{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<figure>\n",
    "<img src=\"../Imagenes/logo-final-ap.png\"  width=\"80\" height=\"80\" align=\"left\"/> \n",
    "</figure>\n",
    "\n",
    "# <span style=\"color:#4361EE\"><left>Aprendizaje Profundo</left></span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# <span style=\"color:red\"><center>Diplomado en Inteligencia Artificial y Aprendizaje Profundo</center></span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# <span style=\"color:green\"><center> Regresion Basica. API Functional</center></span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<figure>\n",
    "<center>\n",
    "<img src=\"../Imagenes/gasolina.jpg\" width=\"800\" height=\"400\" align=\"center\" /> \n",
    "</center>   \n",
    "</figure>\n",
    "<center>\n",
    "\n",
    "Fuente: <a href=\"https://commons.wikimedia.org/wiki/File:Dispensador_de_gasolina_viejo_en_San_Vicente.jpg\">Cesar Pérez</a>, <a href=\"https://creativecommons.org/licenses/by-sa/4.0\">CC BY-SA 4.0</a>, via Wikimedia Commons\n",
    "\n",
    "</center>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <span style=\"color:#4361EE\">Profesores</span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "1. Alvaro  Montenegro, PhD, ammontenegrod@unal.edu.co\n",
    "1. Camilo José Torres Jiménez, Msc, cjtorresj@unal.edu.co\n",
    "1. Daniel  Montenegro, Msc, dextronomo@gmail.com "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <span style=\"color:#4361EE\">Asesora Medios y Marketing digital</span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "4. Maria del Pilar Montenegro, pmontenegro88@gmail.com\n",
    "5. Jessica López Mejía, jelopezme@unal.edu.co"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <span style=\"color:#4361EE\">Jefe Jurídica</span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "6. Paula Andrea Guzmán, guzmancruz.paula@gmail.com"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <span style=\"color:#4361EE\">Coordinador Jurídico</span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "7. David Fuentes, fuentesd065@gmail.com"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <span style=\"color:#4361EE\">Desarrolladores Principales</span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "8. Dairo Moreno, damoralesj@unal.edu.co\n",
    "9. Joan Castro, jocastroc@unal.edu.co\n",
    "10. Bryan Riveros, briveros@unal.edu.co\n",
    "11. Rosmer Vargas, rovargasc@unal.edu.co\n",
    "12. Venus Puertas, vpuertasg@unal.edu.co"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <span style=\"color:#4361EE\">Expertos en Bases de Datos</span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "13. Giovvani Barrera, udgiovanni@gmail.com\n",
    "14. Camilo Chitivo, cchitivo@unal.edu.co"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <span style=\"color:#4361EE\">Contenido</span> "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* [Introducción](#Introducción)\n",
    "* [Importa librerías requeridas](#Importa-librerías-requeridas)\n",
    "* [El conjunto de Datos de MPG](#El-conjunto-de-Datos-de-MPG)\n",
    "* [Lectura de los datos](#Lectura-de-los-datos)\n",
    "* [Preprocesamiento](#Preprocesamiento)\n",
    "* [Construye el modelo Sequential modo 1](#Construye-el-modelo-Sequential-modo-1)\n",
    "* [Entrenamiento del modelo](#Entrenamiento-del-modelo)\n",
    "* [Conclusión](#Conclusión)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <span style=\"color:#4361EE\">Introducción</span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "[Información general sobre Tensorflow](https://www.tensorflow.org/?hl=en).\n",
    "\n",
    "\n",
    "<a target=\"_blank\" href=\"https://www.tensorflow.org/tutorials/keras/regression\"><img src=\"https://www.tensorflow.org/images/tf_logo_32px.png\" />Vea el cuaderno original en: TensorFlow.org</a>\n",
    "\n",
    "En un problema de *regresión*, buscamos predecir la salida de un valor continuo como la probabilidad de un precio. En contraste en un problema de *Clasificación*, buscamos seleccionar una clase de una lista de clases (por ejemplo, en donde una imagen contenga una manzana o una naranja queremos reconocer cual es la fruta en la imagen).\n",
    "\n",
    "En este cuaderno se usa el set de datos clásico [Auto MPG](https://archive.ics.uci.edu/ml/datasets/auto+mpg) y se construye un modelo para predecir la eficiencia de vehículos de 1970 y 1980. Para hacer esto proveeremos el modelo con una descripción de muchos automóviles de ese periodo. Esta descripción incluye atributos como: Cilindros, desplazamiento, potencia y peso.\n",
    "\n",
    "Este ejemplo usa el API *Functional* de `tf.keras`.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <span style=\"color:#4361EE\">Importa librerías requeridas</span>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "1rRo8oNqZ-Rj"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Version de Tensorflow =  2.4.1\n"
     ]
    }
   ],
   "source": [
    "from __future__ import absolute_import, division, print_function\n",
    "\n",
    "import tensorflow as tf\n",
    "\n",
    "#from tensorflow import keras\n",
    "#from tensorflow.keras import layers\n",
    "#from tensorflow.keras.utils import plot_model\n",
    "\n",
    "\n",
    "\n",
    "# Objetos de la API de Keras\n",
