398962</td>\n",
       "      <td>76.697332</td>\n",
       "      <td>78.100593</td>\n",
       "      <td>65969963</td>\n",
       "      <td>0.357981</td>\n",
       "      <td>0.462514</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   estimacion     ic_inf     ic_sup  poblacion  error_std        cv\n",
       "1   77.398962  76.697332  78.100593   65969963   0.357981  0.462514"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "prevalencias(b = b, \n",
    "             lista_vars = ['ds8'], \n",
    "             dicc={1:1, 2:1, 3:0},\n",
    "             alp = 0.95, \n",
    "             ponderador = 'factor_exp', \n",
    "             estrato= 'estrato', \n",
    "             upm = 'upm')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b25ea941",
   "metadata": {},
   "source": [
    "El resultado ahora es mucho más concreto, sólo se desea saber el porcentaje de la población que se estima que no estudia, y este es 77.39%. \n",
    "\n",
    "Sólo para comprobar, saquemos la proporción de cada respuesta de la pregunta `ds8`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "97eceb30",
   "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>clave_respuesta</th>\n",
       "      <th>estimacion</th>\n",
       "      <th>ic_inf</th>\n",
       "      <th>ic_sup</th>\n",
       "      <th>poblacion</th>\n",
       "      <th>error_std</th>\n",
       "      <th>cv</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2.235656</td>\n",
       "      <td>1.998388</td>\n",
       "      <td>2.472924</td>\n",
       "      <td>1905531</td>\n",
       "      <td>0.121057</td>\n",
       "      <td>5.414847</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>75.163307</td>\n",
       "      <td>74.447193</td>\n",
       "      <td>75.879420</td>\n",
       "      <td>64064432</td>\n",
       "      <td>0.365371</td>\n",
       "      <td>0.486103</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>22.601038</td>\n",
       "      <td>21.899407</td>\n",
       "      <td>23.302668</td>\n",
       "      <td>19263690</td>\n",
       "      <td>0.357981</td>\n",
       "      <td>1.583915</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   clave_respuesta  estimacion     ic_inf     ic_sup  poblacion  error_std  \\\n",
       "0                1    2.235656   1.998388   2.472924    1905531   0.121057   \n",
       "1                2   75.163307  74.447193  75.879420   64064432   0.365371   \n",
       "2                3   22.601038  21.899407  23.302668   19263690   0.357981   \n",
       "\n",
       "         cv  \n",
       "0  5.414847  \n",
       "1  0.486103  \n",
       "2  1.583915  "
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "proporciones(b = b, \n",
    "             clave_preg = 'ds8', \n",
    "             alp = 0.95, \n",
    "             ponderador = 'factor_exp', \n",
    "             estrato= 'estrato', \n",
    "             upm = 'upm')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "25f4e0fb",
   "metadata": {},
   "source": [
    "Y bueno, efectivamente, la suma de las estimaciones para las claves `1` y `2` corresponden con la estimación hecha a partir de la función `prevalencias`."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fb655711",
   "metadata": {},
   "source": [
    "### 4.4 ¿Con qué proporción se mencionaron ciertas respuesta de la pregunta seleccionada? \n",
    "### Desagregado por otra variable\n",
    "Al igual que la función `proporciones` tiene la función `proporciones_des` para obtener estimaciones desagregadas por otra variable, la función `prevalencias` tiene la función más específica `prevalencias_des` para generar estimaciones desagregadas por otra variable.\n",
    "\n",
    "Al igual que `proporciones_des`, `prevalencias_des` tiene el argumento `var_des` para indicar la lista de variables con respecto a las cuales se van a desagregar los resultados.\n",
    "\n",
    "Siguiendo con el ejemplo anterior, obtengamos la proporción de personas que no estudia desagregadas por escolaridad:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "63123db5",
   "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>ds9</th>\n",
       "      <th>estimacion</th>\n",
       "      <th>ic_inf</th>\n",
       "      <th>ic_sup</th>\n",
       "      <th>poblacion</th>\n",
       "      <th>error_std</th>\n",
       "      <th>cv</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Nunca ha asistido a la escuela</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>1905531</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Primaria incompleta</td>\n",
       "      <td>90.387407</td>\n",
       "      <td>88.842200</td>\n",
       "      <td>91.932614</td>\n",
