09_etapas_de_un_proyecto_deep_learning.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "09-etapas-de-un-proyecto-deep-learning.ipynb",
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "FKNAOn5Ia7pG",
        "colab_type": "text"
      },
      "source": [
        "\n",
        "# 09. Etapas de un proyecto Deep Learning\n",
        "[**Python Deep Learning** Introducción práctica con Keras y TensorFlow 2. Jordi Torres. Editorial Marcombo ISBN: 9788426728289 ](https://www.marcombo.com/python-deep-learning-9788426728289/)\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "HhxVlFL7j4N6",
        "colab_type": "text"
      },
      "source": [
        "### Inicialización"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "VcFrOCQOYU1R",
        "colab_type": "code",
        "outputId": "8f98cdcb-b314-484a-e2b8-c22cee8b1ccf",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 52
        }
      },
      "source": [
        "%tensorflow_version 2.x\n",
        "import tensorflow as tf\n",
        "\n",
        "print(tf.__version__)\n",
        "\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import pandas as pd\n"
      ],
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "TensorFlow 2.x selected.\n",
            "2.1.0-rc1\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "DtndO_D__Z2T",
        "colab_type": "text"
      },
      "source": [
        "### Descarga datos Auto MPG"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "niPo3Nfh-bVz",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "dataset_path = tf.keras.utils.get_file(\"auto-mpg.data\", \"https://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data\")"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Z7TMTyo--bYr",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "column_names = ['MPG','Cylinders','Displacement','Horsepower','Weight',   'Acceleration', 'Model Year', 'Origin'] \n",
        "\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()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "WEvgfenf-pEf",
        "colab_type": "code",
        "outputId": "bf18a6af-b20a-43f1-9479-7b430dce5315",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 215
        }
      },
      "source": [
        "dataset.tail()"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "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  ...  Acceleration  Model Year  Origin\n",
              "393  27.0          4         140.0  ...          15.6          82       1\n",
              "394  44.0          4          97.0  ...          24.6          82       2\n",
              "395  32.0          4         135.0  ...          11.6          82       1\n",
              "396  28.0          4         120.0  ...          18.6          82       1\n",
              "397  31.0          4         119.0  ...          19.4          82       1\n",
              "\n",
              "[5 rows x 8 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "q6Cqjf_xnwpw",
        "colab_type": "code",
        "outputId": "dc25e065-0250-4a8e-f42d-53f7122f9b5c",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 215
        }
      },
      "source": [
        "dataset.head()"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>0</th>\n",
              "      <td>18.0</td>\n",
              "      <td>8</td>\n",
              "      <td>307.0</td>\n",
              "      <td>130.0</td>\n",
              "      <td>3504.0</td>\n",
              "      <td>12.0</td>\n",
              "      <td>70</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>15.0</td>\n",
              "      <td>8</td>\n",
              "      <td>350.0</td>\n",
              "      <td>165.0</td>\n",
              "      <td>3693.0</td>\n",
              "      <td>11.5</td>\n",
              "      <td>70</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>18.0</td>\n",
              "      <td>8</td>\n",
              "      <td>318.0</td>\n",
              "      <td>150.0</td>\n",
              "      <td>3436.0</td>\n",
              "      <td>11.0</td>\n",
              "      <td>70</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>16.0</td>\n",
              "      <td>8</td>\n",
              "      <td>304.0</td>\n",
              "      <td>150.0</td>\n",
              "      <td>3433.0</td>\n",
              "      <td>12.0</td>\n",
