diff --git a/Ejemplo_nacimientos_2005_2010/Demo_CDS_nacimientos.ipynb b/Ejemplo_nacimientos_2005_2010/Demo_CDS_nacimientos.ipynb
index c77504eb15f035a7be4ca295e0e1b04ca4cb3130..64ba1aca4721d562b6f83db56c31aca124e51eac 100644
--- a/Ejemplo_nacimientos_2005_2010/Demo_CDS_nacimientos.ipynb
+++ b/Ejemplo_nacimientos_2005_2010/Demo_CDS_nacimientos.ipynb
@@ -1,3100 +1,946 @@
 {
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "8s9_BjAlsDvz"
-      },
-      "source": [
-        "# Indice\n",
-        "1. [Introduction](#introduction)\n",
-        "2. [Preparando la información](#paragraph1)\n",
-        "3. [¿Cuántos nacimientos hay por año en el país?](#paragraph2)\n",
-        "4. [¿Cuántos nacimientos hay por año en el país según el grupo etario de la madre?](#paragraph3)\n",
-        "5. [¿Que proporción de madres tuvo hijos antes de los 20?](#paragraph4)\n",
-        "6. [Para cada nivel de instrucción/educación, ¿Cuántos nacimientos hubo en cada grupo etario?](#paragraph5)\n",
-        "7. [Referencias técnicas](#paragraph6)\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "7JgsokQzYAJX"
-      },
-      "source": [
-        "## Introducción <a name=\"introduction\"></a>\n",
-        "\n",
-        "---\n",
-        "En esta propuesta vamos a usar datos del ministerio de salud sobre nacimientos en el país entre 2005 y 2010 para hacer algunas preguntas y obtener una respuesta visual con gráficos.\n",
-        "---\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "# Qué información podemos obtener:\n",
-        "* ¿Cuántos nacimientos hay por año en el país?\n",
-        "* ¿Cuántos nacimientos hay por año en el país según el grupo etario de la madre?\n",
-        "* ¿Que proporción de madres tuvo hijos antes de los 20?\n",
-        "* Para cada nivel de instrucción/educación, ¿Cuántos nacimientos hubo en cada grupo etario?"
-      ],
-      "metadata": {
-        "id": "fTccwFpMvWpQ"
-      }
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "O35LytWBsDv0"
-      },
-      "source": [
-        "## Link donde obtengo el dataset\n",
-        "El dataset viene del ministerio de salud y puede encontrarse en: \n",
-        "http://datos.salud.gob.ar/dataset/nacidos-vivos-registrados-por-jurisdiccion-de-residencia-de-la-madre-republica-argentina-ano-2017/archivo/3c891522-8448-4490-a7da-6deba78d3b32\n",
-        "Aunque los datos fueron limpiados para facilitar su uso"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "Antes de empezar, una aclaración: En muchos lugares de la ejecución, se puede ver un SettingWithCopyWarning que nos avisa que estamos tratando de colocar una parte de una copia del dataframe en el dataframe. Esto no es un problema y se puede ignorar"
-      ],
-      "metadata": {
-        "id": "GqUKO6-k2moi"
-      }
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "QYEZLjtwiH6p"
-      },
-      "source": [
-        "## Preparando la información <a name=\"paragraph1\"></a>\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "Primero importamos pandas, esto nos permitirá usar las funciones que provee, es costumbre renombrarla como **pd** y también el módulo pyplot de matplotlib normalmente abreviado como **plt**"
-      ],
-      "metadata": {
-        "id": "q-PphAWuE151"
-      }
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "gSPpdLmni-mZ"
-      },
-      "outputs": [],
-      "source": [
-        "import pandas as pd\n",
-        "import matplotlib.pyplot as plt"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "mGIGSZnmiTyN"
-      },
-      "source": [
-        "Usamos la función **read_csv** que nos transforma nuestros datos (en formato csv) a un dataframe que podemos manipular fácilmente."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "oanfaLLOvlVG"
-      },
-      "outputs": [],
-      "source": [
-        "nacimientos = pd.read_csv(\"Nacimientos_Arg_2005-2010.csv\",encoding = \"UTF-8\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "6cuhJ6w2zbUc"
-      },
-      "source": [
-        "Vamos a ver como vemos la información:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "FDFSoh0Xwh3M",
-        "outputId": "39b9b53f-9cda-4c25-adb7-ad0fa8ca0609"
-      },
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "   anio  jurisdiccion_de_residencia_id    jurisdicion_residencia_nombre  \\\n",
-              "0  2005                              2  Ciudad Autónoma de Buenos Aires   \n",
-              "1  2005                              2  Ciudad Autónoma de Buenos Aires   \n",
-              "2  2005                              2  Ciudad Autónoma de Buenos Aires   \n",
-              "3  2005                              2  Ciudad Autónoma de Buenos Aires   \n",
-              "4  2005                              2  Ciudad Autónoma de Buenos Aires   \n",
-              "\n",
-              "   edad_madre_grupo_id edad_madre_grupo                instruccion_madre  \\\n",
-              "0                    5          30 a 34  Secundaria/Polimodal Incompleta   \n",
-              "1                    5          30 a 34         Primaria/C. EGB Completa   \n",
-              "2                    4          25 a 29    Secundaria/Polimodal Completa   \n",
-              "3                    5          30 a 34  Secundaria/Polimodal Incompleta   \n",
-              "4                    4          25 a 29    Secundaria/Polimodal Completa   \n",
-              "\n",
-              "   semana_gestacion_id semana_gestacion intervalo_peso_al_nacer       Sexo  \\\n",
-              "0                    4          28 a 31             1500 a 1999  masculino   \n",
-              "1                    4          28 a 31               500 a 999  masculino   \n",
-              "2                    4          28 a 31             1000 a 1499  masculino   \n",
-              "3                    5          32 a 36             1500 a 1999  masculino   \n",
-              "4                    4          28 a 31             1500 a 1999  masculino   \n",
-              "\n",
-              "   nacimientos_cantidad  \n",
-              "0                     1  \n",
-              "1                     2  \n",
-              "2                     6  \n",
-              "3                     5  \n",
-              "4                     1  "
-            ],
-            "text/html": [
-              "\n",
-              "  <div id=\"df-4567b23d-849d-4a0e-a948-ce613b0d640d\">\n",
-              "    <div class=\"colab-df-container\">\n",
-              "      <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>anio</th>\n",
-              "      <th>jurisdiccion_de_residencia_id</th>\n",
-              "      <th>jurisdicion_residencia_nombre</th>\n",
-              "      <th>edad_madre_grupo_id</th>\n",
-              "      <th>edad_madre_grupo</th>\n",
-              "      <th>instruccion_madre</th>\n",
-              "      <th>semana_gestacion_id</th>\n",
-              "      <th>semana_gestacion</th>\n",
-              "      <th>intervalo_peso_al_nacer</th>\n",
-              "      <th>Sexo</th>\n",
-              "      <th>nacimientos_cantidad</th>\n",
-              "    </tr>\n",
-              "  </thead>\n",
-              "  <tbody>\n",
-              "    <tr>\n",
-              "      <th>0</th>\n",
-              "      <td>2005</td>\n",
-              "      <td>2</td>\n",
-              "      <td>Ciudad Autónoma de Buenos Aires</td>\n",
-              "      <td>5</td>\n",
-              "      <td>30 a 34</td>\n",
-              "      <td>Secundaria/Polimodal Incompleta</td>\n",
-              "      <td>4</td>\n",
-              "      <td>28 a 31</td>\n",
-              "      <td>1500 a 1999</td>\n",
-              "      <td>masculino</td>\n",
-              "      <td>1</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>1</th>\n",
-              "      <td>2005</td>\n",
-              "      <td>2</td>\n",
-              "      <td>Ciudad Autónoma de Buenos Aires</td>\n",
-              "      <td>5</td>\n",
-              "      <td>30 a 34</td>\n",
-              "      <td>Primaria/C. EGB Completa</td>\n",
-              "      <td>4</td>\n",
-              "      <td>28 a 31</td>\n",
-              "      <td>500 a 999</td>\n",
-              "      <td>masculino</td>\n",
-              "      <td>2</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>2</th>\n",
-              "      <td>2005</td>\n",
-              "      <td>2</td>\n",
-              "      <td>Ciudad Autónoma de Buenos Aires</td>\n",
-              "      <td>4</td>\n",
-              "      <td>25 a 29</td>\n",
-              "      <td>Secundaria/Polimodal Completa</td>\n",
-              "      <td>4</td>\n",
-              "      <td>28 a 31</td>\n",
-              "      <td>1000 a 1499</td>\n",
-              "      <td>masculino</td>\n",
-              "      <td>6</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>3</th>\n",
-              "      <td>2005</td>\n",
-              "      <td>2</td>\n",
-              "      <td>Ciudad Autónoma de Buenos Aires</td>\n",
-              "      <td>5</td>\n",
-              "      <td>30 a 34</td>\n",
-              "      <td>Secundaria/Polimodal Incompleta</td>\n",
-              "      <td>5</td>\n",
-              "      <td>32 a 36</td>\n",
-              "      <td>1500 a 1999</td>\n",
-              "      <td>masculino</td>\n",
-              "      <td>5</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>4</th>\n",
-              "      <td>2005</td>\n",
-              "      <td>2</td>\n",
-              "      <td>Ciudad Autónoma de Buenos Aires</td>\n",
-              "      <td>4</td>\n",
-              "      <td>25 a 29</td>\n",
-              "      <td>Secundaria/Polimodal Completa</td>\n",
-              "      <td>4</td>\n",
-              "      <td>28 a 31</td>\n",
-              "      <td>1500 a 1999</td>\n",
-              "      <td>masculino</td>\n",
-              "      <td>1</td>\n",
-              "    </tr>\n",
-              "  </tbody>\n",
-              "</table>\n",
-              "</div>\n",
-              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-4567b23d-849d-4a0e-a948-ce613b0d640d')\"\n",
-              "              title=\"Convert this dataframe to an interactive table.\"\n",
-              "              style=\"display:none;\">\n",
-              "        \n",
-              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
-              "       width=\"24px\">\n",
-              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
-              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
-              "  </svg>\n",
-              "      </button>\n",
-              "      \n",
-              "  <style>\n",
-              "    .colab-df-container {\n",
-              "      display:flex;\n",
-              "      flex-wrap:wrap;\n",
-              "      gap: 12px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert {\n",
-              "      background-color: #E8F0FE;\n",
-              "      border: none;\n",
-              "      border-radius: 50%;\n",
-              "      cursor: pointer;\n",
-              "      display: none;\n",
-              "      fill: #1967D2;\n",
-              "      height: 32px;\n",
-              "      padding: 0 0 0 0;\n",
-              "      width: 32px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert:hover {\n",
-              "      background-color: #E2EBFA;\n",
-              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
-              "      fill: #174EA6;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert {\n",
-              "      background-color: #3B4455;\n",
-              "      fill: #D2E3FC;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert:hover {\n",
-              "      background-color: #434B5C;\n",
-              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
-              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
-              "      fill: #FFFFFF;\n",
-              "    }\n",
-              "  </style>\n",
-              "\n",
-              "      <script>\n",
-              "        const buttonEl =\n",
-              "          document.querySelector('#df-4567b23d-849d-4a0e-a948-ce613b0d640d button.colab-df-convert');\n",
-              "        buttonEl.style.display =\n",
-              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
-              "\n",
-              "        async function convertToInteractive(key) {\n",
-              "          const element = document.querySelector('#df-4567b23d-849d-4a0e-a948-ce613b0d640d');\n",
-              "          const dataTable =\n",
-              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
-              "                                                     [key], {});\n",
-              "          if (!dataTable) return;\n",
-              "\n",
-              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
-              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
-              "            + ' to learn more about interactive tables.';\n",
-              "          element.innerHTML = '';\n",
-              "          dataTable['output_type'] = 'display_data';\n",
-              "          await google.colab.output.renderOutput(dataTable, element);\n",
-              "          const docLink = document.createElement('div');\n",
-              "          docLink.innerHTML = docLinkHtml;\n",
-              "          element.appendChild(docLink);\n",
-              "        }\n",
-              "      </script>\n",
-              "    </div>\n",
-              "  </div>\n",
-              "  "
-            ]
-          },
-          "metadata": {},
-          "execution_count": 3
-        }
-      ],
-      "source": [
-        "nacimientos.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "B6kS1QTB6aF9"
-      },
-      "source": [
-        "No vamos a trabajar con toda la información, asi que la cortamos a las columnas que nos interesan:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "Z9xxlqmM6kc4"
-      },
-      "outputs": [],
-      "source": [
-        "nacimientos = nacimientos[[\"anio\",\"edad_madre_grupo\",\"instruccion_madre\",\"nacimientos_cantidad\"]]"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "4lOR_MP7sDv-",
-        "outputId": "f407388c-6bcd-45fe-e984-96be9affface"
-      },
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "        anio edad_madre_grupo                   instruccion_madre  \\\n",
-              "0       2005          30 a 34     Secundaria/Polimodal Incompleta   \n",
-              "1       2005          30 a 34            Primaria/C. EGB Completa   \n",
-              "2       2005          25 a 29       Secundaria/Polimodal Completa   \n",
-              "3       2005          30 a 34     Secundaria/Polimodal Incompleta   \n",
-              "4       2005          25 a 29       Secundaria/Polimodal Completa   \n",
-              "...      ...              ...                                 ...   \n",
-              "497969  2017          30 a 34       Secundaria/Polimodal Completa   \n",
-              "497970  2017          30 a 34       Secundaria/Polimodal Completa   \n",
-              "497971  2007          25 a 29    Terciaria/Universitaria Completa   \n",
-              "497972  2017          30 a 34  Terciaria/Universitaria Incompleta   \n",
-              "497973  2017  Sin especificar                     Sin especificar   \n",
-              "\n",
-              "        nacimientos_cantidad  \n",
-              "0                          1  \n",
-              "1                          2  \n",
-              "2                          6  \n",
-              "3                          5  \n",
-              "4                          1  \n",
-              "...                      ...  \n",
-              "497969                     1  \n",
-              "497970                     1  \n",
-              "497971                     1  \n",
-              "497972                     1  \n",
-              "497973                    10  \n",
-              "\n",
-              "[497974 rows x 4 columns]"
-            ],
-            "text/html": [
-              "\n",
-              "  <div id=\"df-7565c802-91df-4f6a-adc3-3a8a96800402\">\n",
-              "    <div class=\"colab-df-container\">\n",
-              "      <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>anio</th>\n",
-              "      <th>edad_madre_grupo</th>\n",
-              "      <th>instruccion_madre</th>\n",
-              "      <th>nacimientos_cantidad</th>\n",
-              "    </tr>\n",
-              "  </thead>\n",
-              "  <tbody>\n",
-              "    <tr>\n",
-              "      <th>0</th>\n",
-              "      <td>2005</td>\n",
-              "      <td>30 a 34</td>\n",
-              "      <td>Secundaria/Polimodal Incompleta</td>\n",
-              "      <td>1</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>1</th>\n",
-              "      <td>2005</td>\n",
-              "      <td>30 a 34</td>\n",
-              "      <td>Primaria/C. EGB Completa</td>\n",