    "from tensorflow.keras.layers import Dense, Activation, Dropout\n",
    "from tensorflow.keras import Model\n",
    "\n",
    "from tensorflow.keras.utils import plot_model\n",
    "\n",
    "\n",
    "import pathlib\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "\n",
    "\n",
    "\n",
    "print('Version de Tensorflow = ', tf.__version__)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <span style=\"color:#4361EE\">El conjunto de Datos de MPG</span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "F_72b0LCNbjx"
   },
   "source": [
    "\n",
    "\n",
    "El set de datos está disponible en el siguiente repositorio [UCI Machine Learning Repository](https://archive.ics.uci.edu/ml/).\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "gFh9ne3FZ-On"
   },
   "source": [
    "## <span style=\"color:#4361EE\">Lectura de los datos</span>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Primero descargue el set de datos."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "p9kxxgzvzlyz"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'/home/alvaro/.keras/datasets/auto-mpg.data'"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset_path = keras.utils.get_file(\"auto-mpg.data\", \"http://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data\")\n",
    "dataset_path"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "nslsRLh7Zss4"
   },
   "source": [
    "Impórtelo usando pandas."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "CiX2FI4gZtTt"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>MPG</th>\n",
       "      <th>Cylinders</th>\n",
       "      <th>Displacement</th>\n",
       "      <th>Horsepower</th>\n",
       "      <th>Weight</th>\n",
       "      <th>Acceleration</th>\n",
       "      <th>Model Year</th>\n",
       "      <th>Origin</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>393</th>\n",
       "      <td>27.0</td>\n",
       "      <td>4</td>\n",
       "      <td>140.0</td>\n",
       "      <td>86.0</td>\n",
       "      <td>2790.0</td>\n",
       "      <td>15.6</td>\n",
       "      <td>82</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>394</th>\n",
       "      <td>44.0</td>\n",
       "      <td>4</td>\n",
       "      <td>97.0</td>\n",
       "      <td>52.0</td>\n",
       "      <td>2130.0</td>\n",
       "      <td>24.6</td>\n",
       "      <td>82</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>395</th>\n",
       "      <td>32.0</td>\n",
       "      <td>4</td>\n",
       "      <td>135.0</td>\n",
       "      <td>84.0</td>\n",
       "      <td>2295.0</td>\n",
       "      <td>11.6</td>\n",
       "      <td>82</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>396</th>\n",
       "      <td>28.0</td>\n",
       "      <td>4</td>\n",
       "      <td>120.0</td>\n",
       "      <td>79.0</td>\n",
       "      <td>2625.0</td>\n",
       "      <td>18.6</td>\n",
       "      <td>82</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>397</th>\n",
       "      <td>31.0</td>\n",
       "      <td>4</td>\n",
       "      <td>119.0</td>\n",
       "      <td>82.0</td>\n",
       "      <td>2720.0</td>\n",
       "      <td>19.4</td>\n",
       "      <td>82</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      MPG  Cylinders  Displacement  Horsepower  Weight  Acceleration  \\\n",
       "393  27.0          4         140.0        86.0  2790.0          15.6   \n",
       "394  44.0          4          97.0        52.0  2130.0          24.6   \n",
       "395  32.0          4         135.0        84.0  2295.0          11.6   \n",
       "396  28.0          4         120.0        79.0  2625.0          18.6   \n",
       "397  31.0          4         119.0        82.0  2720.0          19.4   \n",
       "\n",
       "     Model Year  Origin  \n",
       "393          82       1  \n",
       "394          82       2  \n",
       "395          82       1  \n",
       "396          82       1  \n",
       "397          82       1  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "column_names = ['MPG','Cylinders','Displacement','Horsepower','Weight',\n",
    "                'Acceleration', 'Model Year', 'Origin']\n",
    "raw_dataset = pd.read_csv(dataset_path, names=column_names,\n",
    "                      na_values = \"?\", comment='\\t',\n",
    "                      sep=\" \", skipinitialspace=True)\n",
    "\n",
    "dataset = raw_dataset.copy()\n",
    "dataset.tail()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <span style=\"color:#4361EE\">Preprocesamiento</span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### <span style=\"color:#4CC9F0\">Detecta datos faltantes y elimina filas</span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "3MWuJTKEDM-f"
   },
   "source": [
    "\n",
    "El set de datos contiene algunos valores desconocidos."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "JEJHhN65a2VV"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "MPG             0\n",
       "Cylinders       0\n",
       "Displacement    0\n",
       "Horsepower      6\n",
       "Weight          0\n",
       "Acceleration    0\n",
       "Model Year      0\n",
       "Origin          0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset.isna().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "9UPN0KBHa_WI"