              "      <td>70</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>17.0</td>\n",
              "      <td>8</td>\n",
              "      <td>302.0</td>\n",
              "      <td>140.0</td>\n",
              "      <td>3449.0</td>\n",
              "      <td>10.5</td>\n",
              "      <td>70</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "    MPG  Cylinders  Displacement  ...  Acceleration  Model Year  Origin\n",
              "0  18.0          8         307.0  ...          12.0          70       1\n",
              "1  15.0          8         350.0  ...          11.5          70       1\n",
              "2  18.0          8         318.0  ...          11.0          70       1\n",
              "3  16.0          8         304.0  ...          12.0          70       1\n",
              "4  17.0          8         302.0  ...          10.5          70       1\n",
              "\n",
              "[5 rows x 8 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "QawPBGCl-vRd",
        "colab_type": "code",
        "outputId": "2ddb1eee-5227-4f0f-e514-98ef5047a531",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 173
        }
      },
      "source": [
        "print(dataset.isna().sum())"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "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\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Ntm2wuai-vUY",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "dataset = dataset.dropna()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "NFpVmTFz-vXM",
        "colab_type": "code",
        "outputId": "2c051a22-93a1-4be8-fc9e-1c9d6b3355eb",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 235
        }
      },
      "source": [
        "origin = dataset.pop('Origin')\n",
        "dataset['USA'] = (origin == 1)*1.0\n",
        "dataset['Europe'] = (origin == 2)*1.0\n",
        "dataset['Japan'] = (origin == 3)*1.0\n",
        "dataset.tail()"
      ],
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "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  ...  Model Year  USA  Europe  Japan\n",
              "393  27.0          4         140.0        86.0  ...          82  1.0     0.0    0.0\n",
              "394  44.0          4          97.0        52.0  ...          82  0.0     1.0    0.0\n",
              "395  32.0          4         135.0        84.0  ...          82  1.0     0.0    0.0\n",
              "396  28.0          4         120.0        79.0  ...          82  1.0     0.0    0.0\n",
              "397  31.0          4         119.0        82.0  ...          82  1.0     0.0    0.0\n",
              "\n",
              "[5 rows x 10 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "wBXjhOwa_eFh",
        "colab_type": "text"
      },
      "source": [
        "## Separar los datos para entrenar y evaluar"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "5yrXBybR_V7j",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "train_dataset = dataset.sample(frac=0.8,random_state=0)\n",
        "test_dataset = dataset.drop(train_dataset.index)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "wtq9cEZV_V-m",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "train_labels = train_dataset.pop('MPG')\n",
        "test_labels = test_dataset.pop('MPG')"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "FekCNTKP_WBI",
        "colab_type": "code",
        "outputId": "552b35e2-d047-4d8b-a13b-93eef59c89bd",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 318
        }
      },
      "source": [
        "train_stats = train_dataset.describe()\n",
        "train_stats = train_stats.transpose()\n",
        "train_stats"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "execute_result",
          "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  ...     50%      75%     max\n",
              "Cylinders     314.0     5.477707    1.699788  ...     4.0     8.00     8.0\n",
              "Displacement  314.0   195.318471  104.331589  ...   151.0   265.75   455.0\n",
              "Horsepower    314.0   104.869427   38.096214  ...    94.5   128.00   225.0\n",
              "Weight        314.0  2990.251592  843.898596  ...  2822.5  3608.00  5140.0\n",
              "Acceleration  314.0    15.559236    2.789230  ...    15.5    17.20    24.8\n",