-              "      <td>2</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>2</th>\n",
-              "      <td>2005</td>\n",
-              "      <td>25 a 29</td>\n",
-              "      <td>Secundaria/Polimodal Completa</td>\n",
-              "      <td>6</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>3</th>\n",
-              "      <td>2005</td>\n",
-              "      <td>30 a 34</td>\n",
-              "      <td>Secundaria/Polimodal Incompleta</td>\n",
-              "      <td>5</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>4</th>\n",
-              "      <td>2005</td>\n",
-              "      <td>25 a 29</td>\n",
-              "      <td>Secundaria/Polimodal Completa</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",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>497969</th>\n",
-              "      <td>2017</td>\n",
-              "      <td>30 a 34</td>\n",
-              "      <td>Secundaria/Polimodal Completa</td>\n",
-              "      <td>1</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>497970</th>\n",
-              "      <td>2017</td>\n",
-              "      <td>30 a 34</td>\n",
-              "      <td>Secundaria/Polimodal Completa</td>\n",
-              "      <td>1</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>497971</th>\n",
-              "      <td>2007</td>\n",
-              "      <td>25 a 29</td>\n",
-              "      <td>Terciaria/Universitaria Completa</td>\n",
-              "      <td>1</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>497972</th>\n",
-              "      <td>2017</td>\n",
-              "      <td>30 a 34</td>\n",
-              "      <td>Terciaria/Universitaria Incompleta</td>\n",
-              "      <td>1</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>497973</th>\n",
-              "      <td>2017</td>\n",
-              "      <td>Sin especificar</td>\n",
-              "      <td>Sin especificar</td>\n",
-              "      <td>10</td>\n",
-              "    </tr>\n",
-              "  </tbody>\n",
-              "</table>\n",
-              "<p>497974 rows × 4 columns</p>\n",
-              "</div>\n",
-              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-7565c802-91df-4f6a-adc3-3a8a96800402')\"\n",
-              "              title=\"Convert this dataframe to an interactive table.\"\n",
-              "              style=\"display:none;\">\n",
-              "        \n",
-              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
-              "       width=\"24px\">\n",
-              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
-              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
-              "  </svg>\n",
-              "      </button>\n",
-              "      \n",
-              "  <style>\n",
-              "    .colab-df-container {\n",
-              "      display:flex;\n",
-              "      flex-wrap:wrap;\n",
-              "      gap: 12px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert {\n",
-              "      background-color: #E8F0FE;\n",
-              "      border: none;\n",
-              "      border-radius: 50%;\n",
-              "      cursor: pointer;\n",
-              "      display: none;\n",
-              "      fill: #1967D2;\n",
-              "      height: 32px;\n",
-              "      padding: 0 0 0 0;\n",
-              "      width: 32px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert:hover {\n",
-              "      background-color: #E2EBFA;\n",
-              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
-              "      fill: #174EA6;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert {\n",
-              "      background-color: #3B4455;\n",
-              "      fill: #D2E3FC;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert:hover {\n",
-              "      background-color: #434B5C;\n",
-              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
-              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
-              "      fill: #FFFFFF;\n",
-              "    }\n",
-              "  </style>\n",
-              "\n",
-              "      <script>\n",
-              "        const buttonEl =\n",
-              "          document.querySelector('#df-7565c802-91df-4f6a-adc3-3a8a96800402 button.colab-df-convert');\n",
-              "        buttonEl.style.display =\n",
-              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
-              "\n",
-              "        async function convertToInteractive(key) {\n",
-              "          const element = document.querySelector('#df-7565c802-91df-4f6a-adc3-3a8a96800402');\n",
-              "          const dataTable =\n",
-              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
-              "                                                     [key], {});\n",
-              "          if (!dataTable) return;\n",
-              "\n",
-              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
-              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
-              "            + ' to learn more about interactive tables.';\n",
-              "          element.innerHTML = '';\n",
-              "          dataTable['output_type'] = 'display_data';\n",
-              "          await google.colab.output.renderOutput(dataTable, element);\n",
-              "          const docLink = document.createElement('div');\n",
-              "          docLink.innerHTML = docLinkHtml;\n",
-              "          element.appendChild(docLink);\n",
-              "        }\n",
-              "      </script>\n",
-              "    </div>\n",
-              "  </div>\n",
-              "  "
-            ]
-          },
-          "metadata": {},
-          "execution_count": 5
-        }
-      ],
-      "source": [
-        "nacimientos"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "HY9NHf7Mw2Z8"
-      },
-      "source": [
-        "## Pregunta: ¿Cuántos nacimientos hay por año en el país? <a name=\"paragraph2\"></a>\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "XJ_i_X3IA5oI"
-      },
-      "source": [
-        "Para esto vamos a necesitar menos información que antes, solo la cantidad de nacimientos y el año en el que ocurrieron.\n",
-        "Se abrevia nacimientos como nac para mayor legibilidad:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 206
-        },
-        "id": "I-PYL_Qez5hV",
-        "outputId": "e0c50fba-5ab8-4d94-989c-65714f666c97"
-      },
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "   anio  nacimientos_cantidad\n",
-              "0  2005                     1\n",
-              "1  2005                     2\n",
-              "2  2005                     6\n",
-              "3  2005                     5\n",
-              "4  2005                     1"
-            ],
-            "text/html": [
-              "\n",
-              "  <div id=\"df-6d429b15-769b-4b60-8e0e-02fb82df0d02\">\n",
-              "    <div class=\"colab-df-container\">\n",
-              "      <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>anio</th>\n",
-              "      <th>nacimientos_cantidad</th>\n",
-              "    </tr>\n",
-              "  </thead>\n",
-              "  <tbody>\n",
-              "    <tr>\n",
-              "      <th>0</th>\n",
-              "      <td>2005</td>\n",
-              "      <td>1</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>1</th>\n",
-              "      <td>2005</td>\n",
-              "      <td>2</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>2</th>\n",
-              "      <td>2005</td>\n",
-              "      <td>6</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>3</th>\n",
-              "      <td>2005</td>\n",
-              "      <td>5</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>4</th>\n",
-              "      <td>2005</td>\n",
-              "      <td>1</td>\n",
-              "    </tr>\n",
-              "  </tbody>\n",
-              "</table>\n",
-              "</div>\n",
-              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-6d429b15-769b-4b60-8e0e-02fb82df0d02')\"\n",
-              "              title=\"Convert this dataframe to an interactive table.\"\n",
-              "              style=\"display:none;\">\n",
-              "        \n",
-              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
-              "       width=\"24px\">\n",
-              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
-              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
-              "  </svg>\n",
-              "      </button>\n",
-              "      \n",
-              "  <style>\n",
-              "    .colab-df-container {\n",
-              "      display:flex;\n",
-              "      flex-wrap:wrap;\n",
-              "      gap: 12px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert {\n",
-              "      background-color: #E8F0FE;\n",
-              "      border: none;\n",
-              "      border-radius: 50%;\n",
-              "      cursor: pointer;\n",
-              "      display: none;\n",
-              "      fill: #1967D2;\n",
-              "      height: 32px;\n",
-              "      padding: 0 0 0 0;\n",
-              "      width: 32px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert:hover {\n",
-              "      background-color: #E2EBFA;\n",
-              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
-              "      fill: #174EA6;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert {\n",
-              "      background-color: #3B4455;\n",
-              "      fill: #D2E3FC;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert:hover {\n",
-              "      background-color: #434B5C;\n",
-              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
-              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
-              "      fill: #FFFFFF;\n",
-              "    }\n",
-              "  </style>\n",
-              "\n",
-              "      <script>\n",
-              "        const buttonEl =\n",
-              "          document.querySelector('#df-6d429b15-769b-4b60-8e0e-02fb82df0d02 button.colab-df-convert');\n",
-              "        buttonEl.style.display =\n",
-              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
-              "\n",
-              "        async function convertToInteractive(key) {\n",
-              "          const element = document.querySelector('#df-6d429b15-769b-4b60-8e0e-02fb82df0d02');\n",
-              "          const dataTable =\n",
-              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
-              "                                                     [key], {});\n",
-              "          if (!dataTable) return;\n",
-              "\n",
-              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
-              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
-              "            + ' to learn more about interactive tables.';\n",
-              "          element.innerHTML = '';\n",
-              "          dataTable['output_type'] = 'display_data';\n",
-              "          await google.colab.output.renderOutput(dataTable, element);\n",
-              "          const docLink = document.createElement('div');\n",
-              "          docLink.innerHTML = docLinkHtml;\n",
-              "          element.appendChild(docLink);\n",
-              "        }\n",
-              "      </script>\n",
-              "    </div>\n",
-              "  </div>\n",
-              "  "
-            ]
-          },
-          "metadata": {},
-          "execution_count": 6
-        }
-      ],
-      "source": [
-        "nac_por_año = nacimientos[[\"anio\",\"nacimientos_cantidad\"]]\n",
-        "nac_por_año.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "D6Dps9axBQrp"
-      },
-      "source": [
-        "Hay un problema con esta información, como la cantidad de nacimientos no está agregada por año sino que también por otros factores, hay que agrupar por año y sumar los nacimientos de cada grupo:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 238
-        },
-        "id": "FbY9_hRmBDuW",
-        "outputId": "2f9f8d43-6014-4f71-abf5-be997855408d"
-      },
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "      nacimientos_cantidad\n",
-              "anio                      \n",
-              "2005                712220\n",
-              "2006                696451\n",
-              "2007                700792\n",
-              "2008                746460\n",
-              "2009                745336"
-            ],
-            "text/html": [
-              "\n",
-              "  <div id=\"df-c2e7d7ab-d88c-41c9-9fe3-47b19a1d223a\">\n",
-              "    <div class=\"colab-df-container\">\n",
-              "      <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>nacimientos_cantidad</th>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>anio</th>\n",
-              "      <th></th>\n",
-              "    </tr>\n",
-              "  </thead>\n",
-              "  <tbody>\n",
-              "    <tr>\n",
-              "      <th>2005</th>\n",
-              "      <td>712220</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>2006</th>\n",
-              "      <td>696451</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>2007</th>\n",
-              "      <td>700792</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>2008</th>\n",
-              "      <td>746460</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>2009</th>\n",
-              "      <td>745336</td>\n",
-              "    </tr>\n",
-              "  </tbody>\n",
-              "</table>\n",
-              "</div>\n",
-              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-c2e7d7ab-d88c-41c9-9fe3-47b19a1d223a')\"\n",
-              "              title=\"Convert this dataframe to an interactive table.\"\n",
-              "              style=\"display:none;\">\n",
-              "        \n",
-              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
-              "       width=\"24px\">\n",
-              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
-              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
-              "  </svg>\n",
-              "      </button>\n",
-              "      \n",
-              "  <style>\n",
-              "    .colab-df-container {\n",
-              "      display:flex;\n",
-              "      flex-wrap:wrap;\n",
-              "      gap: 12px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert {\n",
-              "      background-color: #E8F0FE;\n",
-              "      border: none;\n",
-              "      border-radius: 50%;\n",
-              "      cursor: pointer;\n",
-              "      display: none;\n",
-              "      fill: #1967D2;\n",
-              "      height: 32px;\n",
-              "      padding: 0 0 0 0;\n",
-              "      width: 32px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert:hover {\n",
-              "      background-color: #E2EBFA;\n",
-              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
-              "      fill: #174EA6;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert {\n",
-              "      background-color: #3B4455;\n",
-              "      fill: #D2E3FC;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert:hover {\n",
-              "      background-color: #434B5C;\n",
-              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
-              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
-              "      fill: #FFFFFF;\n",
-              "    }\n",
-              "  </style>\n",
-              "\n",
-              "      <script>\n",
-              "        const buttonEl =\n",
-              "          document.querySelector('#df-c2e7d7ab-d88c-41c9-9fe3-47b19a1d223a button.colab-df-convert');\n",
-              "        buttonEl.style.display =\n",
-              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
-              "\n",
-              "        async function convertToInteractive(key) {\n",
-              "          const element = document.querySelector('#df-c2e7d7ab-d88c-41c9-9fe3-47b19a1d223a');\n",
-              "          const dataTable =\n",
-              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
-              "                                                     [key], {});\n",
-              "          if (!dataTable) return;\n",
-              "\n",
-              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
-              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
-              "            + ' to learn more about interactive tables.';\n",
-              "          element.innerHTML = '';\n",
-              "          dataTable['output_type'] = 'display_data';\n",
-              "          await google.colab.output.renderOutput(dataTable, element);\n",