   },
   "source": [
    "**Para** Mantener este tutorial inicial sencillo eliminemos las siguientes filas."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "4ZUDosChC1UN"
   },
   "outputs": [],
   "source": [
    "dataset = dataset.dropna()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### <span style=\"color:#4CC9F0\">Codificación one-hot</span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "8XKitwaH4v8h"
   },
   "source": [
    "La columna de `\"Origin\"` realmente es categórica, no numérica. Entonces conviértala a un \"one-hot\":"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "gWNTD2QjBWFJ"
   },
   "outputs": [],
   "source": [
    "# retira 'Origin' de dataset y lo entrega. Se recibe en la variable origin\n",
    "Origin = dataset.pop('Origin') "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "ulXz4J7PAUzk"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>MPG</th>\n",
       "      <th>Cylinders</th>\n",
       "      <th>Displacement</th>\n",
       "      <th>Horsepower</th>\n",
       "      <th>Weight</th>\n",
       "      <th>Acceleration</th>\n",
       "      <th>Model Year</th>\n",
       "      <th>USA</th>\n",
       "      <th>Europe</th>\n",
       "      <th>Japan</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>393</th>\n",
       "      <td>27.0</td>\n",
       "      <td>4</td>\n",
       "      <td>140.0</td>\n",
       "      <td>86.0</td>\n",
       "      <td>2790.0</td>\n",
       "      <td>15.6</td>\n",
       "      <td>82</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>394</th>\n",
       "      <td>44.0</td>\n",
       "      <td>4</td>\n",
       "      <td>97.0</td>\n",
       "      <td>52.0</td>\n",
       "      <td>2130.0</td>\n",
       "      <td>24.6</td>\n",
       "      <td>82</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>395</th>\n",
       "      <td>32.0</td>\n",
       "      <td>4</td>\n",
       "      <td>135.0</td>\n",
       "      <td>84.0</td>\n",
       "      <td>2295.0</td>\n",
       "      <td>11.6</td>\n",
       "      <td>82</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>396</th>\n",
       "      <td>28.0</td>\n",
       "      <td>4</td>\n",
       "      <td>120.0</td>\n",
       "      <td>79.0</td>\n",
       "      <td>2625.0</td>\n",
       "      <td>18.6</td>\n",
       "      <td>82</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>397</th>\n",
       "      <td>31.0</td>\n",
       "      <td>4</td>\n",
       "      <td>119.0</td>\n",
       "      <td>82.0</td>\n",
       "      <td>2720.0</td>\n",
       "      <td>19.4</td>\n",
       "      <td>82</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      MPG  Cylinders  Displacement  Horsepower  Weight  Acceleration  \\\n",
       "393  27.0          4         140.0        86.0  2790.0          15.6   \n",
       "394  44.0          4          97.0        52.0  2130.0          24.6   \n",
       "395  32.0          4         135.0        84.0  2295.0          11.6   \n",
       "396  28.0          4         120.0        79.0  2625.0          18.6   \n",
       "397  31.0          4         119.0        82.0  2720.0          19.4   \n",
       "\n",
       "     Model Year  USA  Europe  Japan  \n",
       "393          82  1.0     0.0    0.0  \n",
       "394          82  0.0     1.0    0.0  \n",
       "395          82  1.0     0.0    0.0  \n",
       "396          82  1.0     0.0    0.0  \n",
       "397          82  1.0     0.0    0.0  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset['USA'] = (Origin == 1)*1.0\n",
    "dataset['Europe'] = (Origin == 2)*1.0\n",
    "dataset['Japan'] = (Origin == 3)*1.0\n",
    "dataset.tail()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### <span style=\"color:#4CC9F0\">Ejercicio</span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Investigue cómo hacer esta codificación one-hot utilizando\n",
    "\n",
    "*tf.keras.utils.to_categorical*"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### <span style=\"color:#4CC9F0\">Dividir los datos en entrenamiento y test</span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "Cuym4yvk76vU"
   },
   "source": [
    "\n",
    "Ahora divida el set de datos en un set de entrenamiento y otro de pruebas.\n",
    "\n",
    "Usaremos el set de pruebas en la evaluación final de nuestro modelo."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "qn-IGhUE7_1H"
   },
   "outputs": [],
   "source": [
    "train_dataset = dataset.sample(frac=0.8,random_state=0)\n",
    "test_dataset = dataset.drop(train_dataset.index)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['MPG', 'Cylinders', 'Displacement', 'Horsepower', 'Weight',\n",
       "       'Acceleration', 'Model Year', 'USA', 'Europe', 'Japan'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_dataset.keys()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### <span style=\"color:#4CC9F0\">Descriptivo de los datos</span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "J4ubs136WLNp"
   },
   "source": [
    "\n",