              "Model Year    314.0    75.898089    3.675642  ...    76.0    79.00    82.0\n",
              "USA           314.0     0.624204    0.485101  ...     1.0     1.00     1.0\n",
              "Europe        314.0     0.178344    0.383413  ...     0.0     0.00     1.0\n",
              "Japan         314.0     0.197452    0.398712  ...     0.0     0.00     1.0\n",
              "\n",
              "[9 rows x 8 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "V6-D516VCSUe",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "def norm(x):\n",
        "  return (x - train_stats['mean']) / train_stats['std']\n",
        "\n",
        "normed_train_data = norm(train_dataset)\n",
        "normed_test_data = norm(test_dataset)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "R5PUc7EgFtCn",
        "colab_type": "code",
        "outputId": "86861669-054d-49b8-a5af-94e687beb24a",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 318
        }
      },
      "source": [
        "normed_train_stats = normed_train_data.describe()\n",
        "normed_train_stats = normed_train_stats.transpose()\n",
        "normed_train_stats"
      ],
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>2.093159e-16</td>\n",
              "      <td>1.0</td>\n",
              "      <td>-1.457657</td>\n",
              "      <td>-0.869348</td>\n",
              "      <td>-0.869348</td>\n",
              "      <td>1.483887</td>\n",
              "      <td>1.483887</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Displacement</th>\n",
              "      <td>314.0</td>\n",
              "      <td>1.018294e-16</td>\n",
              "      <td>1.0</td>\n",
              "      <td>-1.220325</td>\n",
              "      <td>-0.860894</td>\n",
              "      <td>-0.424785</td>\n",
              "      <td>0.675074</td>\n",
              "      <td>2.489002</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Horsepower</th>\n",
              "      <td>314.0</td>\n",
              "      <td>-1.909301e-17</td>\n",
              "      <td>1.0</td>\n",
              "      <td>-1.545283</td>\n",
              "      <td>-0.751241</td>\n",
              "      <td>-0.272190</td>\n",
              "      <td>0.607162</td>\n",
              "      <td>3.153347</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Weight</th>\n",
              "      <td>314.0</td>\n",
              "      <td>-9.723291e-17</td>\n",
              "      <td>1.0</td>\n",
              "      <td>-1.589352</td>\n",
              "      <td>-0.869478</td>\n",
              "      <td>-0.198782</td>\n",
              "      <td>0.732017</td>\n",
              "      <td>2.547401</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Acceleration</th>\n",
              "      <td>314.0</td>\n",
              "      <td>2.688832e-15</td>\n",
              "      <td>1.0</td>\n",
              "      <td>-2.710152</td>\n",
              "      <td>-0.630725</td>\n",
              "      <td>-0.021237</td>\n",
              "      <td>0.588250</td>\n",
              "      <td>3.313017</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Model Year</th>\n",
              "      <td>314.0</td>\n",
              "      <td>9.561531e-16</td>\n",
              "      <td>1.0</td>\n",
              "      <td>-1.604642</td>\n",
              "      <td>-0.788458</td>\n",
              "      <td>0.027726</td>\n",
              "      <td>0.843910</td>\n",
              "      <td>1.660094</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>USA</th>\n",
              "      <td>314.0</td>\n",
              "      <td>6.081476e-17</td>\n",
              "      <td>1.0</td>\n",
              "      <td>-1.286751</td>\n",
              "      <td>-1.286751</td>\n",
              "      <td>0.774676</td>\n",
              "      <td>0.774676</td>\n",
              "      <td>0.774676</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Europe</th>\n",
              "      <td>314.0</td>\n",
              "      <td>8.485781e-18</td>\n",
              "      <td>1.0</td>\n",
              "      <td>-0.465148</td>\n",
              "      <td>-0.465148</td>\n",
              "      <td>-0.465148</td>\n",
              "      <td>-0.465148</td>\n",
              "      <td>2.143005</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Japan</th>\n",