-              "          const docLink = document.createElement('div');\n",
-              "          docLink.innerHTML = docLinkHtml;\n",
-              "          element.appendChild(docLink);\n",
-              "        }\n",
-              "      </script>\n",
-              "    </div>\n",
-              "  </div>\n",
-              "  "
-            ]
-          },
-          "metadata": {},
-          "execution_count": 7
-        }
-      ],
-      "source": [
-        "nac_por_año = nac_por_año.groupby(\"anio\").sum()\n",
-        "nac_por_año.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "xPLMRoEUmicq"
-      },
-      "source": [
-        "Ahora está mejor.\n",
-        "Vamos a graficarlo con un simple gráfico de línea:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 459
-        },
-        "id": "19u3wAvl0jIN",
-        "outputId": "97bf73c5-1a0e-4ed4-d2e2-a7d6c12536e7"
-      },
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "<matplotlib.legend.Legend at 0x7f705be255d0>"
-            ]
-          },
-          "metadata": {},
-          "execution_count": 8
-        },
-        {
-          "output_type": "display_data",
-          "data": {
-            "text/plain": [
-              "<Figure size 1080x504 with 1 Axes>"
-            ],
-            "image/png": "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\n"
-          },
-          "metadata": {
-            "needs_background": "light"
-          }
-        }
-      ],
-      "source": [
-        "nac_por_año.plot(kind= \"line\",figsize= (15,7),grid=True)\n",
-        "plt.legend([\"Cantidad de nacimientos\"])"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ef0DL8Gh8jLf"
-      },
-      "source": [
-        "Hay un problema con el gráfico, el eje y no comienza en 0 y hace que el gráfico se vea mal, esto se soluciona indicando el límite inferior de y:\n",
-        "También establecemos la leyenda del gráfico"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 459
-        },
-        "id": "D8TfEws58gvQ",
-        "outputId": "eb6842af-3d5b-40f1-fc04-689461f5abb1"
-      },
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "<matplotlib.legend.Legend at 0x7f705bc787d0>"
-            ]
-          },
-          "metadata": {},
-          "execution_count": 9
-        },
-        {
-          "output_type": "display_data",
-          "data": {
-            "text/plain": [
-              "<Figure size 1080x504 with 1 Axes>"
-            ],
-            "image/png": "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\n"
-          },
-          "metadata": {
-            "needs_background": "light"
-          }
-        }
-      ],
-      "source": [
-        "nac_por_año.plot(kind= \"line\",figsize= (15,7),ylim=(0),grid=True)\n",
-        "plt.legend([\"Cantidad de nacimientos\"])"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "_NpC6hVyzwSc"
-      },
-      "source": [
-        "## Pregunta: ¿Cuántos nacimientos hay por año en el país según el grupo etario de la madre? <a name=\"paragraph3\"></a>\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "IgOe-p4pCly3"
-      },
-      "source": [
-        "En este caso necesitamos saber el año, el grupo etario de la madre y la cantidad:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "glA4XLTT86wg"
-      },
-      "outputs": [],
-      "source": [
-        "nac_edad_madre = nacimientos[[\"anio\",\"edad_madre_grupo\",\"nacimientos_cantidad\"]]"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "qCnqL52JC-SA"
-      },
-      "source": [
-        "Hay algunos nacimientos donde el grupo etario de la madre no fue especificado, por lo tanto no podemos sacar conclusiones, asique se ignoran."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "If8D3jpHC93r",
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "outputId": "073e094d-4b1a-489b-bc72-e76982078ee7"
-      },
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stderr",
-          "text": [
-            "/usr/local/lib/python3.7/dist-packages/pandas/core/frame.py:4913: SettingWithCopyWarning: \n",
-            "A value is trying to be set on a copy of a slice from a DataFrame\n",
-            "\n",
-            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
-            "  errors=errors,\n"
-          ]
-        }
-      ],
-      "source": [
-        "nac_edad_madre.drop(nac_edad_madre.index[nac_edad_madre['edad_madre_grupo'] == \"Sin especificar\"], inplace = True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ccDvLT5BDpKQ"
-      },
-      "source": [
-        "Ahora con la información filtrada, hay que agrupar por dos criterios, primero por el año y luego por el grupo etario y finalmente sumar las cantidades de estos grupos:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 238
-        },
-        "id": "-iJyxCfUC2SY",
-        "outputId": "292a3e1f-01c5-4907-8876-f7aef2a447b2"
-      },
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "                       nacimientos_cantidad\n",
-              "anio edad_madre_grupo                      \n",
-              "2005  Menor de 15                      2699\n",
-              "     15 a 19                         104410\n",
-              "     20 a 24                         177813\n",
-              "     25 a 29                         182778\n",
-              "     30 a 34                         141689"
-            ],
-            "text/html": [
-              "\n",
-              "  <div id=\"df-49138619-ddec-4732-863d-fa57c9dd26e0\">\n",
-              "    <div class=\"colab-df-container\">\n",
-              "      <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></th>\n",
-              "      <th>nacimientos_cantidad</th>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>anio</th>\n",
-              "      <th>edad_madre_grupo</th>\n",
-              "      <th></th>\n",
-              "    </tr>\n",
-              "  </thead>\n",
-              "  <tbody>\n",
-              "    <tr>\n",
-              "      <th rowspan=\"5\" valign=\"top\">2005</th>\n",
-              "      <th>Menor de 15</th>\n",
-              "      <td>2699</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>15 a 19</th>\n",
-              "      <td>104410</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>20 a 24</th>\n",
-              "      <td>177813</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>25 a 29</th>\n",
-              "      <td>182778</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>30 a 34</th>\n",
-              "      <td>141689</td>\n",
-              "    </tr>\n",
-              "  </tbody>\n",
-              "</table>\n",
-              "</div>\n",
-              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-49138619-ddec-4732-863d-fa57c9dd26e0')\"\n",
-              "              title=\"Convert this dataframe to an interactive table.\"\n",
-              "              style=\"display:none;\">\n",
-              "        \n",
-              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
-              "       width=\"24px\">\n",
-              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
-              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
-              "  </svg>\n",
-              "      </button>\n",
-              "      \n",
-              "  <style>\n",
-              "    .colab-df-container {\n",
-              "      display:flex;\n",
-              "      flex-wrap:wrap;\n",
-              "      gap: 12px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert {\n",
-              "      background-color: #E8F0FE;\n",
-              "      border: none;\n",
-              "      border-radius: 50%;\n",
-              "      cursor: pointer;\n",
-              "      display: none;\n",
-              "      fill: #1967D2;\n",
-              "      height: 32px;\n",
-              "      padding: 0 0 0 0;\n",
-              "      width: 32px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert:hover {\n",
-              "      background-color: #E2EBFA;\n",
-              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
-              "      fill: #174EA6;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert {\n",
-              "      background-color: #3B4455;\n",
-              "      fill: #D2E3FC;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert:hover {\n",
-              "      background-color: #434B5C;\n",
-              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
-              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
-              "      fill: #FFFFFF;\n",
-              "    }\n",
-              "  </style>\n",
-              "\n",
-              "      <script>\n",
-              "        const buttonEl =\n",
-              "          document.querySelector('#df-49138619-ddec-4732-863d-fa57c9dd26e0 button.colab-df-convert');\n",
-              "        buttonEl.style.display =\n",
-              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
-              "\n",
-              "        async function convertToInteractive(key) {\n",
-              "          const element = document.querySelector('#df-49138619-ddec-4732-863d-fa57c9dd26e0');\n",
-              "          const dataTable =\n",
-              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
-              "                                                     [key], {});\n",
-              "          if (!dataTable) return;\n",
-              "\n",
-              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
-              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
-              "            + ' to learn more about interactive tables.';\n",
-              "          element.innerHTML = '';\n",
-              "          dataTable['output_type'] = 'display_data';\n",
-              "          await google.colab.output.renderOutput(dataTable, element);\n",
-              "          const docLink = document.createElement('div');\n",
-              "          docLink.innerHTML = docLinkHtml;\n",
-              "          element.appendChild(docLink);\n",
-              "        }\n",
-              "      </script>\n",
-              "    </div>\n",
-              "  </div>\n",
-              "  "
-            ]
-          },
-          "metadata": {},
-          "execution_count": 20
-        }
-      ],
-      "source": [
-        "nac_edad_madre = nac_edad_madre.groupby([\"anio\",\"edad_madre_grupo\"]).sum()\n",
-        "nac_edad_madre.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "AO6pJxA6EIKF"
-      },
-      "source": [
-        "La información como está no puede ser graficada, ya que está toda junta en 2 grupos, asi que usamos la función .unstack(), que despliega la información para que se puede visualizar"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 269
-        },
-        "id": "l13_EjwlEWhK",
-        "outputId": "b6f1b498-b439-4a85-9049-5d09dadb6520"
-      },
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "                 nacimientos_cantidad                                          \\\n",
-              "edad_madre_grupo          Menor de 15 15 a 19 20 a 24 25 a 29 30 a 34 35 a 39   \n",
-              "anio                                                                            \n",
-              "2005                             2699  104410  177813  182778  141689   73194   \n",
-              "2006                             2766  103885  174342  176931  139003   73177   \n",
-              "2007                             2841  106720  174679  175632  139393   73532   \n",
-              "2008                             2937  112034  183265  184978  153805   80258   \n",
-              "2009                             3346  113478  182747  178935  155464   81397   \n",
-              "\n",
-              "                                      \n",
-              "edad_madre_grupo 40 a 44 De 45 y más  \n",
-              "anio                                  \n",
-              "2005               21382        1575  \n",
-              "2006               19866        1488  \n",
-              "2007               19879        1497  \n",
-              "2008               20824        1630  \n",
-              "2009               20840        1546  "
-            ],
-            "text/html": [
-              "\n",
-              "  <div id=\"df-324c2049-af8b-4e4b-8023-7751f69c2aa9\">\n",
-              "    <div class=\"colab-df-container\">\n",
-              "      <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 tr th {\n",
-              "        text-align: left;\n",
-              "    }\n",
-              "\n",
-              "    .dataframe thead tr:last-of-type th {\n",
-              "        text-align: right;\n",
-              "    }\n",
-              "</style>\n",
-              "<table border=\"1\" class=\"dataframe\">\n",
-              "  <thead>\n",
-              "    <tr>\n",
-              "      <th></th>\n",
-              "      <th colspan=\"8\" halign=\"left\">nacimientos_cantidad</th>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>edad_madre_grupo</th>\n",
-              "      <th>Menor de 15</th>\n",
-              "      <th>15 a 19</th>\n",
-              "      <th>20 a 24</th>\n",
-              "      <th>25 a 29</th>\n",
-              "      <th>30 a 34</th>\n",
-              "      <th>35 a 39</th>\n",
-              "      <th>40 a 44</th>\n",
-              "      <th>De 45 y más</th>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>anio</th>\n",
-              "      <th></th>\n",
-              "      <th></th>\n",
-              "      <th></th>\n",
-              "      <th></th>\n",
-              "      <th></th>\n",
-              "      <th></th>\n",
-              "      <th></th>\n",
-              "      <th></th>\n",
-              "    </tr>\n",
-              "  </thead>\n",
-              "  <tbody>\n",
-              "    <tr>\n",
-              "      <th>2005</th>\n",
-              "      <td>2699</td>\n",
-              "      <td>104410</td>\n",
-              "      <td>177813</td>\n",
-              "      <td>182778</td>\n",
-              "      <td>141689</td>\n",
-              "      <td>73194</td>\n",
-              "      <td>21382</td>\n",
-              "      <td>1575</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>2006</th>\n",
-              "      <td>2766</td>\n",
-              "      <td>103885</td>\n",
-              "      <td>174342</td>\n",
-              "      <td>176931</td>\n",
-              "      <td>139003</td>\n",
-              "      <td>73177</td>\n",
-              "      <td>19866</td>\n",
-              "      <td>1488</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>2007</th>\n",
-              "      <td>2841</td>\n",
-              "      <td>106720</td>\n",
-              "      <td>174679</td>\n",
-              "      <td>175632</td>\n",
-              "      <td>139393</td>\n",
-              "      <td>73532</td>\n",
-              "      <td>19879</td>\n",
-              "      <td>1497</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>2008</th>\n",
-              "      <td>2937</td>\n",
-              "      <td>112034</td>\n",
-              "      <td>183265</td>\n",
-              "      <td>184978</td>\n",
-              "      <td>153805</td>\n",
-              "      <td>80258</td>\n",
-              "      <td>20824</td>\n",
-              "      <td>1630</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>2009</th>\n",
-              "      <td>3346</td>\n",
-              "      <td>113478</td>\n",
-              "      <td>182747</td>\n",
-              "      <td>178935</td>\n",
-              "      <td>155464</td>\n",
-              "      <td>81397</td>\n",
-              "      <td>20840</td>\n",
-              "      <td>1546</td>\n",
-              "    </tr>\n",
-              "  </tbody>\n",
-              "</table>\n",
-              "</div>\n",
-              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-324c2049-af8b-4e4b-8023-7751f69c2aa9')\"\n",
-              "              title=\"Convert this dataframe to an interactive table.\"\n",
-              "              style=\"display:none;\">\n",
-              "        \n",
-              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
-              "       width=\"24px\">\n",
-              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
-              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
-              "  </svg>\n",
-              "      </button>\n",
-              "      \n",
-              "  <style>\n",
-              "    .colab-df-container {\n",
-              "      display:flex;\n",
-              "      flex-wrap:wrap;\n",
-              "      gap: 12px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert {\n",
-              "      background-color: #E8F0FE;\n",
-              "      border: none;\n",
-              "      border-radius: 50%;\n",
-              "      cursor: pointer;\n",
-              "      display: none;\n",
-              "      fill: #1967D2;\n",
-              "      height: 32px;\n",
-              "      padding: 0 0 0 0;\n",