    "Revise rápidamente la distribución conjunta de un par de columnas de el set de entrenamiento."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "oRKO_x8gWKv-"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.PairGrid at 0x7f9cc5a02760>"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 720x720 with 20 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.pairplot(train_dataset[[\"MPG\", \"Cylinders\", \"Displacement\", \"Weight\"]], diag_kind=\"kde\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "gavKO_6DWRMP"
   },
   "source": [
    "También revise las estadísticas generales:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "yi2FzC3T21jR"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Cylinders</th>\n",
       "      <td>314.0</td>\n",
       "      <td>5.477707</td>\n",
       "      <td>1.699788</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.00</td>\n",
       "      <td>4.0</td>\n",
       "      <td>8.00</td>\n",
       "      <td>8.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Displacement</th>\n",
       "      <td>314.0</td>\n",
       "      <td>195.318471</td>\n",
       "      <td>104.331589</td>\n",
       "      <td>68.0</td>\n",
       "      <td>105.50</td>\n",
       "      <td>151.0</td>\n",
       "      <td>265.75</td>\n",
       "      <td>455.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Horsepower</th>\n",
       "      <td>314.0</td>\n",
       "      <td>104.869427</td>\n",
       "      <td>38.096214</td>\n",
       "      <td>46.0</td>\n",
       "      <td>76.25</td>\n",
       "      <td>94.5</td>\n",
       "      <td>128.00</td>\n",
       "      <td>225.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Weight</th>\n",
       "      <td>314.0</td>\n",
       "      <td>2990.251592</td>\n",
       "      <td>843.898596</td>\n",
       "      <td>1649.0</td>\n",
       "      <td>2256.50</td>\n",
       "      <td>2822.5</td>\n",
       "      <td>3608.00</td>\n",
       "      <td>5140.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Acceleration</th>\n",
       "      <td>314.0</td>\n",
       "      <td>15.559236</td>\n",
       "      <td>2.789230</td>\n",
       "      <td>8.0</td>\n",
       "      <td>13.80</td>\n",
       "      <td>15.5</td>\n",
       "      <td>17.20</td>\n",
       "      <td>24.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Model Year</th>\n",
       "      <td>314.0</td>\n",
       "      <td>75.898089</td>\n",
       "      <td>3.675642</td>\n",
       "      <td>70.0</td>\n",
       "      <td>73.00</td>\n",
       "      <td>76.0</td>\n",
       "      <td>79.00</td>\n",
       "      <td>82.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>USA</th>\n",
       "      <td>314.0</td>\n",
       "      <td>0.624204</td>\n",
       "      <td>0.485101</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Europe</th>\n",
       "      <td>314.0</td>\n",
       "      <td>0.178344</td>\n",
       "      <td>0.383413</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Japan</th>\n",
       "      <td>314.0</td>\n",
       "      <td>0.197452</td>\n",
       "      <td>0.398712</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              count         mean         std     min      25%     50%  \\\n",
       "Cylinders     314.0     5.477707    1.699788     3.0     4.00     4.0   \n",
       "Displacement  314.0   195.318471  104.331589    68.0   105.50   151.0   \n",
       "Horsepower    314.0   104.869427   38.096214    46.0    76.25    94.5   \n",
       "Weight        314.0  2990.251592  843.898596  1649.0  2256.50  2822.5   \n",
       "Acceleration  314.0    15.559236    2.789230     8.0    13.80    15.5   \n",
       "Model Year    314.0    75.898089    3.675642    70.0    73.00    76.0   \n",
       "USA           314.0     0.624204    0.485101     0.0     0.00     1.0   \n",
       "Europe        314.0     0.178344    0.383413     0.0     0.00     0.0   \n",
       "Japan         314.0     0.197452    0.398712     0.0     0.00     0.0   \n",
       "\n",
       "                  75%     max  \n",
       "Cylinders        8.00     8.0  \n",
       "Displacement   265.75   455.0  \n",
       "Horsepower     128.00   225.0  \n",
       "Weight        3608.00  5140.0  \n",
       "Acceleration    17.20    24.8  \n",
       "Model Year      79.00    82.0  \n",
       "USA              1.00     1.0  \n",
       "Europe           0.00     1.0  \n",
       "Japan            0.00     1.0  "
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_stats = train_dataset.describe()\n",
    "train_stats.pop(\"MPG\")\n",
    "train_stats = train_stats.transpose()\n",
    "train_stats"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "Db7Auq1yXUvh"
   },
   "source": [
    "### <span style=\"color:#4CC9F0\">Separe caracteristicas y etiquetas</span>\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Separe el valor objetivo, o la \"etiqueta\" de las características. Esta etiqueta es el valor que entrenara el modelo para predecir."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "t2sluJdCW7jN"
   },
   "outputs": [],
   "source": [
    "train_labels = train_dataset.pop('MPG')\n",
    "test_labels = test_dataset.pop('MPG')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "mRklxK5s388r"
   },
   "source": [
    "### <span style=\"color:#4CC9F0\">Normalice los datos</span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "mRklxK5s388r"
   },
   "source": [