              "      <td>314.0</td>\n",
              "      <td>3.164489e-17</td>\n",
              "      <td>1.0</td>\n",
              "      <td>-0.495225</td>\n",
              "      <td>-0.495225</td>\n",
              "      <td>-0.495225</td>\n",
              "      <td>-0.495225</td>\n",
              "      <td>2.012852</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "              count          mean  std  ...       50%       75%       max\n",
              "Cylinders     314.0  2.093159e-16  1.0  ... -0.869348  1.483887  1.483887\n",
              "Displacement  314.0  1.018294e-16  1.0  ... -0.424785  0.675074  2.489002\n",
              "Horsepower    314.0 -1.909301e-17  1.0  ... -0.272190  0.607162  3.153347\n",
              "Weight        314.0 -9.723291e-17  1.0  ... -0.198782  0.732017  2.547401\n",
              "Acceleration  314.0  2.688832e-15  1.0  ... -0.021237  0.588250  3.313017\n",
              "Model Year    314.0  9.561531e-16  1.0  ...  0.027726  0.843910  1.660094\n",
              "USA           314.0  6.081476e-17  1.0  ...  0.774676  0.774676  0.774676\n",
              "Europe        314.0  8.485781e-18  1.0  ... -0.465148 -0.465148  2.143005\n",
              "Japan         314.0  3.164489e-17  1.0  ... -0.495225 -0.495225  2.012852\n",
              "\n",
              "[9 rows x 8 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "qmNpCfOqCwqv",
        "colab_type": "text"
      },
      "source": [
        "## Desarrollar el modelo"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "aydxA-K9inqG",
        "colab_type": "code",
        "outputId": "d9eebe17-fb09-4cdd-d9cd-bded7a2b6d0d",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 259
        }
      },
      "source": [
        "from tensorflow.keras import Sequential\n",
        "from tensorflow.keras.layers import Dense\n",
        "\n",
        "def build_model():  \n",
        "  model = Sequential()\n",
        "  model.add(Dense(64, activation='relu', input_shape=[len(train_dataset.keys())]))\n",
        "  model.add(Dense(64, activation='relu'))\n",
        "  model.add(Dense(1))\n",
        "  return model\n",
        "\n",
        "model = build_model()\n",
        "model.summary()"
      ],
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Model: \"sequential\"\n",
            "_________________________________________________________________\n",
            "Layer (type)                 Output Shape              Param #   \n",
            "=================================================================\n",
            "dense (Dense)                (None, 64)                640       \n",
            "_________________________________________________________________\n",
            "dense_1 (Dense)              (None, 64)                4160      \n",
            "_________________________________________________________________\n",
            "dense_2 (Dense)              (None, 1)                 65        \n",
            "=================================================================\n",
            "Total params: 4,865\n",
            "Trainable params: 4,865\n",
            "Non-trainable params: 0\n",
            "_________________________________________________________________\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "FpTRcHXDCSew",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "optimizer = tf.keras.optimizers.RMSprop(0.001)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "EWp8Vcl0CShg",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "model.compile(loss='mse',\n",
        "                optimizer=optimizer,\n",
        "                metrics=['mae', 'mse'])"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "vdfftlXWEG-e",
        "colab_type": "text"
      },
      "source": [
        "##entrenamiento del modelo"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "fOaq8eGtCSkd",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "EPOCHS = 1000\n",
        "\n",
        "history = model.fit(\n",
        "  normed_train_data, train_labels,\n",
        "  epochs=EPOCHS, validation_split = 0.2, verbose=0)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "5obUY1dBEnFY",
        "colab_type": "text"
      },
      "source": [
        "## Evaluación el modelo"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "w3FgAK4CCSnX",