-              "      width: 32px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert:hover {\n",
-              "      background-color: #E2EBFA;\n",
-              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
-              "      fill: #174EA6;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert {\n",
-              "      background-color: #3B4455;\n",
-              "      fill: #D2E3FC;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert:hover {\n",
-              "      background-color: #434B5C;\n",
-              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
-              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
-              "      fill: #FFFFFF;\n",
-              "    }\n",
-              "  </style>\n",
-              "\n",
-              "      <script>\n",
-              "        const buttonEl =\n",
-              "          document.querySelector('#df-324c2049-af8b-4e4b-8023-7751f69c2aa9 button.colab-df-convert');\n",
-              "        buttonEl.style.display =\n",
-              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
-              "\n",
-              "        async function convertToInteractive(key) {\n",
-              "          const element = document.querySelector('#df-324c2049-af8b-4e4b-8023-7751f69c2aa9');\n",
-              "          const dataTable =\n",
-              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
-              "                                                     [key], {});\n",
-              "          if (!dataTable) return;\n",
-              "\n",
-              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
-              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
-              "            + ' to learn more about interactive tables.';\n",
-              "          element.innerHTML = '';\n",
-              "          dataTable['output_type'] = 'display_data';\n",
-              "          await google.colab.output.renderOutput(dataTable, element);\n",
-              "          const docLink = document.createElement('div');\n",
-              "          docLink.innerHTML = docLinkHtml;\n",
-              "          element.appendChild(docLink);\n",
-              "        }\n",
-              "      </script>\n",
-              "    </div>\n",
-              "  </div>\n",
-              "  "
-            ]
-          },
-          "metadata": {},
-          "execution_count": 21
-        }
-      ],
-      "source": [
-        "nac_edad_madre = nac_edad_madre.unstack()\n",
-        "nac_edad_madre.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "tNJtFS-WEc0l"
-      },
-      "source": [
-        "Finalmente graficamos como en los ejemplos anteriores, con la diferencia de que ahora hay varios grupos lo que nos da varias líneas. No existe el mismo problema del eje y ya que ciertos grupos tienen muy pocos nacimientos y esto hace que el eje empiece en 0:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 894
-        },
-        "id": "o6puSivZDjIQ",
-        "outputId": "5f231d70-edcc-4eae-b7e2-91bd01715eba"
-      },
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "<matplotlib.legend.Legend at 0x7fa99f5fd550>"
-            ]
-          },
-          "metadata": {},
-          "execution_count": 22
-        },
-        {
-          "output_type": "display_data",
-          "data": {
-            "text/plain": [
-              "<Figure size 2160x1080 with 1 Axes>"
-            ],
-            "image/png": "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\n"
-          },
-          "metadata": {
-            "needs_background": "light"
-          }
-        }
-      ],
-      "source": [
-        "nac_edad_madre.plot(kind= \"line\",figsize= (30,15),grid=True)\n",
-        "plt.legend([\"Menor de 15\", \"15 a 19\", \"20 a 24\", \"25 a 29\", \"30 a 34\", \"35 a 39\", \"40 a 44\", \"De 45 y más\"])"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "bPtagRwyz4t4"
-      },
-      "source": [
-        "## Pregunta: ¿Que proporción de madres tuvo hijos antes de los 20? <a name=\"paragraph4\"></a>\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "BoE73R4ysDwD"
-      },
-      "source": [
-        "Igual que los ejemplos anteriores, obtenemos las columnas de interés. Pero si consultamos cuáles son los valores únicos que tiene la columna \"edad_madre:grupo\" nos encontramos con filas que no tienen información significativa"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "s_CVX6d0sDwD",
-        "outputId": "96f454ce-3d71-4621-8f0f-b8f5bd69f9aa"
-      },
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "array(['30 a 34', '25 a 29', '20 a 24', '15 a 19', 'Sin especificar',\n",
-              "       '40 a 44', 'De 45 y más', ' Menor de 15', '35 a 39'], dtype=object)"
-            ]
-          },
-          "metadata": {},
-          "execution_count": 11
-        }
-      ],
-      "source": [
-        "nac_madre_menor_20 = nacimientos[[\"edad_madre_grupo\",\"nacimientos_cantidad\"]]\n",
-        "nac_madre_menor_20[\"edad_madre_grupo\"].unique()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "l_yNY0RXsDwD"
-      },
-      "source": [
-        "Eliminamos las filas que dicen 'Sin especificar' "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "lzOk-dbysDwD"
-      },
-      "outputs": [],
-      "source": [
-        "nac_madre_menor_20 = nac_madre_menor_20.drop(nac_madre_menor_20[nac_madre_menor_20['edad_madre_grupo'] == \"Sin especificar\"].index)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 265
-        },
-        "id": "9K-2RWhcsDwD",
-        "outputId": "6b4de7ce-be2c-47ff-b43f-e392d3deb8cf"
-      },
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "<matplotlib.axes._subplots.AxesSubplot at 0x7fa9a1378810>"
-            ]
-          },
-          "metadata": {},
-          "execution_count": 13
-        },
-        {
-          "output_type": "display_data",
-          "data": {
-            "text/plain": [
-              "<Figure size 432x288 with 1 Axes>"
-            ],
-            "image/png": "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\n"
-          },
-          "metadata": {}
-        }
-      ],
-      "source": [
-        "nac_madre_menor_20.groupby(\"edad_madre_grupo\")[\"nacimientos_cantidad\"].count().plot(kind='pie')"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "Gyor1fguGMyw"
-      },
-      "source": [
-        "Luego agrupamos los nacimientos en dos categorías, basado en si cumple o no la condición: Si está en los grupos \" Menor de 15\" o \"15 a 19\", ponerlos en un  grupo, sino en otro grupo. (la | es el equivalente a un \"o\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "KzbpAR3kGMPo"
-      },
-      "outputs": [],
-      "source": [
-        "nac_madre_menor_20 = nac_madre_menor_20.groupby(\n",
-        "                        (nac_madre_menor_20.edad_madre_grupo == \" Menor de 15\") \n",
-        "                        | (nac_madre_menor_20.edad_madre_grupo == \"15 a 19\"))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "a-9-o4q3MGjm"
-      },
-      "source": [
-        "Luego sumamos los nacimientos de cada grupo:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 143
-        },
-        "id": "3HFy7OavMCJU",
-        "outputId": "04da3989-7e63-49d9-d713-25b8744b708c"
-      },
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "                  nacimientos_cantidad\n",
-              "edad_madre_grupo                      \n",
-              "False                          9630285\n",
-              "True                           1657570"
-            ],
-            "text/html": [
-              "\n",
-              "  <div id=\"df-e984a7a8-85d4-4cae-b227-95540334dcb8\">\n",
-              "    <div class=\"colab-df-container\">\n",
-              "      <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>nacimientos_cantidad</th>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>edad_madre_grupo</th>\n",
-              "      <th></th>\n",
-              "    </tr>\n",
-              "  </thead>\n",
-              "  <tbody>\n",
-              "    <tr>\n",
-              "      <th>False</th>\n",
-              "      <td>9630285</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>True</th>\n",
-              "      <td>1657570</td>\n",
-              "    </tr>\n",
-              "  </tbody>\n",
-              "</table>\n",
-              "</div>\n",
-              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-e984a7a8-85d4-4cae-b227-95540334dcb8')\"\n",
-              "              title=\"Convert this dataframe to an interactive table.\"\n",
-              "              style=\"display:none;\">\n",
-              "        \n",
-              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
-              "       width=\"24px\">\n",
-              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
-              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
-              "  </svg>\n",
-              "      </button>\n",
-              "      \n",
-              "  <style>\n",
-              "    .colab-df-container {\n",
-              "      display:flex;\n",
-              "      flex-wrap:wrap;\n",
-              "      gap: 12px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert {\n",
-              "      background-color: #E8F0FE;\n",
-              "      border: none;\n",
-              "      border-radius: 50%;\n",
-              "      cursor: pointer;\n",
-              "      display: none;\n",
-              "      fill: #1967D2;\n",
-              "      height: 32px;\n",
-              "      padding: 0 0 0 0;\n",
-              "      width: 32px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert:hover {\n",
-              "      background-color: #E2EBFA;\n",
-              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
-              "      fill: #174EA6;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert {\n",
-              "      background-color: #3B4455;\n",
-              "      fill: #D2E3FC;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert:hover {\n",
-              "      background-color: #434B5C;\n",
-              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
-              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
-              "      fill: #FFFFFF;\n",
-              "    }\n",
-              "  </style>\n",
-              "\n",
-              "      <script>\n",
-              "        const buttonEl =\n",
-              "          document.querySelector('#df-e984a7a8-85d4-4cae-b227-95540334dcb8 button.colab-df-convert');\n",
-              "        buttonEl.style.display =\n",
-              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
-              "\n",
-              "        async function convertToInteractive(key) {\n",
-              "          const element = document.querySelector('#df-e984a7a8-85d4-4cae-b227-95540334dcb8');\n",
-              "          const dataTable =\n",
-              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
-              "                                                     [key], {});\n",
-              "          if (!dataTable) return;\n",
-              "\n",
-              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
-              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
-              "            + ' to learn more about interactive tables.';\n",
-              "          element.innerHTML = '';\n",
-              "          dataTable['output_type'] = 'display_data';\n",
-              "          await google.colab.output.renderOutput(dataTable, element);\n",
-              "          const docLink = document.createElement('div');\n",
-              "          docLink.innerHTML = docLinkHtml;\n",
-              "          element.appendChild(docLink);\n",
-              "        }\n",
-              "      </script>\n",
-              "    </div>\n",
-              "  </div>\n",
-              "  "
-            ]
-          },
-          "metadata": {},
-          "execution_count": 15
-        }
-      ],
-      "source": [
-        "nac_madre_menor_20 = nac_madre_menor_20.sum()\n",
-        "nac_madre_menor_20.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "UQj6wVmoNjq5"
-      },
-      "source": [
-        "Hay un problema con esta información, en la columna de grupo dece \"True\" y \"False\", esto es por la operación de clasificación de más arriba. Esto se soluciona en el gráfico usando las etiquetas definidas en la lista etiquetas y pasandoselas al gráfico.\n",
-        "\n",
-        "Finalmente, graficamos con un gráfico de torta para mostrar la propoción visualmente, agregando algunas cosas como los porcentajes (con autopct ='%.2f'), el título y el tamaño."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 608
-        },
-        "id": "fNs2UewvS6Bq",
-        "outputId": "693ee5d8-6718-4dfb-cdeb-81b4dcac06ae"
-      },
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "<matplotlib.legend.Legend at 0x7fa99f6b6910>"
-            ]
-          },
-          "metadata": {},
-          "execution_count": 16
-        },
-        {
-          "output_type": "display_data",
-          "data": {
-            "text/plain": [
-              "<Figure size 720x720 with 1 Axes>"
-            ],
-            "image/png": "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\n"
-          },
-          "metadata": {}
-        }
-      ],
-      "source": [
-        "etiquetas= [\"20 o mayor\", \"Menor a 20\"]\n",
-        "nac_madre_menor_20.plot(kind='pie', y='nacimientos_cantidad', figsize=(10, 10),\n",
-        "                          autopct='%.2f',title = \"Proporción de madres tuvo hijos antes de los 20\",\n",
-        "                          labels=etiquetas\n",
-        "                        ,ylabel=\"\")\n",
-        "\n",
-        "plt.legend(etiquetas)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 143
-        },
-        "id": "IiU4eCi_MwbO",
-        "outputId": "6f4a02c6-f291-43e1-f019-3d17288fedf2"
-      },
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "                  nacimientos_cantidad\n",
-              "edad_madre_grupo                      \n",
-              "20 o mayor                     9630285\n",
-              "Menor a 20                     1657570"
-            ],
-            "text/html": [
-              "\n",
-              "  <div id=\"df-420ead63-ee68-474f-9634-9ddad5bd0dec\">\n",
-              "    <div class=\"colab-df-container\">\n",
-              "      <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>nacimientos_cantidad</th>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>edad_madre_grupo</th>\n",
-              "      <th></th>\n",
-              "    </tr>\n",
-              "  </thead>\n",
-              "  <tbody>\n",
-              "    <tr>\n",
-              "      <th>20 o mayor</th>\n",
-              "      <td>9630285</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>Menor a 20</th>\n",
-              "      <td>1657570</td>\n",
-              "    </tr>\n",
-              "  </tbody>\n",
-              "</table>\n",
-              "</div>\n",
-              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-420ead63-ee68-474f-9634-9ddad5bd0dec')\"\n",
-              "              title=\"Convert this dataframe to an interactive table.\"\n",
-              "              style=\"display:none;\">\n",
-              "        \n",
-              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
-              "       width=\"24px\">\n",
-              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
-              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
-              "  </svg>\n",
-              "      </button>\n",
-              "      \n",
-              "  <style>\n",
-              "    .colab-df-container {\n",
-              "      display:flex;\n",
-              "      flex-wrap:wrap;\n",
-              "      gap: 12px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert {\n",
-              "      background-color: #E8F0FE;\n",
-              "      border: none;\n",
-              "      border-radius: 50%;\n",
-              "      cursor: pointer;\n",
-              "      display: none;\n",
-              "      fill: #1967D2;\n",
-              "      height: 32px;\n",
-              "      padding: 0 0 0 0;\n",
-              "      width: 32px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert:hover {\n",
-              "      background-color: #E2EBFA;\n",
-              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
-              "      fill: #174EA6;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert {\n",
-              "      background-color: #3B4455;\n",
-              "      fill: #D2E3FC;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert:hover {\n",
-              "      background-color: #434B5C;\n",
-              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
-              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
-              "      fill: #FFFFFF;\n",
-              "    }\n",