    "Revise otra vez el bloque de `train_stats` que se presentó antes y note la diferencia de rangos de cada característica."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "-ywmerQ6dSox"
   },
   "source": [
    "Es una buena práctica normalizar variables que utilizan diferentes escalas y rangos. Aunque el modelo *podría* converger sin normalización de características, dificulta el entrenamiento y hace que el modelo resultante dependa de la elección de las unidades utilizadas en la entrada."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "-ywmerQ6dSox"
   },
   "source": [
    "### <span style=\"color:#4CC9F0\">Nota</span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "-ywmerQ6dSox"
   },
   "source": [
    "Aunque generamos intencionalmente estas estadísticas solo del conjunto de datos de entrenamiento, estas estadísticas también se utilizarán para normalizar el conjunto de datos de prueba. Necesitamos hacer eso para proyectar el conjunto de datos de prueba en la misma distribución en la que el modelo ha sido entrenado."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "JlC5ooJrgjQF"
   },
   "outputs": [],
   "source": [
    "def norm(x):\n",
    "  return (x - train_stats['mean']) / train_stats['std']\n",
    "normed_train_data = norm(train_dataset)\n",
    "normed_test_data = norm(test_dataset)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "BuiClDk45eS4"
   },
   "source": [
    "Estos datos normalizados es lo que usaremos para entrenar el modelo."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "BuiClDk45eS4"
   },
   "source": [
    "### <span style=\"color:#4CC9F0\">Precaución: </span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "BuiClDk45eS4"
   },
   "source": [
    "Las estadísticas utilizadas para normalizar las entradas aquí (media y desviación estándar) deben aplicarse a cualquier otro dato que se alimente al modelo, junto con la codificación de un punto que hicimos anteriormente. Eso incluye el conjunto de pruebas, así como los datos en vivo cuando el modelo se usa en producción."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "6SWtkIjhrZwa"
   },
   "source": [
    "## <span style=\"color:#4361EE\">Construye el modelo API Functional</span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "6SWtkIjhrZwa"
   },
   "source": [
    "Construyamos nuestro modelo. Aquí, utilizaremos un modelo `Sequential` con dos capas ocultas densamente conectadas y una capa de salida que devuelve un único valor continuo. Los pasos de construcción del modelo se envuelven en una función, `build_model`, ya que crearemos un segundo modelo, más adelante."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "c26juK7ZG8j-"
   },
   "outputs": [],
   "source": [
    "class Regression(Model):\n",
    "    def __init__(self):\n",
    "        super(Regression,self).__init__()\n",
    "        self.dense1 = Dense(64, activation='relu')\n",
    "        self.dropout1 = Dropout(0.4)\n",
    "        self.dense2 = Dense(32, activation='relu')\n",
    "        self.dropout2 = Dropout(0.4)\n",
    "        self.dense_out = Dense(1)\n",
    "\n",
    "    def call(self,x):\n",
    "        x = self.dense1(x)\n",
    "        x = self.dropout1(x)\n",
    "        x = self.dense2(x)\n",
    "        x = self.dropout2(x)\n",
    "        return(self.dense_out(x))\n",
    "\n",
    "model = Regression()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <span style=\"color:#4361EE\">Compila</span>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "c26juK7ZG8j-"
   },
   "outputs": [],
   "source": [
    "optimizer = tf.keras.optimizers.Adam()\n",
    "model.compile(loss='mse',\n",
    "                optimizer=optimizer,\n",
    "                metrics=['mae', 'mse'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "0-qWCsh6DlyH"
   },
   "source": [
    "## <span style=\"color:#4361EE\">Entrena</span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "0-qWCsh6DlyH"
   },
   "source": [
    "Entrene el modelo durante 1000 epochs y registre la precisión de entrenamiento y validación en el objeto `history`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "sD7qHCmNIOY0"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "....................................................................................................\n",
      "....................................................................................................\n",
      "....................................................................................................\n",
      "....................................................................................................\n",
      "....................................................................................................\n",
      "....................................................................................................\n",
      "....................................................................................................\n",
      "....................................................................................................\n",
      "....................................................................................................\n",
      "...................................................................................................."