        "colab_type": "code",
        "outputId": "a1e0e254-8b78-4930-8be3-f0e5abe9e8e1",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 198
        }
      },
      "source": [
        "hist = pd.DataFrame(history.history)\n",
        "hist['epoch'] = history.epoch\n",
        "hist.tail()"
      ],
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>2.589891</td>\n",
              "      <td>1.013521</td>\n",
              "      <td>2.589891</td>\n",
              "      <td>8.190395</td>\n",
              "      <td>2.191818</td>\n",
              "      <td>8.190394</td>\n",
              "      <td>995</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>996</th>\n",
              "      <td>2.912394</td>\n",
              "      <td>1.075663</td>\n",
              "      <td>2.912394</td>\n",
              "      <td>8.304448</td>\n",
              "      <td>2.213434</td>\n",
              "      <td>8.304447</td>\n",
              "      <td>996</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>997</th>\n",
              "      <td>2.684659</td>\n",
              "      <td>1.012064</td>\n",
              "      <td>2.684659</td>\n",
              "      <td>8.486971</td>\n",
              "      <td>2.253339</td>\n",
              "      <td>8.486972</td>\n",
              "      <td>997</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>998</th>\n",
              "      <td>2.623651</td>\n",
              "      <td>1.007520</td>\n",
              "      <td>2.623652</td>\n",
              "      <td>8.616540</td>\n",
              "      <td>2.281941</td>\n",
              "      <td>8.616540</td>\n",
              "      <td>998</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>999</th>\n",
              "      <td>2.623010</td>\n",
              "      <td>1.034779</td>\n",
              "      <td>2.623010</td>\n",
              "      <td>8.535312</td>\n",
              "      <td>2.228194</td>\n",
              "      <td>8.535312</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  2.589891  1.013521  2.589891  8.190395  2.191818  8.190394    995\n",
              "996  2.912394  1.075663  2.912394  8.304448  2.213434  8.304447    996\n",
              "997  2.684659  1.012064  2.684659  8.486971  2.253339  8.486972    997\n",
              "998  2.623651  1.007520  2.623652  8.616540  2.281941  8.616540    998\n",
              "999  2.623010  1.034779  2.623010  8.535312  2.228194  8.535312    999"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "PHxBjzT8Ep82",
        "colab_type": "code",
        "colab": {}
      },
      "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 Square Error')\n",
        "  plt.plot(hist['epoch'], hist['mse'],'r--',\n",
        "           label='Training Error')\n",
        "  plt.plot(hist['epoch'], hist['val_mse'],'b',\n",
        "           label = 'Validation Error')\n",
        "  plt.ylim([0,20])\n",
        "  plt.legend()\n",
        "  plt.show()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "XnwnYCxcEqCw",
        "colab_type": "code",
        "outputId": "e8f71753-c122-41e0-add0-7d8e60400890",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 283
        }
      },
      "source": [
        "plot_history(history)"
      ],
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAAEKCAYAAAAIO8L1AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjIsIGh0\ndHA6Ly9tYXRwbG90bGliLm9yZy8li6FKAAAgAElEQVR4nO2daXhURdaA30MSCIZdEWTHZVhljaiD\nKLuICqKoICqIisM47jqDjivjjOjngo6OioobiDoqyCgIiCg6igiI7AygoEBYlX1Lwvl+1O10p9Od\ndJLudJI+7/PU07eWW3Vu3+57btWpOiWqimEYhmEEUyHeAhiGYRilE1MQhmEYRkhMQRiGYRghMQVh\nGIZhhMQUhGEYhhESUxCGYRhGSGKmIESkoYjMEZEVIrJcRG7x0muJyCwRWeN91gxz/lCvzBoRGRor\nOQ3DMIzQSKzWQYjICcAJqrpIRKoCC4GLgGHAr6o6RkRGATVV9S9B59YCFgDpgHrndlTV32IirGEY\nhpGHmPUgVDVDVRd5x3uBlUB9oD/wulfsdZzSCOZcYJaq/uophVlAn1jJahiGYeQluSQaEZEmQHvg\nW6COqmZ4WVuAOiFOqQ/8EhDf6KWFqnsEMAIgLS2tY/PmzaMi867lm1h3qD4tW0LlylGp0jAMo9Sx\ncOHCHapaO1RezBWEiFQB3gduVdU9IpKTp6oqIsUa41LVccA4gPT0dF2wYEFxqsvhw1b3cNGKfzBh\nArRvH5UqDcMwSh0isiFcXkxnMYlICk45TFTVD7zkrZ59wmen2Bbi1E1Aw4B4Ay+txKjQszsAR4+W\nZKuGYRilh1jOYhLgFWClqj4ZkDUV8M1KGgp8GOL0GUBvEanpzXLq7aWVGBV69wRMQRiGkbjEsgfR\nGbgK6C4ii73QFxgD9BKRNUBPL46IpIvIywCq+ivwN+A7L4z20kqMCvv2AKYgDMNIXGJmg1DVrwAJ\nk90jRPkFwHUB8fHA+NhIVzAVHhsD/IPs7HhJYBilh8zMTDZu3MihQ4fiLYpRRFJTU2nQoAEpKSkR\nn1Mis5jKIkkVnO3cehCGARs3bqRq1ao0adKEwIkmRtlAVdm5cycbN26kadOmEZ9nrjbCUMH7ZkxB\nGAYcOnSIY4891pRDGUVEOPbYYwvdAzQFEYYKSe6PYArCMBymHMo2Rbl/piDCYD0IwzASHVMQYahw\n/nmAKQjDKA3s3LmTdu3a0a5dO+rWrUv9+vVz4keOHImojmuuuYbVq1fnW+a5555j4sSJ0RCZs846\ni2bNmuXIefnll0el3pLEjNRhqHBOFwCbxWQYpYBjjz2WxYsXA/Dggw9SpUoV7rzzzlxlVBVVpUKF\n0O+9r776aoHt3HjjjcUXNoB33nmHdu3ahc3PysoiOTk5bDzS82KF9SDCkPTbDsB6EIZRmlm7di0t\nW7ZkyJAhtGrVioyMDEaMGEF6ejqtWrVi9OjROWXPOussFi9eTFZWFjVq1GDUqFG0bduWM888k23b\nnEOHe++9l7Fjx+aUHzVqFJ06daJZs2Z8/fXXAOzfv59LLrmEli1bMnDgQNLT03OUVyRceeWVjBw5\nkk6dOnHPPfdw7733cvXVV9O5c2eGDRvGwYMHGTp0KKeeeiodOnRg7ty5ALz88stcdNFFdOvWjXPP\nPTdaX2G+WA8iDBWeGQs8bArCMELRtWvetMsugz/+EQ4cgL598+YPG+bCjh0wcGDuvM8/L7Ioq1at\n4o033iA9PR2AMWPGUKtWLbKysujWrRsDBw6kZcuWuc7ZvXs355xzDmPGjOH2229n/PjxjBo1Kk/d\nqsr8+fOZOnUqo0eP5pNPPuGf//wndevW5f333+eHH36gQ4cOYWW7/PLLqex5++zTpw9jxowBICMj\ng3nz5lGhQgXuvfdeVq1axdy5c0lNTeXRRx+lUqVKLF26lOXLl9O3b1/WrFkDwPfff8/ixYupWTPk\nNjpRxxREGMxIbRhlg5NOOilHOQBMmjSJV155haysLDZv3syKFSvyKIjKlStz3nnOztixY0e+/PLL\nkHVffPHFOWXWr18PwFdffcVf/uK2sGnbti2tWrUKK1u4IaZLL70011BY//79SU1Nzan/rrvuAqBV\nq1bUq1ePtWvXAtC7d+8SUw5gCiIsNs3VMPIhvzf+Y47JP/+444rVYwgmLS0t53jNmjU8/fTTzJ8/\nnxo1anDllVeGnPtfsWLFnOOkpCSysrJC1l2pUqUCyxRX5lDxSM+LNWaDCIMpCMMoe+zZs4eqVatS\nrVo1MjIymDEj+j4+O3fuzLvvvgvA0qVLWbFiRVTr79KlS85MqpUrV5KRkcHJJ58c1TYixXoQYfD1\n/mwWk2GUHTp06EDLli1p3rw5jRs3pnPnzlFv46abbuLqq6+mZcuWOaF69eohywbaIOrUqRORwrrp\nppu44YYbOPXUU0lJSeGNN97I1eMpSWK2J3U8iOaGQSvf+I6WQ09j0iQYNCgqVRpGmWXlypW0aNEi\n3mKUCrKyssjKyiI1NZU1a9bQu3dv1qxZUyLTTotLqPsoIgtVNT1U+dJ/RXEi5fenARDFYUfDMMoB\n+/bto0ePHmRlZaGqvPjii2VCORSF8nlVUSB56yagPpmZ8ZbEMIzSRI0aNVi4cGG8xSgRzEgdhpSX\nnwcwBWEYRsJiCiIMKcnONmMKwjCMRMUURBh8my6ZgjAMI1GJmQ1CRMYDFwDbVLW1l/YO0MwrUgPY\npap5lhmKyHpgL5ANZIWzsMcSn83JjNSGYSQqsexBvAb0CUxQ1ctVtZ2nFN4HPsjn/G5e2RJXDmBD\nTIZRmujWrVueNQRjx45l5MiR+Z5XpUoVADZv3szAYP9PHl27dqWg6fFjx47lwIEDOfG+ffuya9eu\nSETPlwcffDCX6/J27dpFpd5oETMFoapzgV9D5Ynb2ugyYFKs2i8uKUMuA0xBGEZpYPDgwbz99tu5\n0t5++20GDx4c0fn16tXjvffeK3L7wQpi2rRp1KhRo8j1BXLbbbexePHinBBcb7CLj0hdfqgqR4vp\nCiJeNoguwFZVXRMmX4GZIrJQREaUoFw5JHVsh4gpCMMoDQwcOJCPP/44Z3Og9evXs3nzZrp06ZKz\nLqFDhw6ceuqpfPjhh3nOX79+Pa1btwbg4MGDDBo0iBYtWjBgwAAOHjyYU27kyJE5rsIfeOABAJ55\n5hk2b95Mt27d6NatGwBNmjRhxw63JcCTTz5J69atad26dY6r8PXr19OiRQuuv/56WrVqRe/evXO1\nUxCvvfYa/fr1o3v37vTo0YPPP/+cLl260K9fvxzHg+HabdasGVdffTWtW7fml19+KdT3HEy81kEM\nJv/ew1mquklEjgdmicgqr0eSB0+BjABo1KhR9CT86SdSkhuTlWV2fMMI5NZboRDbH0REu3bgPeNC\nUqtWLTp16sT06dPp378/b7/9NpdddhkiQmpqKpMnT6ZatWrs2LGDM844g379+oXdg/n555/nmGOO\nYeXKlSxZsiSXu+6///3v1KpVi+zsbHr06MGSJUu4+eabefLJJ5kzZw7HHXdcrroWLlzIq6++yrff\nfouqcvrpp3POOedQs2ZN1qxZw6RJk3jppZe47LLLeP/997nyyivzyPPUU08xYcIEAGrWrMmcOXMA\nWLRoEUuWLKFWrVp8/vnnLFq0iGXLltG0adMC23399dc544wzCnsb8lDiTz8RSQYuBt4JV0ZVN3mf\n24DJQKd8yo5T1XRVTa9du3b0BH3tNZIzD5J5pPy4IjGMskzgMFPg8JKqcs8999CmTRt69uzJpk2b\n2Lp1a9h65s6dm/OgbtOmDW3atMnJe/fdd+nQoQPt27dn+fLlBTri++qrrxgwYABpaWlUqVKFiy++\nOMd1eNOmTXNcfQe6Cw8mcIjJpxwAevXqRa1atXLinTp1omnTpgW227hx46goB4hPD6InsEpVN4bK\nFJE0oIKq7vWOewOjQ5WNKUlJpJBpQ0yGEUR+b/qxpH///tx2220sWrSIAwcO0LFjRwAmTpzI9u3b\nWbhwISkpKTRp0iSki++C+Omnn3j88cf57rvvqFmzJsOGDStSPT58rsLBuQsvzBATlA6X4DHrQYjI\nJOAboJmIbBSRa72sQQQNL4lIPRGZ5kXrAF+JyA/AfOBjVf0kVnKGpUIFpyCsB2EYpYIqVarQrVs3\nhg8fnss4vXv3bo4//nhSUlKYM2cOGzZsyLees88+m7feeguAZcuWsWTJEsC5Ck9LS6N69eps3bqV\n6dOn55xTtWpV9u7dm6euLl26MGXKFA4cOMD+/fuZPHkyXbp0icbl5ktJtRuzHoSqhpxeoKrDQqRt\nBvp6xz8CbWMlV8T4ehBHjmLrCQ2jdDB48GAGDBiQa0bTkCFDuPDCCzn11FNJT0+nefPm+dYxcuRI\nrrnmGlq0aEGLFi1yeiJt27alffv2NG/enIYNG+ZyFT5ixAj69OlDvXr1cg0DdejQgWHDhtGpkxsF\nv+6662jfvn3Y4aRQBNogAKZMmVLgOdFoNxLM3Xc4HnuMRn8ZRI8rT+DVN1OiU6dhlFHM3Xf5oLDu\nvu3VOBwXX0xK3WPJzE6KtySGYRhxwdx9h+Pkk0mpDpm2o5xhGAmK9SDCsX49KQf3kHnINIRhgJtO\napRdinL/TEGEY8YMUn5eS9ZBm+dqGKmpqezcudOURBlFVdm5cyepqamFOs+GmMKRnEwyWWRm2h/C\nMBo0aMDGjRvZvn17vEUxikhqaioNGjQo1DmmIMKRnOxNc423IIYRf1JSUnJW8RqJgw0xhcOnIKwH\nYRhGgmIKIhw5CiLeghiGYcQHG2IKR7duJHdKJiu7UsFlDcMwyiHWgwjH8ceTUqeWLZQzDCNhMQUR\njs2bSdnyM5mHbFNqwzASE1MQ4ViyhJTvvibzgBkhDMNITExBhCNnP4jQu1IZhmGUd0xBhMNbKJdl\nnjYMw0hQTEGEwzfNNct6EIZhJCamIMJhCsIwjATHFEQ4Tj2VlMGXkoltFmQYRmJiC+XCUaUKKfWr\nkGWzXA3DSFBi1oMQkfEisk1ElgWkPSgim0RksRf6hjm3j4isFpG1IjIqVjLmy6+/krx0kfliMgwj\nYYnlENNrQJ8Q6U+pajsvTAvOFJEk4DngPKAlMFhEWsZQztBs2ULKjI/IzBTMBb5hGIlIzBSEqs4F\nfi3CqZ2Atar6o6oeAd4G+kdVuEjwjNQA2TbV1TCMBCQeRuo/icgSbwiqZoj8+sAvAfGNXlpIRGSE\niCwQkQVR3czEWygHmEdXwzASkpJWEM8DJwHtgAzgieJWqKrjVDVdVdNr165d3Or8eAvlADNUG4aR\nkJSoglDVraqarapHgZdww0nBbAIaBsQbeGklS8AQk/UgDMNIREpUQYjICQHRAcCyEMW+A04RkaYi\nUhEYBEwtCflyUacOKQ/8FTAFYRhGYhKzdRAiMgnoChwnIhuBB4CuItIOUGA9cINXth7wsqr2VdUs\nEfkTMANIAsar6vJYyRmW5GRS6h8PmIIwDCMxiZmCUNXBIZJfCVN2M9A3ID4NyDMFtkQ5fJiUT2cD\nfc0GYRhGQmKuNsKRmUnyu2/5Dg3DMBIOUxDhMCO1YRgJjimIcJiCMAwjwclXQYhIkojcVlLClCps\noZxhGAlOvgpCVbOBUMbm8o8IyXIUsIVyhmEkJpEMMf1XRJ4VkS4i0sEXYi5ZKSBl0huA9SAMw0hM\nIpnm2s77HB2QpkD36ItTukipeyxgCsIwjMSkQAWhqt1KQpDSSMpbrwNDTUEYhpGQFDjEJCLVReRJ\nn8dUEXlCRKqXhHDxxoaYDMNIZCKxQYwH9gKXeWEP8GoshSotpCS7nYJMQRiGkYhEYoM4SVUvCYg/\nJCKLYyVQaSIlyc1iMgVhGEYiEkkP4qCInOWLiEhn4GDsRCo9WA/CMIxEJpIexB+ANwLsDr8BQ2Mn\nUunBFIRhGIlMvgpCRCoAzVS1rYhUA1DVPSUiWSkg5dPp0NwUhGEYiUlBK6mPAn/2jvckknIASKmR\nBpiCMAwjMYnEBvGpiNwpIg1FpJYvxFyyUkDy+HGAKQjDMBKTSGwQl3ufNwakKXBi9MUpXaRMfR8Y\nYQrCMIyEJBIbxJWq+t8SkqdUkZKaBFgPwjCMxCQSG8SzRalYRMaLyDYRWRaQ9n8iskpElojIZBGp\nEebc9SKyVEQWi8iCorQfDUxBGIaRyERig5gtIpeIiBSy7teAPkFps4DWqtoG+B9wdz7nd1PVdqqa\nXsh2o0ZSagpg7r4Nw0hMIlEQNwD/Bg6LyB4R2SsiBc5mUtW5wK9BaTNV1fe4nQc0KKzAJYmkViKF\nI9aDMAwjISlQQahqVVWtoKoVVbWaF68WhbaHA9PDNQvMFJGFIjIiv0pEZITPkeD27dujIFYAb71F\nxbSKHDkS3WoNwzDKAmEVhIhcGXDcOSjvT8VpVET+CmQBE8MUOUtVOwDnATeKyNnh6lLVcaqarqrp\ntWvXLo5YoQSlWjXYk1CrPwzDMBz59SBuDzj+Z1De8KI2KCLDgAuAIaqqocqo6ibvcxswGehU1PaK\nxbvvUv3gFnbtikvrhmEYcSU/BSFhjkPFI0JE+uBWZvdT1QNhyqSJSFXfMdAbWBaqbMxZsIAauzeY\ngjAMIyHJT0FomONQ8TyIyCTgG6CZiGwUkWtxU2arArO8KawveGXricg079Q6wFci8gMwH/hYVT+J\n7HKiTKVK1NBf2bWrwMs1DMMod+S3UK65iCzB9RZO8o7x4gWuolbVwSGSXwlTdjPQ1zv+EWhbUP0l\nQqVK1GAXa60HYRhGApKfgmhRYlKUVlJTqcEudu9SijiqZhiGUWYJqyBUdUNJClIqqVKFGpUOsmu3\noAqFXipoGIZRhonEWV/i8oc/UGM3ZI6CgwfhmGPiLZBhGEbJEclK6oSmhuctymYyGYaRaESkIESk\nsog0i7UwpY5586j+6lOAKQjDMBKPAhWEiFwILAY+8eLtRGRqrAUrFWRkUOXb2QDs3x9nWQzDMEqY\nSHoQD+JWMu8CUNXFQNMYylR6qFSJNJxmMAVhGEaiEYmCyFTV3UFpibFyLDU1R0Hs2xdnWQzDMEqY\nSGYxLReRK4AkETkFuBn4OrZilRLS0qwHYRhGwhJJD+ImoBVwGHgL2A3cGkuhSg3Vq5NW13k2NwVh\nGEaiUdCe1EnAaFW9E/hryYhUimjenLQl38DxpiAMw0g8CtqTOhs4q4RkKZWkpblPUxCGYSQakdgg\nvvemtf4byHlMquoHMZOqtJCVReVL+iHyMfv3m58NwzASi0gURCqwE+gekKZA+VcQSUnIp7M4JvkI\n+/dXirc0hmEYJUqBCkJVrykJQUolIm4m0xFTEIZhJB4FKggRSQWuxc1kSvWlq2qRtx0tU1SpQtqe\nQ+zfXzXekhiGYZQokUxzfROoC5wLfAE0APbGUqhSRZUqVKlwwBbKGYaRcESiIE5W1fuA/ar6OnA+\ncHpsxSpFtG5NWuWjNovJMIyEIyJXG97nLhFpDVQHjo+kchEZLyLbRGRZQFotEZklImu8z5phzh3q\nlVkjIkMjaS8mvPceVVo3ZW/i9JkMwzCAyBTEOO8hfh8wFVgBPBZh/a8BfYLSRgGzVfUUYLYXz4WI\n1AIewPVUOgEPhFMkJcHxx8O2bfFq3TAMIz4UqCBU9WVV/U1Vv1DVE1X1eFV9IZLKVXUu8GtQcn/g\nde/4deCiEKeeC8xS1V9V9TdgFnkVTcnw0EPUnT+VrVtBE8NFoWEYBhDZLKb7Q6Wr6ugitllHVTO8\n4y1AnRBl6gO/BMQ3emmh5BsBjABo1KhREUXKh02bqLtFOHCgHzNnQsuW0LBh9JsxDMMobUQyxLQ/\nIGQD5wFNotG4qirFdB2uquNUNV1V02vXrh0NsXJTsyYnHXImlD59oFni7atnGEaCEslCuScC4yLy\nODCjGG1uFZETVDVDRE4AQo3ubwK6BsQbAJ8Xo82iU7MmrbKm5EQPHoyLFIZRrjlwACpUgNTUgssa\nJUdEe1IHcQzugV1UpgK+WUlDgQ9DlJkB9BaRmp5xujfFU0pFp2ZNTmJdXJo2yg/Z2fDHP8LatfGW\npHSSlgYnnxxvKYxgItmTeqmILPHCcmA1MDaSykVkEvAN0ExENorItcAYoJeIrAF6enFEJF1EXgZQ\n1V+BvwHfeWG0l1byNG1K8tmdqVHtaFyaN6LLtdc6DyrRZuZMqFwZ3n03dP7ixfD883DFFdFvu7yw\naVO8JTCCES1gao6INA6IZgFbVTUrplIVkfT0dF2wYEFM6m7dGpYvd8c2mym2vPyyG8q76abo1+1T\nDtG+h756q1WD3cEb9AILFsBpp0F6Onz3XeHr370bKlZ0Sqg8Eqv7EgmZmZCSUvLtlhZEZKGqpofK\ni2SIaW9AOAhU8xa71fLWKyQEd9zhPosyUSrUA8MIz/XXw803x7aNQ4diU2+lSrBnD9x6a257VXEf\nfDVqwOmJ47+gxHjrLad4begvNJEoiEXAduB/wBrveKEXYvO6XprYtAmaN+eaKv/m4ovh55/hs88i\nP33RIvfnfued2IlYWsnKgl9+KbhcPDj//NDpq1dDz55E5HvLp/izs/1plSrBmDHw9NPw0kv+9FAK\nYu/ewk16WLo08rJGZPz73+5zyZL4ylFaiURBzAIuVNXjVPVY4AJgpqo2VdUTYyteKSA11T01Nm/O\n6Yb26BH56YsXu8/p06MvWmHZtAkyMsLnX301PPaYe+BlRWEQ8a67XI9r+vTI3qCXLoWNG4vfbiSE\nUvLffw/Nm8Ps2S7kxwcfOMW/YAEsW+ZPr1TJ/90dOOBPz/Qc1gTaP6pVg7Ztiya/UTiOHIEhQ2DN\nmtD50Rza2rMHNm/OnfbOO2XzJTESBXGGqk7zRVR1OvD72IlUyqhZ0ymJjRs56SR/cnp6XvcbR47k\n/aFV8L7ho2Fs3F9+Wbzu7a+/uofOjAjmeDVoAPXq5U3ft8/V8eab8Je/QJs2cNxxsHKlexAGsndv\n7jfm/Pj4Y/fZt6+ruyDatMl/EeL+/fDss+67XL06/J96+/aibRHbq5f/2PcysHYtDB/uHvAiLkyY\nAK+95vJXroR27fznVazovxeBSvbvf3efIjB/Pnz0kYuHemCpujZ8vZhwvx0jf+bPhx9+cMf//a8b\nTurb1/XqfRTX9jFtGgwYkPv81q2hftCy3kGDXChzqGq+ATe99F7c4rgmwF+BGQWdF4/QsWNHjQmt\nWqn2769ZWaqPP67qfg4u+Ni0ycVvuSX3qa+/7tJbtVLdvTtv1cH1FJbZs93555xTcNngtn7+WfWd\nd1TXrs19TcHBR2ami//xj5HJ1qKFv45HHolcvlDfSUaG6qBBufMnTVLdvNkdP/VU7no6dCi4jczM\n3PckKcmfN2OGS+va1cW/+CL0dzN5cvjv7f77Xf6ll0b2/c6cqbpiheo337j04cNd+t69xf+dxIrF\ni1UnTFA9fLh49YS7vvffV33jjeLXOXdu6O/84otd/N//Llzdf/ub6vnn++tr1Ej1X/8KfS379vnT\nHnywaNcSS4AFGu75Hy4jpwDUAp4GvvfC00Ctgs6LR4iZgujfX7VlS1VVPXJEddYs/w3/v/9TXbcu\n949vyRL/qRMm+NOrV89d7YwZRfvjb9um