-              "  </style>\n",
-              "\n",
-              "      <script>\n",
-              "        const buttonEl =\n",
-              "          document.querySelector('#df-420ead63-ee68-474f-9634-9ddad5bd0dec button.colab-df-convert');\n",
-              "        buttonEl.style.display =\n",
-              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
-              "\n",
-              "        async function convertToInteractive(key) {\n",
-              "          const element = document.querySelector('#df-420ead63-ee68-474f-9634-9ddad5bd0dec');\n",
-              "          const dataTable =\n",
-              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
-              "                                                     [key], {});\n",
-              "          if (!dataTable) return;\n",
-              "\n",
-              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
-              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
-              "            + ' to learn more about interactive tables.';\n",
-              "          element.innerHTML = '';\n",
-              "          dataTable['output_type'] = 'display_data';\n",
-              "          await google.colab.output.renderOutput(dataTable, element);\n",
-              "          const docLink = document.createElement('div');\n",
-              "          docLink.innerHTML = docLinkHtml;\n",
-              "          element.appendChild(docLink);\n",
-              "        }\n",
-              "      </script>\n",
-              "    </div>\n",
-              "  </div>\n",
-              "  "
-            ]
-          },
-          "metadata": {},
-          "execution_count": 17
-        }
-      ],
-      "source": [
-        "nac_madre_menor_20 = nac_madre_menor_20.rename({True:'Menor a 20',False:'20 o mayor'})\n",
-        "nac_madre_menor_20.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "Jlvd07tY0QyB"
-      },
-      "source": [
-        "##Pregunta: Para cada nivel de instrucción/educación, ¿Cuántos nacimientos hubo en cada grupo etario? <a name=\"paragraph5\"></a>\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "g7S4DRKWT5_Y"
-      },
-      "source": [
-        "Primero obtenemos la información necesaria para responder la pregunta, esta está en las columnas: instruccion_madre , edad_madre_grupo y nacimientos_cantidad"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 206
-        },
-        "id": "eqcTPtN1TPxQ",
-        "outputId": "0a6a59d4-cb61-4657-8c36-b8b72b311aa7"
-      },
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "                 instruccion_madre edad_madre_grupo  nacimientos_cantidad\n",
-              "0  Secundaria/Polimodal Incompleta          30 a 34                     1\n",
-              "1         Primaria/C. EGB Completa          30 a 34                     2\n",
-              "2    Secundaria/Polimodal Completa          25 a 29                     6\n",
-              "3  Secundaria/Polimodal Incompleta          30 a 34                     5\n",
-              "4    Secundaria/Polimodal Completa          25 a 29                     1"
-            ],
-            "text/html": [
-              "\n",
-              "  <div id=\"df-c0786fa3-468f-4bbe-ad4b-98c1713d13a3\">\n",
-              "    <div class=\"colab-df-container\">\n",
-              "      <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>instruccion_madre</th>\n",
-              "      <th>edad_madre_grupo</th>\n",
-              "      <th>nacimientos_cantidad</th>\n",
-              "    </tr>\n",
-              "  </thead>\n",
-              "  <tbody>\n",
-              "    <tr>\n",
-              "      <th>0</th>\n",
-              "      <td>Secundaria/Polimodal Incompleta</td>\n",
-              "      <td>30 a 34</td>\n",
-              "      <td>1</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>1</th>\n",
-              "      <td>Primaria/C. EGB Completa</td>\n",
-              "      <td>30 a 34</td>\n",
-              "      <td>2</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>2</th>\n",
-              "      <td>Secundaria/Polimodal Completa</td>\n",
-              "      <td>25 a 29</td>\n",
-              "      <td>6</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>3</th>\n",
-              "      <td>Secundaria/Polimodal Incompleta</td>\n",
-              "      <td>30 a 34</td>\n",
-              "      <td>5</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>4</th>\n",
-              "      <td>Secundaria/Polimodal Completa</td>\n",
-              "      <td>25 a 29</td>\n",
-              "      <td>1</td>\n",
-              "    </tr>\n",
-              "  </tbody>\n",
-              "</table>\n",
-              "</div>\n",
-              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-c0786fa3-468f-4bbe-ad4b-98c1713d13a3')\"\n",
-              "              title=\"Convert this dataframe to an interactive table.\"\n",
-              "              style=\"display:none;\">\n",
-              "        \n",
-              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
-              "       width=\"24px\">\n",
-              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
-              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
-              "  </svg>\n",
-              "      </button>\n",
-              "      \n",
-              "  <style>\n",
-              "    .colab-df-container {\n",
-              "      display:flex;\n",
-              "      flex-wrap:wrap;\n",
-              "      gap: 12px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert {\n",
-              "      background-color: #E8F0FE;\n",
-              "      border: none;\n",
-              "      border-radius: 50%;\n",
-              "      cursor: pointer;\n",
-              "      display: none;\n",
-              "      fill: #1967D2;\n",
-              "      height: 32px;\n",
-              "      padding: 0 0 0 0;\n",
-              "      width: 32px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert:hover {\n",
-              "      background-color: #E2EBFA;\n",
-              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
-              "      fill: #174EA6;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert {\n",
-              "      background-color: #3B4455;\n",
-              "      fill: #D2E3FC;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert:hover {\n",
-              "      background-color: #434B5C;\n",
-              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
-              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
-              "      fill: #FFFFFF;\n",
-              "    }\n",
-              "  </style>\n",
-              "\n",
-              "      <script>\n",
-              "        const buttonEl =\n",
-              "          document.querySelector('#df-c0786fa3-468f-4bbe-ad4b-98c1713d13a3 button.colab-df-convert');\n",
-              "        buttonEl.style.display =\n",
-              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
-              "\n",
-              "        async function convertToInteractive(key) {\n",
-              "          const element = document.querySelector('#df-c0786fa3-468f-4bbe-ad4b-98c1713d13a3');\n",
-              "          const dataTable =\n",
-              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
-              "                                                     [key], {});\n",
-              "          if (!dataTable) return;\n",
-              "\n",
-              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
-              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
-              "            + ' to learn more about interactive tables.';\n",
-              "          element.innerHTML = '';\n",
-              "          dataTable['output_type'] = 'display_data';\n",
-              "          await google.colab.output.renderOutput(dataTable, element);\n",
-              "          const docLink = document.createElement('div');\n",
-              "          docLink.innerHTML = docLinkHtml;\n",
-              "          element.appendChild(docLink);\n",
-              "        }\n",
-              "      </script>\n",
-              "    </div>\n",
-              "  </div>\n",
-              "  "
-            ]
-          },
-          "metadata": {},
-          "execution_count": 23
-        }
-      ],
-      "source": [
-        "nac_edad_edu_madre= nacimientos[[\"instruccion_madre\",\"edad_madre_grupo\",\"nacimientos_cantidad\"]]\n",
-        "nac_edad_edu_madre.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "4rh4mxCDT5GQ"
-      },
-      "source": [
-        "Como en la pregunta anterior hay dos campos que tienen \"sin especificar\", los ignoramos:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 293
-        },
-        "id": "don6Rac5TPkY",
-        "outputId": "22dbe015-1964-4d0e-8b9a-db15f7414c6c"
-      },
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stderr",
-          "text": [
-            "/usr/local/lib/python3.7/dist-packages/pandas/core/frame.py:4913: SettingWithCopyWarning: \n",
-            "A value is trying to be set on a copy of a slice from a DataFrame\n",
-            "\n",
-            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
-            "  errors=errors,\n"
-          ]
-        },
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "                 instruccion_madre edad_madre_grupo  nacimientos_cantidad\n",
-              "0  Secundaria/Polimodal Incompleta          30 a 34                     1\n",
-              "1         Primaria/C. EGB Completa          30 a 34                     2\n",
-              "2    Secundaria/Polimodal Completa          25 a 29                     6\n",
-              "3  Secundaria/Polimodal Incompleta          30 a 34                     5\n",
-              "4    Secundaria/Polimodal Completa          25 a 29                     1"
-            ],
-            "text/html": [
-              "\n",
-              "  <div id=\"df-3ae2024c-d73e-4a09-8dd4-6af7330b534a\">\n",
-              "    <div class=\"colab-df-container\">\n",
-              "      <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>instruccion_madre</th>\n",
-              "      <th>edad_madre_grupo</th>\n",
-              "      <th>nacimientos_cantidad</th>\n",
-              "    </tr>\n",
-              "  </thead>\n",
-              "  <tbody>\n",
-              "    <tr>\n",
-              "      <th>0</th>\n",
-              "      <td>Secundaria/Polimodal Incompleta</td>\n",
-              "      <td>30 a 34</td>\n",
-              "      <td>1</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>1</th>\n",
-              "      <td>Primaria/C. EGB Completa</td>\n",
-              "      <td>30 a 34</td>\n",
-              "      <td>2</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>2</th>\n",
-              "      <td>Secundaria/Polimodal Completa</td>\n",
-              "      <td>25 a 29</td>\n",
-              "      <td>6</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>3</th>\n",
-              "      <td>Secundaria/Polimodal Incompleta</td>\n",
-              "      <td>30 a 34</td>\n",
-              "      <td>5</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>4</th>\n",
-              "      <td>Secundaria/Polimodal Completa</td>\n",
-              "      <td>25 a 29</td>\n",
-              "      <td>1</td>\n",
-              "    </tr>\n",
-              "  </tbody>\n",
-              "</table>\n",
-              "</div>\n",
-              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-3ae2024c-d73e-4a09-8dd4-6af7330b534a')\"\n",
-              "              title=\"Convert this dataframe to an interactive table.\"\n",
-              "              style=\"display:none;\">\n",
-              "        \n",
-              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
-              "       width=\"24px\">\n",
-              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
-              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
-              "  </svg>\n",
-              "      </button>\n",
-              "      \n",
-              "  <style>\n",
-              "    .colab-df-container {\n",
-              "      display:flex;\n",
-              "      flex-wrap:wrap;\n",
-              "      gap: 12px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert {\n",
-              "      background-color: #E8F0FE;\n",
-              "      border: none;\n",
-              "      border-radius: 50%;\n",
-              "      cursor: pointer;\n",
-              "      display: none;\n",
-              "      fill: #1967D2;\n",
-              "      height: 32px;\n",
-              "      padding: 0 0 0 0;\n",
-              "      width: 32px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert:hover {\n",
-              "      background-color: #E2EBFA;\n",
-              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
-              "      fill: #174EA6;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert {\n",
-              "      background-color: #3B4455;\n",
-              "      fill: #D2E3FC;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert:hover {\n",
-              "      background-color: #434B5C;\n",
-              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
-              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
-              "      fill: #FFFFFF;\n",
-              "    }\n",
-              "  </style>\n",
-              "\n",
-              "      <script>\n",
-              "        const buttonEl =\n",
-              "          document.querySelector('#df-3ae2024c-d73e-4a09-8dd4-6af7330b534a button.colab-df-convert');\n",
-              "        buttonEl.style.display =\n",
-              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
-              "\n",
-              "        async function convertToInteractive(key) {\n",
-              "          const element = document.querySelector('#df-3ae2024c-d73e-4a09-8dd4-6af7330b534a');\n",
-              "          const dataTable =\n",
-              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
-              "                                                     [key], {});\n",
-              "          if (!dataTable) return;\n",
-              "\n",
-              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
-              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
-              "            + ' to learn more about interactive tables.';\n",
-              "          element.innerHTML = '';\n",
-              "          dataTable['output_type'] = 'display_data';\n",
-              "          await google.colab.output.renderOutput(dataTable, element);\n",
-              "          const docLink = document.createElement('div');\n",
-              "          docLink.innerHTML = docLinkHtml;\n",
-              "          element.appendChild(docLink);\n",
-              "        }\n",
-              "      </script>\n",
-              "    </div>\n",
-              "  </div>\n",
-              "  "
-            ]
-          },
-          "metadata": {},
-          "execution_count": 24
-        }
-      ],
-      "source": [
-        "nac_edad_edu_madre.drop(nac_edad_edu_madre.index[nac_edad_edu_madre['edad_madre_grupo'] == \"Sin especificar\"], inplace = True)\n",
-        "nac_edad_edu_madre.drop(nac_edad_edu_madre.index[nac_edad_edu_madre['instruccion_madre'] == \"Sin especificar\"], inplace = True)\n",
-        "nac_edad_edu_madre.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "jZRnk0HlT6ch"
-      },
-      "source": [
-        "Agrupamos por instrucción/educación de la madre y grupo etario, luego se suma la cantidad de nacimientos por esas categorías:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 238
-        },
-        "id": "0oQCwFn2TSd5",
-        "outputId": "624b8961-5a22-45cf-bdd5-28b1fa351270"
-      },
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "                                           nacimientos_cantidad\n",
-              "instruccion_madre        edad_madre_grupo                      \n",
-              "Primaria/C. EGB Completa  Menor de 15                     13561\n",
-              "                         15 a 19                         447330\n",
-              "                         20 a 24                         687506\n",
-              "                         25 a 29                         594204\n",
-              "                         30 a 34                         449616"
-            ],
-            "text/html": [
-              "\n",
-              "  <div id=\"df-6f28fa94-840e-4c1d-8b6a-97a2f83b3d9c\">\n",
-              "    <div class=\"colab-df-container\">\n",
-              "      <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></th>\n",
-              "      <th>nacimientos_cantidad</th>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>instruccion_madre</th>\n",
-              "      <th>edad_madre_grupo</th>\n",