     ]
    }
   ],
   "source": [
    "# Display training progress by printing a single dot for each completed epoch\n",
    "class PrintDot(keras.callbacks.Callback):\n",
    "  def on_epoch_end(self, epoch, logs):\n",
    "    if epoch % 100 == 0: print('')\n",
    "    print('.', end='')\n",
    "\n",
    "epochs = 1000\n",
    "\n",
    "history = model.fit(\n",
    "  normed_train_data, train_labels,\n",
    "  epochs=epochs, validation_split = 0.2, verbose=0,\n",
    "  callbacks=[PrintDot()])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### <span style=\"color:#4CC9F0\">Summary</span>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "c26juK7ZG8j-",
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"regression_1\"\n",
      "_________________________________________________________________\n",
      "Layer (type)                 Output Shape              Param #   \n",
      "=================================================================\n",
      "dense_3 (Dense)              multiple                  640       \n",
      "_________________________________________________________________\n",
      "dropout_2 (Dropout)          multiple                  0         \n",
      "_________________________________________________________________\n",
      "dense_4 (Dense)              multiple                  2080      \n",
      "_________________________________________________________________\n",
      "dropout_3 (Dropout)          multiple                  0         \n",
      "_________________________________________________________________\n",
      "dense_5 (Dense)              multiple                  33        \n",
      "=================================================================\n",
      "Total params: 2,753\n",
      "Trainable params: 2,753\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAJsAAAA8CAYAAABxeMjaAAAABmJLR0QA/wD/AP+gvaeTAAAHFUlEQVR4nO3cX0hT/xsH8PdS9+fUPHMik6zMSWaXFUV4kZWWSn+0oXkRUheGdBMpQRdheNFNN90FkXRREGEJStMRmkgXaQiVUheaGYqS8x85t3TDted382s4z5nNb+6zff0+LzgXfs7j5/Oc+eZ4zmGbhogIjEXfiy2x7oD9d3DYmDAcNiYMh40Jk7h6oLe3F/fu3YtFL2wTefHihWJMcWYbHx9Hc3OzkIbY5jMxMRE2P4oz229qyWTsT54/f47KykrVfXzNxoThsDFhOGxMGA4bE4bDxoThsDFhOGxMGA4bE4bDxoThsDFhOGxMGA4bE4bDxoThsDEAgMPhQE5ODhITw74R6K9Fb2YW5PF4sH//fuzduxdtbW2xbifEyMgIamtrMTY2hqmpqaiuxWc2AYgIgUAAgUAg1q0o1NfXIy8vD+/fv4fRaIzqWnxmE8BoNGJkZCTWbah69OgRDAaDkLX4zPYfJypowAaErbW1FRqNJrgNDQ3hwoULSE1NDY7Nzs4CAGZmZnDt2jXs3r0bWq0WaWlpsNls6O/vV8w7ODiIsrIyyLIMSZJw+PBhtLW1obCwMDhvdXV1VNb3+Xy4ffs2cnNzIUkSzGYzzp49i5cvX+LXr1/rqlvdn9frDVlrbm4OdXV1yM7OhlarRUpKCkpKStDd3R32NR4dHUVlZSVMJhNSU1Nx5syZuD1zhqBVmpqaSGX4j0pLSwkA5efnU3d3N/38+ZPevXtHCQkJNDMzQ9+/f6fMzEyyWCzU3t5ObrebPn/+TPn5+aTX66mnpyc41/DwMJlMJsrIyKCOjo5gbWFhIaWlpZFOp4vq+tXV1STLMnV0dNDi4iI5nU66ceMGAaDu7u51163sb2lpKTg2OTlJWVlZZLFYyG63k8vloqGhIbLZbKTRaKixsVF1jtLSUurp6SGPx0OdnZ1kMBjo0KFD6/6brZaRkUEJCQl/Ncca+Xm+4WFzOByq+y9dukQA6OnTpyHjk5OTpNPp6ODBg8GxiooKAkDNzc0htdPT0yRJ0pph24j1s7KyKC8vTzFHTk5OSIgirVvZ38qwXb58mQDQs2fPQmq9Xi9t376dDAYDOZ1OxRx2uz2kvry8nADQzMyM6rFH6l8XttnZWdX9sizTli1byOVyKfYdOHCAAND4+DgRERmNRgJAbrdbtXatsG3E+levXiUAdOXKFert7SW/3686Z6R1K/tbGTZZlgkALSwsKOqrqqoIAD1+/Fgxx8oAEhHV1tYSABoYGAi7fiSiHbYNv0HYunWrYszn88HlciEQCECW5ZDrD41Ggw8fPgAAhoeH4fP54Ha7odfrsW3bNsVcKSkpUV0fAO7fv48nT57g27dvKCgoQHJyMoqLi9HS0hIyb6R1an73pNfrVR85WCwWAIDT6VTsk2U55GetVgsAcfloZSUhd6M6nQ4mkwmJiYlYXl4GEalux48fh06ng9FohNfrhcfjUcw1PT0d1fUBQKPRoKqqCq9fv8b8/DxaW1tBRLDZbCHfFhBpXbieZFmG1+uF2+1W7P/9gDU9PX3dxxuvhD36sNls8Pv9ePv2rWLf3bt3sWvXLvj9fgBASUkJAODVq1chdU6nE1++fIn6+iaTCYODgwCApKQknDx5MnhH2N7eHvy9SOvCOX/+PAAoan0+H7q6umAwGFBUVPSPjjcureN/7prUrklWmpqaouzsbLJareRwOGh+fp7m5ubowYMHJEkSNTU1BWu/fv1KZrM55G7006dPVFxcTJmZmWtes23E+rIsU35+Pg0MDJDX66WpqSlqaGggAHTnzp1114Xrb/Xd6MLCQsjd6MOHDyM6xps3bxIA+vjxo+qxRyrubxB6e3sJgGJTMzc3R3V1dWS1WikpKYnS0tLo1KlT1NnZqagdGhqisrIySk5OJkmSKC8vj968eUPHjh0jSZKiun5/fz/V1NTQvn37SJIkMpvNdOTIEWpsbKRAILCuupaWFkVvFy9eDM4xOztL169fp6ysLEpKSiJZlqmoqIi6urrWPMZbt24RESnGT58+/ac/WQi73a76+gFQPHqJxFph0/y/4aDf39VAcfrtp7m5uVhaWsLY2FisW2Eq1shPfH7NqdPphNlsxvLycsj46OgoRkZGcOLEiRh1xv5GXIYNAH78+IGamhqMj49jcXERfX19qKysRHJyMurr62PdHvsH4jJs6enpwccJR48eRUpKCs6dO4c9e/agr68PVqs11i3GtdXPEdW2hoYG4X3F7VuMCgoKUFBQEOs2/pXi9Xo7Ls9sbHPisDFhOGxMGA4bE4bDxoThsDFhOGxMGA4bE4bDxoThsDFhOGxMGA4bE4bDxoQJ+66PiooKkX2wTWJiYiLsPsWZbefOnSgvL49qQ2zz2rFjR9j8KD6DwFiUxOdnENjmxGFjwnDYmDAcNibM/wDCbUNbgMr0zAAAAABJRU5ErkJggg==",