       "      <td>5811612</td>\n",
       "      <td>0.788385</td>\n",
       "      <td>0.872229</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Primaria completa</td>\n",
       "      <td>82.431266</td>\n",
       "      <td>81.057882</td>\n",
       "      <td>83.804650</td>\n",
       "      <td>10671142</td>\n",
       "      <td>0.700719</td>\n",
       "      <td>0.850065</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Secundaria incompleta</td>\n",
       "      <td>47.288119</td>\n",
       "      <td>45.279154</td>\n",
       "      <td>49.297085</td>\n",
       "      <td>4066190</td>\n",
       "      <td>1.025001</td>\n",
       "      <td>2.167566</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Secundaria completa</td>\n",
       "      <td>88.140337</td>\n",
       "      <td>87.301344</td>\n",
       "      <td>88.979330</td>\n",
       "      <td>18880798</td>\n",
       "      <td>0.428066</td>\n",
       "      <td>0.485664</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Bachillerato incompleto</td>\n",
       "      <td>55.351290</td>\n",
       "      <td>52.807981</td>\n",
       "      <td>57.894599</td>\n",
       "      <td>4182323</td>\n",
       "      <td>1.297630</td>\n",
       "      <td>2.344354</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Bachillerato completo</td>\n",
       "      <td>81.850715</td>\n",
       "      <td>79.939909</td>\n",
       "      <td>83.761522</td>\n",
       "      <td>11665490</td>\n",
       "      <td>0.974919</td>\n",
       "      <td>1.191094</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Estudios Universitarios incompletos</td>\n",
       "      <td>44.712893</td>\n",
       "      <td>39.912790</td>\n",
       "      <td>49.512997</td>\n",
       "      <td>1940870</td>\n",
       "      <td>2.449077</td>\n",
       "      <td>5.477340</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Estudios  Universitarios completos</td>\n",
       "      <td>89.665885</td>\n",
       "      <td>87.782222</td>\n",
       "      <td>91.549548</td>\n",
       "      <td>6181975</td>\n",
       "      <td>0.961070</td>\n",
       "      <td>1.071835</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Estudios de Posgrado</td>\n",
       "      <td>72.042038</td>\n",
       "      <td>64.857167</td>\n",
       "      <td>79.226908</td>\n",
       "      <td>542916</td>\n",
       "      <td>3.665818</td>\n",
       "      <td>5.088443</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>No contesta</td>\n",
       "      <td>89.068981</td>\n",
       "      <td>79.756956</td>\n",
       "      <td>98.381005</td>\n",
       "      <td>121116</td>\n",
       "      <td>4.751120</td>\n",
       "      <td>5.334203</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                    ds9  estimacion      ic_inf      ic_sup  \\\n",
       "9        Nunca ha asistido a la escuela  100.000000  100.000000  100.000000   \n",
       "3                   Primaria incompleta   90.387407   88.842200   91.932614   \n",
       "5                     Primaria completa   82.431266   81.057882   83.804650   \n",
       "4                 Secundaria incompleta   47.288119   45.279154   49.297085   \n",
       "0                   Secundaria completa   88.140337   87.301344   88.979330   \n",
       "2               Bachillerato incompleto   55.351290   52.807981   57.894599   \n",
       "1                 Bachillerato completo   81.850715   79.939909   83.761522   \n",
       "6   Estudios Universitarios incompletos   44.712893   39.912790   49.512997   \n",
       "8    Estudios  Universitarios completos   89.665885   87.782222   91.549548   \n",
       "7                  Estudios de Posgrado   72.042038   64.857167   79.226908   \n",
       "10                          No contesta   89.068981   79.756956   98.381005   \n",
       "\n",
       "    poblacion  error_std        cv  \n",
       "9     1905531   0.000000  0.000000  \n",
       "3     5811612   0.788385  0.872229  \n",
       "5    10671142   0.700719  0.850065  \n",
       "4     4066190   1.025001  2.167566  \n",
       "0    18880798   0.428066  0.485664  \n",
       "2     4182323   1.297630  2.344354  \n",
       "1    11665490   0.974919  1.191094  \n",
       "6     1940870   2.449077  5.477340  \n",
       "8     6181975   0.961070  1.071835  \n",
       "7      542916   3.665818  5.088443  \n",
       "10     121116   4.751120  5.334203  "
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "prevalencias_des(b = b,\n",
    "                 lista_vars = ['ds8'],\n",
    "                 dicc={1:1, 2:1, 3:0},\n",
    "                 var_des = ['ds9'],\n",
    "                 alp = 0.95,\n",