-              "      <th></th>\n",
-              "    </tr>\n",
-              "  </thead>\n",
-              "  <tbody>\n",
-              "    <tr>\n",
-              "      <th rowspan=\"5\" valign=\"top\">Primaria/C. EGB Completa</th>\n",
-              "      <th>Menor de 15</th>\n",
-              "      <td>13561</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>15 a 19</th>\n",
-              "      <td>447330</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>20 a 24</th>\n",
-              "      <td>687506</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>25 a 29</th>\n",
-              "      <td>594204</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>30 a 34</th>\n",
-              "      <td>449616</td>\n",
-              "    </tr>\n",
-              "  </tbody>\n",
-              "</table>\n",
-              "</div>\n",
-              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-6f28fa94-840e-4c1d-8b6a-97a2f83b3d9c')\"\n",
-              "              title=\"Convert this dataframe to an interactive table.\"\n",
-              "              style=\"display:none;\">\n",
-              "        \n",
-              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
-              "       width=\"24px\">\n",
-              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
-              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
-              "  </svg>\n",
-              "      </button>\n",
-              "      \n",
-              "  <style>\n",
-              "    .colab-df-container {\n",
-              "      display:flex;\n",
-              "      flex-wrap:wrap;\n",
-              "      gap: 12px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert {\n",
-              "      background-color: #E8F0FE;\n",
-              "      border: none;\n",
-              "      border-radius: 50%;\n",
-              "      cursor: pointer;\n",
-              "      display: none;\n",
-              "      fill: #1967D2;\n",
-              "      height: 32px;\n",
-              "      padding: 0 0 0 0;\n",
-              "      width: 32px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert:hover {\n",
-              "      background-color: #E2EBFA;\n",
-              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
-              "      fill: #174EA6;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert {\n",
-              "      background-color: #3B4455;\n",
-              "      fill: #D2E3FC;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert:hover {\n",
-              "      background-color: #434B5C;\n",
-              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
-              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
-              "      fill: #FFFFFF;\n",
-              "    }\n",
-              "  </style>\n",
-              "\n",
-              "      <script>\n",
-              "        const buttonEl =\n",
-              "          document.querySelector('#df-6f28fa94-840e-4c1d-8b6a-97a2f83b3d9c button.colab-df-convert');\n",
-              "        buttonEl.style.display =\n",
-              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
-              "\n",
-              "        async function convertToInteractive(key) {\n",
-              "          const element = document.querySelector('#df-6f28fa94-840e-4c1d-8b6a-97a2f83b3d9c');\n",
-              "          const dataTable =\n",
-              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
-              "                                                     [key], {});\n",
-              "          if (!dataTable) return;\n",
-              "\n",
-              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
-              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
-              "            + ' to learn more about interactive tables.';\n",
-              "          element.innerHTML = '';\n",
-              "          dataTable['output_type'] = 'display_data';\n",
-              "          await google.colab.output.renderOutput(dataTable, element);\n",
-              "          const docLink = document.createElement('div');\n",
-              "          docLink.innerHTML = docLinkHtml;\n",
-              "          element.appendChild(docLink);\n",
-              "        }\n",
-              "      </script>\n",
-              "    </div>\n",
-              "  </div>\n",
-              "  "
-            ]
-          },
-          "metadata": {},
-          "execution_count": 25
-        }
-      ],
-      "source": [
-        "nac_edad_edu_madre = nac_edad_edu_madre.groupby([\"instruccion_madre\",\"edad_madre_grupo\"]).sum()\n",
-        "nac_edad_edu_madre.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "n9cVIZ3pT6yI"
-      },
-      "source": [
-        "Como agrupamos por dos categorías usamos unstack para graficar los datos más facilmente:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 269
-        },
-        "id": "hHta7iM9T0B2",
-        "outputId": "e5b7b688-1dd0-44d1-d21a-b8a3517b428b"
-      },
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "                                nacimientos_cantidad                          \\\n",
-              "edad_madre_grupo                         Menor de 15 15 a 19 20 a 24 25 a 29   \n",
-              "instruccion_madre                                                              \n",
-              "Primaria/C. EGB Completa                       13561  447330  687506  594204   \n",
-              "Primaria/C. EGB Incompleta                     13424  171170  172795  128707   \n",
-              "Secundaria/Polimodal Completa                    348  224291  862070  875452   \n",
-              "Secundaria/Polimodal Incompleta                13535  679556  722392  481346   \n",
-              "Sin instrucción                                  455    6851   10413   10255   \n",
-              "\n",
-              "                                                                     \n",
-              "edad_madre_grupo                30 a 34 35 a 39 40 a 44 De 45 y más  \n",
-              "instruccion_madre                                                    \n",
-              "Primaria/C. EGB Completa         449616  271336   87279        6532  \n",
-              "Primaria/C. EGB Incompleta        95095   60494   22362        1998  \n",
-              "Secundaria/Polimodal Completa    655385  334111   80448        5187  \n",
-              "Secundaria/Polimodal Incompleta  305220  160782   44473        2972  \n",
-              "Sin instrucción                    8756    6030    2618         317  "
-            ],
-            "text/html": [
-              "\n",
-              "  <div id=\"df-47f6543f-f112-4253-b4e7-65799cca68be\">\n",
-              "    <div class=\"colab-df-container\">\n",
-              "      <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 tr th {\n",
-              "        text-align: left;\n",
-              "    }\n",
-              "\n",
-              "    .dataframe thead tr:last-of-type th {\n",
-              "        text-align: right;\n",
-              "    }\n",
-              "</style>\n",
-              "<table border=\"1\" class=\"dataframe\">\n",
-              "  <thead>\n",
-              "    <tr>\n",
-              "      <th></th>\n",
-              "      <th colspan=\"8\" halign=\"left\">nacimientos_cantidad</th>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>edad_madre_grupo</th>\n",
-              "      <th>Menor de 15</th>\n",
-              "      <th>15 a 19</th>\n",
-              "      <th>20 a 24</th>\n",
-              "      <th>25 a 29</th>\n",
-              "      <th>30 a 34</th>\n",
-              "      <th>35 a 39</th>\n",
-              "      <th>40 a 44</th>\n",
-              "      <th>De 45 y más</th>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>instruccion_madre</th>\n",
-              "      <th></th>\n",
-              "      <th></th>\n",
-              "      <th></th>\n",
-              "      <th></th>\n",
-              "      <th></th>\n",
-              "      <th></th>\n",
-              "      <th></th>\n",
-              "      <th></th>\n",
-              "    </tr>\n",
-              "  </thead>\n",
-              "  <tbody>\n",
-              "    <tr>\n",
-              "      <th>Primaria/C. EGB Completa</th>\n",
-              "      <td>13561</td>\n",
-              "      <td>447330</td>\n",
-              "      <td>687506</td>\n",
-              "      <td>594204</td>\n",
-              "      <td>449616</td>\n",
-              "      <td>271336</td>\n",
-              "      <td>87279</td>\n",
-              "      <td>6532</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>Primaria/C. EGB Incompleta</th>\n",
-              "      <td>13424</td>\n",
-              "      <td>171170</td>\n",
-              "      <td>172795</td>\n",
-              "      <td>128707</td>\n",
-              "      <td>95095</td>\n",
-              "      <td>60494</td>\n",
-              "      <td>22362</td>\n",
-              "      <td>1998</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>Secundaria/Polimodal Completa</th>\n",
-              "      <td>348</td>\n",
-              "      <td>224291</td>\n",
-              "      <td>862070</td>\n",
-              "      <td>875452</td>\n",
-              "      <td>655385</td>\n",
-              "      <td>334111</td>\n",
-              "      <td>80448</td>\n",
-              "      <td>5187</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>Secundaria/Polimodal Incompleta</th>\n",
-              "      <td>13535</td>\n",
-              "      <td>679556</td>\n",
-              "      <td>722392</td>\n",
-              "      <td>481346</td>\n",
-              "      <td>305220</td>\n",
-              "      <td>160782</td>\n",
-              "      <td>44473</td>\n",
-              "      <td>2972</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>Sin instrucción</th>\n",
-              "      <td>455</td>\n",
-              "      <td>6851</td>\n",
-              "      <td>10413</td>\n",
-              "      <td>10255</td>\n",
-              "      <td>8756</td>\n",
-              "      <td>6030</td>\n",
-              "      <td>2618</td>\n",
-              "      <td>317</td>\n",
-              "    </tr>\n",
-              "  </tbody>\n",
-              "</table>\n",
-              "</div>\n",
-              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-47f6543f-f112-4253-b4e7-65799cca68be')\"\n",
-              "              title=\"Convert this dataframe to an interactive table.\"\n",
-              "              style=\"display:none;\">\n",
-              "        \n",
-              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
-              "       width=\"24px\">\n",
-              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
-              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
-              "  </svg>\n",
-              "      </button>\n",
-              "      \n",
-              "  <style>\n",
-              "    .colab-df-container {\n",
-              "      display:flex;\n",
-              "      flex-wrap:wrap;\n",
-              "      gap: 12px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert {\n",
-              "      background-color: #E8F0FE;\n",
-              "      border: none;\n",
-              "      border-radius: 50%;\n",
-              "      cursor: pointer;\n",
-              "      display: none;\n",
-              "      fill: #1967D2;\n",
-              "      height: 32px;\n",
-              "      padding: 0 0 0 0;\n",
-              "      width: 32px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert:hover {\n",
-              "      background-color: #E2EBFA;\n",
-              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
-              "      fill: #174EA6;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert {\n",
-              "      background-color: #3B4455;\n",
-              "      fill: #D2E3FC;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert:hover {\n",
-              "      background-color: #434B5C;\n",
-              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
-              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
-              "      fill: #FFFFFF;\n",
-              "    }\n",
-              "  </style>\n",
-              "\n",
-              "      <script>\n",
-              "        const buttonEl =\n",
-              "          document.querySelector('#df-47f6543f-f112-4253-b4e7-65799cca68be button.colab-df-convert');\n",
-              "        buttonEl.style.display =\n",
-              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
-              "\n",
-              "        async function convertToInteractive(key) {\n",
-              "          const element = document.querySelector('#df-47f6543f-f112-4253-b4e7-65799cca68be');\n",
-              "          const dataTable =\n",
-              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
-              "                                                     [key], {});\n",
-              "          if (!dataTable) return;\n",
-              "\n",
-              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
-              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
-              "            + ' to learn more about interactive tables.';\n",
-              "          element.innerHTML = '';\n",
-              "          dataTable['output_type'] = 'display_data';\n",
-              "          await google.colab.output.renderOutput(dataTable, element);\n",
-              "          const docLink = document.createElement('div');\n",
-              "          docLink.innerHTML = docLinkHtml;\n",
-              "          element.appendChild(docLink);\n",
-              "        }\n",
-              "      </script>\n",
-              "    </div>\n",
-              "  </div>\n",
-              "  "
-            ]
-          },
-          "metadata": {},
-          "execution_count": 26
-        }
-      ],
-      "source": [
-        "nac_edad_edu_madre = nac_edad_edu_madre.unstack()\n",
-        "nac_edad_edu_madre.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "YIh4bD50T7VR"
-      },
-      "source": [
-        "Finalmente graficamos con un gáfico de barras, donde cada grupo corresponde a un nivel de educación y cada barra a un grupo etario, mientras más alta la barra, más nacimientos. También agregamos un título y la leyenda:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 946
-        },
-        "id": "bf6v9x7gAwku",
-        "outputId": "d76f0e80-b08b-4590-e897-1a067fcccb60"
-      },
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "<matplotlib.legend.Legend at 0x7fa99f5a3150>"
-            ]
-          },
-          "metadata": {},
-          "execution_count": 27
-        },
-        {
-          "output_type": "display_data",
-          "data": {
-            "text/plain": [
-              "<Figure size 1800x936 with 1 Axes>"
-            ],
-            "image/png": "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\n"
-          },
-          "metadata": {
-            "needs_background": "light"
-          }
-        }
-      ],
-      "source": [
-        "nac_edad_edu_madre.plot.bar(figsize= (25,13),xlabel=\"\",title = \"Cantidad de nacimientos por grupo etario y educación de la madre\",grid=True)\n",
-        "plt.legend([\"Menor de 15\", \"15 a 19\", \"20 a 24\", \"25 a 29\", \"30 a 34\", \"35 a 39\", \"40 a 44\", \"De 45 y más\"])"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        ""
-      ],
-      "metadata": {
-        "id": "mqrIQcbnDVGQ"
-      }
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "# Referencias técnicas <a name=\"paragraph6\"></a>"
-      ],
-      "metadata": {
-        "id": "dPsfdz_yEXOq"
-      }
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "HusbZdgnsDv0"
-      },
-      "source": [
-        "\n",
-        "---\n",
-        "Este es un apartado más técnico sobre las funciones que se ven en la demostración\n",
-        "---\n",
-        "El lenguaje de programación que estamos utilizando es **Python**, un lenguaje muy popular para ciencia de datos, combinado con la librería *pandas*, también muy popular, ya que nos permite manejar los datos fácilmente y finalmente usamos *matplotlib* para graficar los datos.\n",
-        "\n",
-        "Pandas trabaja con dataframes, estos son la estructura básica que vamos a manipular y funcionan como una tabla con filas y columnas.\n",
-        "\n",
-        "\n",
-        "\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "---\n",
-        "## Funciones importantes\n",
-        "---\n",
-        "A lo largo de esta demostración vamos a usar 7 funciones principales:"
-      ],
-      "metadata": {
-        "id": "osqzdhscEsR4"
-      }
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "### head:\n",
-        "Esta función nos permite ver las primeras 5 filas de un dataframe, además de los nombres de columnas. Es muy útil para visualizar una operación."