      "text/plain": [
       "<IPython.core.display.Image object>"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.summary()\n",
    "plot_model(model, to_file='../Imagenes/gasolina_model_2.png', \n",
    "           show_shapes=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "tQm3pc0FYPQB"
   },
   "source": [
    "Visualice el progreso de entrenamiento del modelo usando las estadísticas almacenadas en el objeto `history`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "4Xj91b-dymEy"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>loss</th>\n",
       "      <th>mae</th>\n",
       "      <th>mse</th>\n",
       "      <th>val_loss</th>\n",
       "      <th>val_mae</th>\n",
       "      <th>val_mse</th>\n",
       "      <th>epoch</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>995</th>\n",
       "      <td>25.988325</td>\n",
       "      <td>3.652177</td>\n",
       "      <td>25.988325</td>\n",
       "      <td>7.582301</td>\n",
       "      <td>2.164073</td>\n",
       "      <td>7.582301</td>\n",
       "      <td>995</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>996</th>\n",
       "      <td>25.640924</td>\n",
       "      <td>3.874132</td>\n",
       "      <td>25.640924</td>\n",
       "      <td>8.171700</td>\n",
       "      <td>2.243850</td>\n",
       "      <td>8.171700</td>\n",
       "      <td>996</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>997</th>\n",
       "      <td>26.333399</td>\n",
       "      <td>3.852148</td>\n",
       "      <td>26.333399</td>\n",
       "      <td>9.003630</td>\n",
       "      <td>2.322664</td>\n",
       "      <td>9.003630</td>\n",
       "      <td>997</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>998</th>\n",
       "      <td>27.441383</td>\n",
       "      <td>3.948963</td>\n",
       "      <td>27.441383</td>\n",
       "      <td>9.499057</td>\n",
       "      <td>2.374269</td>\n",
       "      <td>9.499057</td>\n",
       "      <td>998</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>999</th>\n",
       "      <td>27.871454</td>\n",
       "      <td>3.889062</td>\n",
       "      <td>27.871454</td>\n",
       "      <td>8.844047</td>\n",
       "      <td>2.273642</td>\n",
       "      <td>8.844047</td>\n",
       "      <td>999</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          loss       mae        mse  val_loss   val_mae   val_mse  epoch\n",
       "995  25.988325  3.652177  25.988325  7.582301  2.164073  7.582301    995\n",
       "996  25.640924  3.874132  25.640924  8.171700  2.243850  8.171700    996\n",
       "997  26.333399  3.852148  26.333399  9.003630  2.322664  9.003630    997\n",
       "998  27.441383  3.948963  27.441383  9.499057  2.374269  9.499057    998\n",
       "999  27.871454  3.889062  27.871454  8.844047  2.273642  8.844047    999"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hist = pd.DataFrame(history.history)\n",
    "hist['epoch'] = history.epoch\n",
    "hist.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "B6XriGbVPh2t"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "def plot_history(history):\n",
    "  hist = pd.DataFrame(history.history)\n",
    "  hist['epoch'] = history.epoch\n",
    "\n",
    "  plt.figure()\n",
    "  plt.xlabel('Epoch')\n",
    "  plt.ylabel('Mean Abs Error [MPG]')\n",
    "  plt.plot(hist['epoch'], hist['mae'],\n",
    "           label='Train Error')\n",
    "  plt.plot(hist['epoch'], hist['val_mae'],\n",
    "           label = 'Val Error')\n",
    "  plt.ylim([0,10])\n",
    "  plt.legend()\n",
    "\n",
    "  plt.figure()\n",
    "  plt.xlabel('Epoch')\n",
    "  plt.ylabel('Mean Square Error [$MPG^2$]')\n",
    "  plt.plot(hist['epoch'], hist['mse'],\n",
    "           label='Train Error')\n",
    "  plt.plot(hist['epoch'], hist['val_mse'],\n",
    "           label = 'Val Error')\n",
    "  plt.ylim([0,50])\n",
    "  plt.legend()\n",
    "  plt.show()\n",
    "\n",
    "\n",
    "plot_history(history)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "AqsuANc11FYv"
   },
   "source": [