    "                 ponderador = 'factor_exp',\n",
    "                 estrato= 'estrato',\n",
    "                 upm = 'upm').replace({'ds9':{1:'Primaria incompleta', \n",
    "                                    2:'Primaria completa',\n",
    "                                    3:'Secundaria incompleta',\n",
    "                                    4:'Secundaria completa',\n",
    "                                    5:'Bachillerato incompleto',\n",
    "                                    6:'Bachillerato completo',\n",
    "                                    7:'Estudios Universitarios incompletos',\n",
    "                                    8:'Estudios  Universitarios completos',\n",
    "                                    9:'Estudios de Posgrado',\n",
    "                                    99:'No contesta',\n",
    "                                    0:'Nunca ha asistido a la escuela',}})"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0e2f60fd",
   "metadata": {},
   "source": [
    "Estas estimaciones se pueden interpretar de la siguiente manera:\n",
    " > Del 100% de personas con ________ , el ____% no estudia\n",
    "\n",
    "Por ejemplo, del 100% de personas con \"secundaria completa\", el 88.14% no estudia."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9fb0aeea",
   "metadata": {},
   "source": [
    "### 4.5 ¿Con qué proporción se mencionaron ciertas respuesta de la pregunta seleccionada? \n",
    "### Desagregado por sexo y grupo etario\n",
    "Una de las desagregaciones más solicitadas es por sexo y grupo etario, por ello se creó la función `tabulados_prevalencias`.\n",
    "\n",
    "Los argumentos de esta función son los mismos que en la función `prevalencias_des`, con excepción de `var_sexo` y `var_ge` para indicar los nombres de las variables que contienen la información del sexo y el grupo etario en la encuesta.\n",
    "\n",
    "Ahora bien, para usar esta función, vamos a crear una variable correspondiente a los grupos etarios de nuestra encuesta y estructuraremos la variable de género que se tiene:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "740534bb",
   "metadata": {},
   "outputs": [],
   "source": [
    "# ---------- # Adecuaciones a las bases de datos # ------------------ #\n",
    "\n",
    "# Creación de grupos etarios \n",
    "#(los grupos etarios se pueden cambiar si así se desea) \n",
    "grupos_etarios=['12-17', '18-34', '35-59', '60-75']\n",
    "divisiones=[int(x[:2])-1 for x in grupos_etarios]+[int(grupos_etarios[-1][-2:])]\n",
    "b.insert(len(b.columns),'grupo_etario',pd.cut(list(b['ds3']), bins=divisiones, labels=grupos_etarios))\n",
    "\n",
    "# Cambio de nombre y valores de las columnas entidad y sexo\n",
    "b.rename(columns={'entidad':'cve_ent','desc_ent':'nom_ent','ds2':'sexo'}, inplace=True)\n",
    "valores_sexo = {1:'Hombre', 2:'Mujer'}\n",
    "b['sexo'] = b['sexo'].map(valores_sexo).fillna(b['sexo'])\n",
    "b['nom_ent']=b['nom_ent'].str.strip().apply(arreglar_palabras)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f9bfc1c3",
   "metadata": {},
   "source": [
    "Con estas adecuaciones es posible utilizar `tabulados_prevalencias` para estimar la proporción de personas en cada nivel escolar que no asisten a la escuela desagregado por género y grupo etario:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "059b1738",
   "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>sexo</th>\n",
       "      <th>grupo_etario</th>\n",
       "      <th>ds9</th>\n",
       "      <th>estimacion</th>\n",
       "      <th>ic_inf</th>\n",
       "      <th>ic_sup</th>\n",
       "      <th>poblacion</th>\n",
       "      <th>error_std</th>\n",
       "      <th>cv</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Mujeres y hombres</td>\n",
       "      <td>Población total</td>\n",
       "      <td>0</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>1905531</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Mujeres y hombres</td>\n",
       "      <td>Población total</td>\n",
       "      <td>1</td>\n",
       "      <td>90.387407</td>\n",
       "      <td>88.842200</td>\n",
       "      <td>91.932614</td>\n",
       "      <td>5811612</td>\n",
       "      <td>0.788385</td>\n",
       "      <td>0.872229</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Mujeres y hombres</td>\n",
       "      <td>Población total</td>\n",
       "      <td>2</td>\n",
       "      <td>82.431266</td>\n",
       "      <td>81.057882</td>\n",
       "      <td>83.804650</td>\n",
       "      <td>10671142</td>\n",
       "      <td>0.700719</td>\n",
       "      <td>0.850065</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Mujeres y hombres</td>\n",