-      ],
-      "metadata": {
-        "id": "Jlkc7qhmEiGN"
-      }
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "xa6NE0LLsDv5"
-      },
-      "source": [
-        "\n",
-        "### groupby\n",
-        "\n",
-        "Esta potente función, nos permite agrupar nuestra información basados en los valores de una columna y luego realizar operaciones con esos grupos.\n",
-        "\n",
-        "\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ZYFkU_DLsDv6"
-      },
-      "source": [
-        "### sum\n",
-        "Nos permite sumar los valores de un conjunto de datos, columna, fila, o en nuestro caso de los grupos de un groupby.\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "LhFsPjissDv7"
-      },
-      "source": [
-        "\n",
-        "### drop\n",
-        "Esta función nos permite eliminar filas de un dataframe, hay que indicarle una condición para seleccionar cuales se borran.\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "XwrmQ5MGsDv7"
-      },
-      "source": [
-        "\n",
-        "### plot\n",
-        "Nos permite graficar los datos de un dataframe, le indicamos el tipo de gráfico con la instrucción *kind*, y tiene otros parámetros para cosas como tamaño, titulo, etc.\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "RC12jKRmsDv7"
-      },
-      "source": [
-        "### plt.legend\n",
-        "Esta función nos permite especificar la leyenda que queremos en nuestro gráfico."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "### unstack\n",
-        "Esta función nos permite desagrupar un dataframe compuesto de dataframes en uno solo con toda la información. Nos sirve para graficar datos que requieren de agrupación por más de una categoría."
-      ],
-      "metadata": {
-        "id": "23uSeoIWPf8K"
-      }
-    }
-  ],
-  "metadata": {
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "8s9_BjAlsDvz"
+   },
+   "source": [
+    "# Indice\n",
+    "1. [Introduction](#introduction)\n",
+    "2. [Preparando la información](#paragraph1)\n",
+    "3. [¿Cuántos nacimientos hay por año en el país?](#paragraph2)\n",
+    "4. [¿Cuántos nacimientos hay por año en el país según el grupo etario de la madre?](#paragraph3)\n",
+    "5. [¿Que proporción de madres tuvo hijos antes de los 20?](#paragraph4)\n",
+    "6. [Para cada nivel de instrucción/educación, ¿Cuántos nacimientos hubo en cada grupo etario?](#paragraph5)\n",
+    "7. [Referencias técnicas](#paragraph6)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "7JgsokQzYAJX"
+   },
+   "source": [
+    "## Introducción <a name=\"introduction\"></a>\n",
+    "\n",
+    "---\n",
+    "En esta propuesta vamos a usar datos del ministerio de salud sobre nacimientos en el país entre 2005 y 2010 para hacer algunas preguntas y obtener una respuesta visual con gráficos.\n",
+    "---\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "fTccwFpMvWpQ"
+   },
+   "source": [
+    "# Qué información podemos obtener:\n",
+    "* ¿Cuántos nacimientos hay por año en el país?\n",
+    "* ¿Cuántos nacimientos hay por año en el país según el grupo etario de la madre?\n",
+    "* ¿Que proporción de madres tuvo hijos antes de los 20?\n",
+    "* Para cada nivel de instrucción/educación, ¿Cuántos nacimientos hubo en cada grupo etario?"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "O35LytWBsDv0"
+   },
+   "source": [
+    "## Link donde obtengo el dataset\n",
+    "El dataset viene del ministerio de salud y puede encontrarse en: \n",
+    "http://datos.salud.gob.ar/dataset/nacidos-vivos-registrados-por-jurisdiccion-de-residencia-de-la-madre-republica-argentina-ano-2017/archivo/3c891522-8448-4490-a7da-6deba78d3b32\n",
+    "Aunque los datos fueron limpiados para facilitar su uso"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "GqUKO6-k2moi"
+   },
+   "source": [
+    "Antes de empezar, una aclaración: En muchos lugares de la ejecución, se puede ver un SettingWithCopyWarning que nos avisa que estamos tratando de colocar una parte de una copia del dataframe en el dataframe. Esto no es un problema y se puede ignorar"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "QYEZLjtwiH6p"
+   },
+   "source": [
+    "## Preparando la información <a name=\"paragraph1\"></a>\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "q-PphAWuE151"
+   },
+   "source": [
+    "Primero importamos pandas, esto nos permitirá usar las funciones que provee, es costumbre renombrarla como **pd** y también el módulo pyplot de matplotlib normalmente abreviado como **plt**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "gSPpdLmni-mZ"
+   },
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "mGIGSZnmiTyN"
+   },
+   "source": [
+    "Usamos la función **read_csv** que nos transforma nuestros datos (en formato csv) a un dataframe que podemos manipular fácilmente."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "oanfaLLOvlVG"
+   },
+   "outputs": [],
+   "source": [
+    "nacimientos = pd.read_csv(\"Nacimientos_Arg_2005-2010.csv\",encoding = \"UTF-8\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "6cuhJ6w2zbUc"
+   },
+   "source": [
+    "Vamos a ver como vemos la información:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
     "colab": {
-      "collapsed_sections": [
-        "O35LytWBsDv0",
-        "QYEZLjtwiH6p",
-        "HY9NHf7Mw2Z8",
-        "_NpC6hVyzwSc",
-        "bPtagRwyz4t4",
-        "Jlvd07tY0QyB"
-      ],
-      "name": "Demo_CDS_nacimientos.ipynb",
-      "provenance": [],
-      "toc_visible": true
-    },
-    "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": "3.10.4"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}
\ No newline at end of file
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "FDFSoh0Xwh3M",
+    "outputId": "39b9b53f-9cda-4c25-adb7-ad0fa8ca0609"
+   },
+   "outputs": [],
+   "source": [
+    "nacimientos.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "B6kS1QTB6aF9"
+   },
+   "source": [
+    "No vamos a trabajar con toda la información, asi que la cortamos a las columnas que nos interesan:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "Z9xxlqmM6kc4"
+   },
+   "outputs": [],
+   "source": [
+    "nacimientos = nacimientos[[\"anio\",\"edad_madre_grupo\",\"instruccion_madre\",\"nacimientos_cantidad\"]]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "4lOR_MP7sDv-",
+    "outputId": "f407388c-6bcd-45fe-e984-96be9affface"
+   },
+   "outputs": [],
+   "source": [
+    "nacimientos"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "HY9NHf7Mw2Z8"
+   },
+   "source": [
+    "## Pregunta: ¿Cuántos nacimientos hay por año en el país? <a name=\"paragraph2\"></a>\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "XJ_i_X3IA5oI"
+   },
+   "source": [
+    "Para esto vamos a necesitar menos información que antes, solo la cantidad de nacimientos y el año en el que ocurrieron.\n",
+    "Se abrevia nacimientos como nac para mayor legibilidad:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 206
+    },
+    "id": "I-PYL_Qez5hV",
+    "outputId": "e0c50fba-5ab8-4d94-989c-65714f666c97"
+   },
+   "outputs": [],
+   "source": [
+    "nac_por_año = nacimientos[[\"anio\",\"nacimientos_cantidad\"]]\n",
+    "nac_por_año.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "D6Dps9axBQrp"
+   },
+   "source": [
+    "Hay un problema con esta información, como la cantidad de nacimientos no está agregada por año sino que también por otros factores, hay que agrupar por año y sumar los nacimientos de cada grupo:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 238
+    },
+    "id": "FbY9_hRmBDuW",
+    "outputId": "2f9f8d43-6014-4f71-abf5-be997855408d"
+   },
+   "outputs": [],
+   "source": [
+    "nac_por_año = nac_por_año.groupby(\"anio\").sum()\n",
+    "nac_por_año.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "xPLMRoEUmicq"
+   },
+   "source": [
+    "Ahora está mejor.\n",
+    "Vamos a graficarlo con un simple gráfico de línea:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 459
+    },
+    "id": "19u3wAvl0jIN",
+    "outputId": "97bf73c5-1a0e-4ed4-d2e2-a7d6c12536e7"
+   },
+   "outputs": [],
+   "source": [
+    "nac_por_año.plot(kind= \"line\",figsize= (15,7),grid=True)\n",
+    "plt.legend([\"Cantidad de nacimientos\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "ef0DL8Gh8jLf"
+   },
+   "source": [
+    "Hay un problema con el gráfico, el eje y no comienza en 0 y hace que el gráfico se vea mal, esto se soluciona indicando el límite inferior de y:\n",
+    "También establecemos la leyenda del gráfico"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 459
+    },
+    "id": "D8TfEws58gvQ",
+    "outputId": "eb6842af-3d5b-40f1-fc04-689461f5abb1"
+   },
+   "outputs": [],
+   "source": [
+    "nac_por_año.plot(kind= \"line\",figsize= (15,7),ylim=(0),grid=True)\n",
+    "plt.legend([\"Cantidad de nacimientos\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "_NpC6hVyzwSc"
+   },
+   "source": [
+    "## Pregunta: ¿Cuántos nacimientos hay por año en el país según el grupo etario de la madre? <a name=\"paragraph3\"></a>\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "IgOe-p4pCly3"
+   },
+   "source": [
+    "En este caso necesitamos saber el año, el grupo etario de la madre y la cantidad:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "glA4XLTT86wg"
+   },
+   "outputs": [],
+   "source": [
+    "nac_edad_madre = nacimientos[[\"anio\",\"edad_madre_grupo\",\"nacimientos_cantidad\"]]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "qCnqL52JC-SA"
+   },
+   "source": [
+    "Hay algunos nacimientos donde el grupo etario de la madre no fue especificado, por lo tanto no podemos sacar conclusiones, asique se ignoran."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "If8D3jpHC93r",
+    "outputId": "073e094d-4b1a-489b-bc72-e76982078ee7"
+   },
+   "outputs": [],
+   "source": [
+    "nac_edad_madre.drop(nac_edad_madre.index[nac_edad_madre['edad_madre_grupo'] == \"Sin especificar\"], inplace = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "ccDvLT5BDpKQ"
+   },
+   "source": [
+    "Ahora con la información filtrada, hay que agrupar por dos criterios, primero por el año y luego por el grupo etario y finalmente sumar las cantidades de estos grupos:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 238
+    },
+    "id": "-iJyxCfUC2SY",
+    "outputId": "292a3e1f-01c5-4907-8876-f7aef2a447b2"
+   },
+   "outputs": [],
+   "source": [
+    "nac_edad_madre = nac_edad_madre.groupby([\"anio\",\"edad_madre_grupo\"]).sum()\n",
+    "nac_edad_madre.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "AO6pJxA6EIKF"
+   },
+   "source": [
+    "La información como está no puede ser graficada, ya que está toda junta en 2 grupos, asi que usamos la función .unstack(), que despliega la información para que se puede visualizar"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 269
+    },
+    "id": "l13_EjwlEWhK",
+    "outputId": "b6f1b498-b439-4a85-9049-5d09dadb6520"
+   },
+   "outputs": [],
+   "source": [
+    "nac_edad_madre = nac_edad_madre.unstack()\n",
+    "nac_edad_madre.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "tNJtFS-WEc0l"
+   },
+   "source": [
+    "Finalmente graficamos como en los ejemplos anteriores, con la diferencia de que ahora hay varios grupos lo que nos da varias líneas. No existe el mismo problema del eje y ya que ciertos grupos tienen muy pocos nacimientos y esto hace que el eje empiece en 0:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 894
+    },
+    "id": "o6puSivZDjIQ",
+    "outputId": "5f231d70-edcc-4eae-b7e2-91bd01715eba",
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "nac_edad_madre.plot(kind= \"line\",figsize= (30,15),grid=True)\n",