    "Este gráfico muestra poca mejora, o incluso degradación en el error de validación después de aproximadamente 100 épocas. Actualicemos la llamada `model.fit` para detener automáticamente el entrenamiento cuando el puntaje de validación no mejore. Utilizaremos una * devolución de llamada de EarlyStopping * que pruebe una condición de entrenamiento para cada época. Si transcurre una cantidad determinada de épocas sin mostrar mejoría, entonces detiene automáticamente el entrenamiento.\n",
    "\n",
    "Puedes obtener más información sobre esta devolución de llamada [Aca](https://www.tensorflow.org/versions/master/api_docs/python/tf/keras/callbacks/EarlyStopping)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "3St8-DmrX8P4"
   },
   "source": [
    "El gráfico muestra que en el conjunto de validación, el error promedio generalmente es de alrededor de +/- 2 MPG. ¿Es esto bueno? Le dejaremos esa decisión a usted.\n",
    "\n",
    "Veamos qué tan bien generaliza el modelo al usar el conjunto **test**, que no usamos al entrenar el modelo. Esto nos dice qué tan bien podemos esperar que el modelo prediga cuándo lo usamos en el mundo real."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "jl_yNr5n1kms"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3/3 - 0s - loss: 6.3135 - mae: 1.7939 - mse: 6.3135\n",
      "Testing set Mean Abs Error:  1.79 MPG\n"
     ]
    }
   ],
   "source": [
    "loss, mae, mse = model.evaluate(normed_test_data, test_labels, verbose=2)\n",
    "\n",
    "print(\"Testing set Mean Abs Error: {:5.2f} MPG\".format(mae))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "ft603OzXuEZC"
   },
   "source": [
    "## <span style=\"color:#4361EE\">Predicciones</span>\n",
    "\n",
    "Finalmente, prediga los valores de MPG utilizando datos en el conjunto de pruebas:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "Xe7RXH3N3CWU"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "test_predictions = model.predict(normed_test_data).flatten()\n",
    "\n",
    "plt.scatter(test_labels, test_predictions)\n",
    "plt.xlabel('True Values [MPG]')\n",
    "plt.ylabel('Predictions [MPG]')\n",
    "plt.axis('equal')\n",
    "plt.axis('square')\n",
    "plt.xlim([0,plt.xlim()[1]])\n",
    "plt.ylim([0,plt.ylim()[1]])\n",
    "_ = plt.plot([-100, 100], [-100, 100])\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "19wyogbOSU5t"
   },
   "source": [
    "Parece que nuestro modelo predice razonablemente bien. Echemos un vistazo a la distribución de errores."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "f-OHX4DiXd8x"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "error = test_predictions - test_labels\n",
    "plt.hist(error, bins = 25)\n",
    "plt.xlabel(\"Prediction Error [MPG]\")\n",
    "_ = plt.ylabel(\"Count\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "m0CB5tBjSU5w"
   },
   "source": [
    "No es del todo gaussiano, pero podríamos esperar eso porque el número de muestras es muy pequeño."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "vgGQuV-yqYZH"
   },
   "source": [
    "## <span style=\"color:#4361EE\">Conclusión</span>\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "vgGQuV-yqYZH"
   },
   "source": [
    "\n",
    "Este cuaderno introdujo algunas técnicas para manejar un problema de regresión.\n",
    "\n",
    "* El error cuadrático medio (MSE) es una función de pérdida común utilizada para problemas de regresión (se utilizan diferentes funciones de pérdida para problemas de clasificación).\n",
    "* Del mismo modo, las métricas de evaluación utilizadas para la regresión difieren de la clasificación. Una métrica de regresión común es el error absoluto medio (MAE).\n",
    "* Cuando las características de datos de entrada numéricos tienen valores con diferentes rangos, cada característica debe escalarse independientemente al mismo rango.\n",
    "* Si no hay muchos datos de entrenamiento, una técnica es preferir una red pequeña con pocas capas ocultas para evitar el sobreajuste.\n",
    "* La detención temprana es una técnica útil para evitar el sobreajuste."
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "regression.ipynb",
   "private_outputs": true,
   "provenance": [],
   "toc_visible": true,
   "version": "0.3.2"
  },
  "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": "3.9.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}