       "      <td>Población total</td>\n",
       "      <td>3</td>\n",
       "      <td>47.288119</td>\n",
       "      <td>45.279154</td>\n",
       "      <td>49.297085</td>\n",
       "      <td>4066190</td>\n",
       "      <td>1.025001</td>\n",
       "      <td>2.167566</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Mujeres y hombres</td>\n",
       "      <td>Población total</td>\n",
       "      <td>4</td>\n",
       "      <td>88.140337</td>\n",
       "      <td>87.301344</td>\n",
       "      <td>88.979330</td>\n",
       "      <td>18880798</td>\n",
       "      <td>0.428066</td>\n",
       "      <td>0.485664</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>81</th>\n",
       "      <td>Hombre</td>\n",
       "      <td>60-75</td>\n",
       "      <td>99</td>\n",
       "      <td>95.948251</td>\n",
       "      <td>86.146261</td>\n",
       "      <td>105.750242</td>\n",
       "      <td>6749</td>\n",
       "      <td>5.001107</td>\n",
       "      <td>5.212297</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78</th>\n",
       "      <td>Mujer</td>\n",
       "      <td>12-17</td>\n",
       "      <td>99</td>\n",
       "      <td>37.823834</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>82.008822</td>\n",
       "      <td>1460</td>\n",
       "      <td>22.543775</td>\n",
       "      <td>59.602036</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>76</th>\n",
       "      <td>Mujer</td>\n",
       "      <td>18-34</td>\n",
       "      <td>99</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>4347</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>74</th>\n",
       "      <td>Mujer</td>\n",
       "      <td>35-59</td>\n",
       "      <td>99</td>\n",
       "      <td>97.911906</td>\n",
       "      <td>94.702574</td>\n",
       "      <td>101.121238</td>\n",
       "      <td>43702</td>\n",
       "      <td>1.637444</td>\n",
       "      <td>1.672365</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>66</th>\n",
       "      <td>Mujer</td>\n",
       "      <td>60-75</td>\n",
       "      <td>99</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>20263</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>117 rows × 9 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                 sexo     grupo_etario  ds9  estimacion      ic_inf  \\\n",
       "9   Mujeres y hombres  Población total    0  100.000000  100.000000   \n",
       "3   Mujeres y hombres  Población total    1   90.387407   88.842200   \n",
       "5   Mujeres y hombres  Población total    2   82.431266   81.057882   \n",
       "4   Mujeres y hombres  Población total    3   47.288119   45.279154   \n",
       "0   Mujeres y hombres  Población total    4   88.140337   87.301344   \n",
       "..                ...              ...  ...         ...         ...   \n",
       "81             Hombre            60-75   99   95.948251   86.146261   \n",
       "78              Mujer            12-17   99   37.823834    0.000000   \n",
       "76              Mujer            18-34   99  100.000000  100.000000   \n",
       "74              Mujer            35-59   99   97.911906   94.702574   \n",
       "66              Mujer            60-75   99  100.000000  100.000000   \n",
       "\n",
       "        ic_sup  poblacion  error_std         cv  \n",
       "9   100.000000    1905531   0.000000   0.000000  \n",
       "3    91.932614    5811612   0.788385   0.872229  \n",
       "5    83.804650   10671142   0.700719   0.850065  \n",
       "4    49.297085    4066190   1.025001   2.167566  \n",
       "0    88.979330   18880798   0.428066   0.485664  \n",
       "..         ...        ...        ...        ...  \n",
       "81  105.750242       6749   5.001107   5.212297  \n",
       "78   82.008822       1460  22.543775  59.602036  \n",
       "76  100.000000       4347   0.000000   0.000000  \n",
       "74  101.121238      43702   1.637444   1.672365  \n",
       "66  100.000000      20263   0.000000   0.000000  \n",
       "\n",
       "[117 rows x 9 columns]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tabulados_prevalencias(b = b,\n",
    "                       lista_vars = ['ds8'],\n",
    "                       dicc={1:1, 2:1, 3:0},\n",
    "                       var_des = ['ds9'],\n",
    "                       alp = 0.95,\n",
    "                       var_sexo='sexo',\n",
    "                       var_ge='grupo_etario',\n",
    "                       ponderador = 'factor_exp',\n",
    "                       estrato= 'estrato',\n",
    "                       upm = 'upm')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5bdb0894",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}