+    "plt.legend([\"Menor de 15\", \"15 a 19\", \"20 a 24\", \"25 a 29\", \"30 a 34\", \"35 a 39\", \"40 a 44\", \"De 45 y más\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "¿Cómo reemplazamos datos de  algunas filas?. Por ejemplo si vemos los valores únicos de la columna **Sexo** nos encontramos con dos valores que podríamos unificar"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "nacimientos['Sexo'].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "nacimientos_mod = nacimientos.replace(to_replace=['indeterminado'], value='desconocido')\n",
+    "nacimientos_mod"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Verificamos el cambio realizado:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "nacimientos_mod['Sexo'].unique()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Desafío 1:\n",
+    "Graficar los nacimientos agrupados por sexo y año."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Desafío 2:\n",
+    "Graficar los nacimientos de la provincia de Buenos Aires, agrupados por sexo y año.(Pista: en el primer encuentro filtramos por provincia, en el segundo vimos agrupamientos por varios criterios)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "bPtagRwyz4t4"
+   },
+   "source": [
+    "## Pregunta: ¿Que proporción de madres tuvo hijos antes de los 20? <a name=\"paragraph4\"></a>\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "BoE73R4ysDwD"
+   },
+   "source": [
+    "Igual que los ejemplos anteriores, obtenemos las columnas de interés. Pero si consultamos cuáles son los valores únicos que tiene la columna \"edad_madre:grupo\" nos encontramos con filas que no tienen información significativa"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "s_CVX6d0sDwD",
+    "outputId": "96f454ce-3d71-4621-8f0f-b8f5bd69f9aa"
+   },
+   "outputs": [],
+   "source": [
+    "nac_madre_menor_20 = nacimientos[[\"edad_madre_grupo\",\"nacimientos_cantidad\"]]\n",
+    "nac_madre_menor_20[\"edad_madre_grupo\"].unique()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "l_yNY0RXsDwD"
+   },
+   "source": [
+    "Eliminamos las filas que dicen 'Sin especificar' "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "lzOk-dbysDwD"
+   },
+   "outputs": [],
+   "source": [
+    "nac_madre_menor_20 = nac_madre_menor_20.drop(nac_madre_menor_20[nac_madre_menor_20['edad_madre_grupo'] == \"Sin especificar\"].index)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 265
+    },
+    "id": "9K-2RWhcsDwD",
+    "outputId": "6b4de7ce-be2c-47ff-b43f-e392d3deb8cf"
+   },
+   "outputs": [],
+   "source": [
+    "nac_madre_menor_20.groupby(\"edad_madre_grupo\")[\"nacimientos_cantidad\"].count().plot(kind='pie')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Gyor1fguGMyw"
+   },
+   "source": [
+    "Luego agrupamos los nacimientos en dos categorías, basado en si cumple o no la condición: Si está en los grupos \" Menor de 15\" o \"15 a 19\", ponerlos en un  grupo, sino en otro grupo. (la | es el equivalente a un \"o\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "KzbpAR3kGMPo"
+   },
+   "outputs": [],
+   "source": [
+    "nac_madre_menor_20 = nac_madre_menor_20.groupby(\n",
+    "                        (nac_madre_menor_20.edad_madre_grupo == \" Menor de 15\") \n",
+    "                        | (nac_madre_menor_20.edad_madre_grupo == \"15 a 19\"))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "a-9-o4q3MGjm"
+   },
+   "source": [
+    "Luego sumamos los nacimientos de cada grupo:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 143
+    },
+    "id": "3HFy7OavMCJU",
+    "outputId": "04da3989-7e63-49d9-d713-25b8744b708c"
+   },
+   "outputs": [],
+   "source": [
+    "nac_madre_menor_20 = nac_madre_menor_20.sum()\n",
+    "nac_madre_menor_20.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "UQj6wVmoNjq5"
+   },
+   "source": [
+    "Hay un problema con esta información, en la columna de grupo dece \"True\" y \"False\", esto es por la operación de clasificación de más arriba. Esto se soluciona en el gráfico usando las etiquetas definidas en la lista etiquetas y pasandoselas al gráfico.\n",
+    "\n",
+    "Finalmente, graficamos con un gráfico de torta para mostrar la propoción visualmente, agregando algunas cosas como los porcentajes (con autopct ='%.2f'), el título y el tamaño."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 608
+    },
+    "id": "fNs2UewvS6Bq",
+    "outputId": "693ee5d8-6718-4dfb-cdeb-81b4dcac06ae"
+   },
+   "outputs": [],
+   "source": [
+    "etiquetas= [\"20 o mayor\", \"Menor a 20\"]\n",
+    "nac_madre_menor_20.plot(kind='pie', y='nacimientos_cantidad', figsize=(10, 10),\n",
+    "                          autopct='%.2f',title = \"Proporción de madres tuvo hijos antes de los 20\",\n",
+    "                          labels=etiquetas\n",
+    "                        ,ylabel=\"\")\n",
+    "\n",
+    "plt.legend(etiquetas)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 143
+    },
+    "id": "IiU4eCi_MwbO",
+    "outputId": "6f4a02c6-f291-43e1-f019-3d17288fedf2"
+   },
+   "outputs": [],
+   "source": [
+    "nac_madre_menor_20 = nac_madre_menor_20.rename({True:'Menor a 20',False:'20 o mayor'})\n",
+    "nac_madre_menor_20.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Jlvd07tY0QyB"
+   },
+   "source": [
+    "##Pregunta: Para cada nivel de instrucción/educación, ¿Cuántos nacimientos hubo en cada grupo etario? <a name=\"paragraph5\"></a>\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "g7S4DRKWT5_Y"
+   },
+   "source": [
+    "Primero obtenemos la información necesaria para responder la pregunta, esta está en las columnas: instruccion_madre , edad_madre_grupo y nacimientos_cantidad"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 206
+    },
+    "id": "eqcTPtN1TPxQ",
+    "outputId": "0a6a59d4-cb61-4657-8c36-b8b72b311aa7"
+   },
+   "outputs": [],
+   "source": [
+    "nac_edad_edu_madre= nacimientos[[\"instruccion_madre\",\"edad_madre_grupo\",\"nacimientos_cantidad\"]]\n",
+    "nac_edad_edu_madre.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "4rh4mxCDT5GQ"
+   },
+   "source": [
+    "Como en la pregunta anterior hay dos campos que tienen \"sin especificar\", los ignoramos:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 293
+    },
+    "id": "don6Rac5TPkY",
+    "outputId": "22dbe015-1964-4d0e-8b9a-db15f7414c6c"
+   },
+   "outputs": [],
+   "source": [
+    "nac_edad_edu_madre.drop(nac_edad_edu_madre.index[nac_edad_edu_madre['edad_madre_grupo'] == \"Sin especificar\"], inplace = True)\n",
+    "nac_edad_edu_madre.drop(nac_edad_edu_madre.index[nac_edad_edu_madre['instruccion_madre'] == \"Sin especificar\"], inplace = True)\n",
+    "nac_edad_edu_madre.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "jZRnk0HlT6ch"
+   },
+   "source": [
+    "Agrupamos por instrucción/educación de la madre y grupo etario, luego se suma la cantidad de nacimientos por esas categorías:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 238
+    },
+    "id": "0oQCwFn2TSd5",
+    "outputId": "624b8961-5a22-45cf-bdd5-28b1fa351270"
+   },
+   "outputs": [],
+   "source": [
+    "nac_edad_edu_madre = nac_edad_edu_madre.groupby([\"instruccion_madre\",\"edad_madre_grupo\"]).sum()\n",
+    "nac_edad_edu_madre.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "n9cVIZ3pT6yI"
+   },
+   "source": [
+    "Como agrupamos por dos categorías usamos unstack para graficar los datos más facilmente:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 269
+    },
+    "id": "hHta7iM9T0B2",
+    "outputId": "e5b7b688-1dd0-44d1-d21a-b8a3517b428b"
+   },
+   "outputs": [],
+   "source": [
+    "nac_edad_edu_madre = nac_edad_edu_madre.unstack()\n",
+    "nac_edad_edu_madre.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "YIh4bD50T7VR"
+   },
+   "source": [
+    "Finalmente graficamos con un gáfico de barras, donde cada grupo corresponde a un nivel de educación y cada barra a un grupo etario, mientras más alta la barra, más nacimientos. También agregamos un título y la leyenda:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 946
+    },
+    "id": "bf6v9x7gAwku",
+    "outputId": "d76f0e80-b08b-4590-e897-1a067fcccb60"
+   },
+   "outputs": [],
+   "source": [
+    "nac_edad_edu_madre.plot.bar(figsize= (25,13),xlabel=\"\",title = \"Cantidad de nacimientos por grupo etario y educación de la madre\",grid=True)\n",
+    "plt.legend([\"Menor de 15\", \"15 a 19\", \"20 a 24\", \"25 a 29\", \"30 a 34\", \"35 a 39\", \"40 a 44\", \"De 45 y más\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "mqrIQcbnDVGQ"
+   },
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "dPsfdz_yEXOq"
+   },
+   "source": [
+    "# Referencias técnicas <a name=\"paragraph6\"></a>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "HusbZdgnsDv0"
+   },
+   "source": [
+    "\n",
+    "---\n",
+    "Este es un apartado más técnico sobre las funciones que se ven en la demostración\n",
+    "---\n",
+    "El lenguaje de programación que estamos utilizando es **Python**, un lenguaje muy popular para ciencia de datos, combinado con la librería *pandas*, también muy popular, ya que nos permite manejar los datos fácilmente y finalmente usamos *matplotlib* para graficar los datos.\n",
+    "\n",
+    "Pandas trabaja con dataframes, estos son la estructura básica que vamos a manipular y funcionan como una tabla con filas y columnas.\n",
+    "\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "osqzdhscEsR4"
+   },
+   "source": [
+    "---\n",
+    "## Funciones importantes\n",
+    "---\n",
+    "A lo largo de esta demostración vamos a usar 7 funciones principales:"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Jlkc7qhmEiGN"
+   },
+   "source": [
+    "### head:\n",
+    "Esta función nos permite ver las primeras 5 filas de un dataframe, además de los nombres de columnas. Es muy útil para visualizar una operación."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "xa6NE0LLsDv5"
+   },
+   "source": [
+    "\n",
+    "### groupby\n",
+    "\n",
+    "Esta potente función, nos permite agrupar nuestra información basados en los valores de una columna y luego realizar operaciones con esos grupos.\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "ZYFkU_DLsDv6"
+   },
+   "source": [
+    "### sum\n",
+    "Nos permite sumar los valores de un conjunto de datos, columna, fila, o en nuestro caso de los grupos de un groupby.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "LhFsPjissDv7"
+   },
+   "source": [
+    "\n",
+    "### drop\n",
+    "Esta función nos permite eliminar filas de un dataframe, hay que indicarle una condición para seleccionar cuales se borran.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "XwrmQ5MGsDv7"
+   },
+   "source": [
+    "\n",
+    "### plot\n",
+    "Nos permite graficar los datos de un dataframe, le indicamos el tipo de gráfico con la instrucción *kind*, y tiene otros parámetros para cosas como tamaño, titulo, etc.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "RC12jKRmsDv7"
+   },
+   "source": [
+    "### plt.legend\n",
+    "Esta función nos permite especificar la leyenda que queremos en nuestro gráfico."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "23uSeoIWPf8K"
+   },
+   "source": [
+    "### unstack\n",
+    "Esta función nos permite desagrupar un dataframe compuesto de dataframes en uno solo con toda la información. Nos sirve para graficar datos que requieren de agrupación por más de una categoría."
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "collapsed_sections": [
+    "O35LytWBsDv0",
+    "QYEZLjtwiH6p",
+    "HY9NHf7Mw2Z8",
+    "_NpC6hVyzwSc",
+    "bPtagRwyz4t4",
+    "Jlvd07tY0QyB"
+   ],
+   "name": "Demo_CDS_nacimientos.ipynb",
+   "provenance": [],
+   "toc_visible": true
+  },
+  "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": "3.10.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}