+p//uONPP3Xnd+1a8Hm+tiZOdA/HRo1cfPHi/B9gWVnu\n/O3bXTwpSfXVV1UPHlQ9cEB13rzQ7dWs6a/j5ZddWtu2qjffnLvc0aNO6YR7cGZnh5briSdUp0/3\nx48edfLk950Gnn/11e7ztdfy1j11qurSparNmuX/3UyaFD7v7rvzP9cXNm92svvivmvq2dPJnJER\n+e9kwwbV5GTVRYtyp2dlue/9xx/zP79tW3evNm1yv4+VK8OXDZTrrrsKli0/wl2fL33vXtWNG4te\n55w5ub/zo0dd+iWXaJEURH7KPvhaRowI/btWdf/D885TPf109zvwsXVr7nL796tOmeKXO5oUS0Hk\nKgw18abGlsYQMwXxr3+p3nBDrqS0NP8Nb9gw7w8lO9v9wcM99FTzpv/yi+q0afmLEvgg2b3bryBO\nP909wH3Mnu0e4j/95PJTUnK3F9wTyi9MmKB69tmqy5fnTg+8vjlzXLvffKN6/fW533pB9bHH3I88\n1PcwcWLodv/yF9WFC1WvuSZ0/iOP5E0T8R+vW+fC1KnuHo0eHfk1RxoeeCD6dd50k/ts29bd7zVr\ncrd3993hfx/PPefKXXWV6q5d/vT//teld++u+uijeRWIqlMivnZefNF9XnNN3nI9e6r+6U+q//uf\nv/yAAfn/bn0sXOge9CNHOhkefji0Uv/ll9y/9fbt8/5ufBw5Ejrdd+5vv7keduB37Os5+hTEu+9G\nJn9w3cEh8KXAR69eecutWePyfvwx9/9J1f/CNmKE6rffqjZp4i8TqMgyM90LQXEpkoIA7geae8eV\ngM+AnTjXGD3DnRfPEDMFEYKZM/P/k48dGzr9kkvcQzvwx+97CLdt64737PG3c/iw6qFDrjvbp4/q\n/Pn+c1asUL3tttz1/O9/7jxfvGnT4j+wIg1Hjqimprrj++/Pv+y6darjxrkHQUnJVxbDl1/6FUZg\nyM529/mLL1S//tr/e3n22dzlfPiGIjt3dp8VKuT9Tf/2m/+8KVPcZ+/eecv5yjzxhP+4b9/cZXbu\ndD2MQIJ/875w333+4y++8L+IPP103rK+N+h589w1fPut+7znnvByXnVV3nreesspq4EDXXziRHdO\nZqb7DwX3tI4ccWV833sk965/f9W331Y95ZS8eX36uO/4s8/8afXqufJnn+1PO+mk3Oc99phr/6yz\nVGvUcGlbtuS99sJQVAWxHP9CuhE4X0hJQAtgfrjz4hliqiCOHnW/Ho+DB1XPPLNof/qTT87/3OOO\nU92xQ/XJJ1186NDC1e97iyzp8I9/xKfdaIZAO0RpDj//7H6HvvgLL6h+9VXecocPuzfT1q1dvGNH\nf14wGzb48957z322auXe+JOS3NvxkCGh5enZ0w23vfmmqys52aVv3uyGQ6+9Nvxvftiw3HGfXSBU\nGD7c9aJ8dp3LLvPnde6cuzcRyffoUxAjRrheRGCeqns5C5b73HNL7j77Xrh84cEH8/bO//hHd++L\nSlEVxPcBx+8DNwTEF4U7Lxw7lBUAAB+3SURBVJ4hZgri11+dAWHUqDxZgeOwvgd6IoWbb45eXb4/\na37hrbecYb0o9ftsLuHCmjW5h8GCw6WXqqanu+MePSJvt1q10Mf5BZ99JFyYPTv8wzq/0LKl/3jC\nBDc0uGmT6vr1zuYC7uH+5pvuuGZN1ZdeKrjewLfe4AdYQaFfv6L/Zs44I3f8++/d/zJwuCy/kN8E\nAtXQ9ql4hrvucjbOcPIWhaIqiHlAa6A2btOfpgF5q8KdF88Q0x5Eenro/ra68UzfD/OZZ8Lf3Hff\nDT1cEKtQu7b/+Lzz8ub36eM/Pv9897Bo1crFf/ghd9lvv3VvL1984TpTvvyVK/OX4cQT/cfNmql2\n6RK63MCB7vu77rrQ+SNH+g3dqqrt2vnzAh/8V12leuGF7rhaNZe3YoXqnXe6t+knn3TjuAMGuDIn\nn+xmQAUaY6dPV/3oI9XmzXPbGFTdu4LP1hM8s+mNN3LHjx51M1h8SvQ//3EyBJaZPt1vH+rd25/u\nswFEOwSOZweHwGHTK6/0Hz/8cMH1tmkTWfuRlos0VK+eO37OOc4OtWdP8etetSo296A44frrww8b\nh7PFFERRFcTpwCrP7nBfQHpfYFK48+IZYqogzj8//NzJALKz3Tjwjz+6NzJfVxv8s5tmz3bTX+fN\ny//H4DOggXugBXe9//53Nw0Q/FNKA8c7N2xw8rz6qnswde/u0qdO9Ru3/vxnl+YbL160yD8eW6WK\ne1OePz//aw6We9YsN+RwxRWu3S++cG+oPnxv3/XqufHzV15xXXlV9/Y5dqz7c44d64YQfPIEsnu3\nG0MGN+ywYYNfzqlTXfqnn4aXOTPTGVojMfJdfXX4qb1r1rjrmDrVxQ8dcm2npPjLHDyoOn68f/x8\n/373huubHbZ3r1Me2dnuO/Pdo3g/jHyhb9/o1bVzZ3yvpX//+LTbq1fBPdhIwu9+Fzp98eKCf8fh\niNosptIeYqoghg51d7iQ7Nnj3rYPHgyd36GDuwvXXut/a+zVyxlxMzP9Y+IHDrjyR46ofvBBbsPU\n0aPu4bJli3sgb9gQfjqcz8gWTTZscFNvL71UtVu3yM6ZPNmdU1xWrPArl0ACpwyWNIsXF739nTud\nLSdwiKRCBff517/mnQ58xhkFT1OOZahc2T/sVlBo3NhdY/36ofN9/4VYhU6dwg89DR/ubBiBvbjg\n7z84dO+euxceHGrV8h/fequbEl/cawicOh4YQv0HIsUURDS44w73b4jyROTffvNPeVN1D3jfm6Wq\nM0YuXRrVJo0ygu/P7xum27vXpQcOMfjWw6xZ4x9WOeYY1zObPNnZFz7/PP+HTt26bjZN5cqFf2Cd\neWbo4ctQoU4dJ2vg7KfAoOqGasG9KfuMwT4De926qhUr+uvynTdgQPhZc2edpTkPed/Q4Pr17vuZ\nMkX1ootc787HL7+46dWBdQTPJPL1xBctcsOVvrStW51RuVIl1dtvVx0zxn/Ovfe6/NNOc4rKl75g\ngRu29Mkfamp8oCE+MPhmmvm+u6L/zkxBFB/fAO3IkbFrwzAC8NkmfvpJ9fnnc+dlZbmFlsHvKxkZ\nrhcSzPr1uddT+ML55/vLBC5I9BnTJ0/O/QbdqpVbG3HBBS7erJkbOv3d71xPxrdeYdo01apV3TDh\ntGku7eKLXTtHj+a2ESxd6u9x+aY9n3eeu0bfuPqGDW5dx7p17sF79KhTjvff7++J+toODOPHu8+C\nhkmD2bbNDdfWr++GOwOn3P73v/4Rgd27XS9i3ToX37XL39v3KTtwjw8fCxY4RRA4nd03A/D2252C\nadxYdfBg1e++c/mhFMTRo24atM/+WVRMQUSDQOuiYZQAP//sJgdEk3r13E/YN3X6xRdz53fr5hTC\n7t3+ce2sLDdEEvimffSoe5gFy7d7txtSDWbRImewD2T2bPe2HswHH4RWcgUR6DLGZ9dRjd6w6vLl\nrsdRmOGcvXud0isInzL54gtXf7DBOVg53H574WTPj/wURIEbBgGIyO89P0w5e1ir6hsFnljCxHLD\nIAAuuMB5oMvO9nvhM4wyxLZtzqPv7Nluj5NZs5x7cx++R1BZ/Xm3awedOsG4cfGWJLr4nAoOHw7J\nyfDii9GsO/yGQcmhEoNOfhM4CVgM+Px4KlDqFETM8bka/fRT6N07vrIYRhE4/ngXmjeHc8+FVq1y\n5/s81pZVfO71yxtffw0rVrgtc0uSAhUEkA601Ei6GhEgIs2AQM/oJwL3q+rYgDJdgQ+Bn7ykD1R1\ndDTaLxb/93/w4Yewa1e8JTGMYlGpUl7lYJRezjzThZImEgWxDKgL5LPVTOSo6mqgHYCIJAGbgMkh\nin6pqhdEo82oUaVK3p1ADMMwyimRKIjjgBUiMh847EtU1X5RaL8HsE5VN0ShrpLh8GG3NVSzZjB+\nPFx4obNNGIZhlDMiURAPxrD9QcCkMHlnisgPwGbgTlVdHqqQiIzAOROkUaNGMREyF0lJcOON/u2+\ntm41BWEYRrmkQAWhql/EomERqQj0A+4Okb0IaKyq+0SkLzAFOCWMfOOAceBmMcVC1lwkJ7v9BFev\ndvHzz495k4ZhGPGgwMlsInKGiHwnIvtE5IiIZIvInii0fR7OK+zW4AxV3aOq+7zjaUCKiBwXhTaj\nw9ln+4+3bImfHIZhGDEkktnOzwKDgTVAZeA64LkotD2YMMNLIlJXxE22E5FOnpw7o9BmdBg7Fm65\nxR3ffz8cOhRfeQzDMGJARMthVHUtkKSq2ar6KtCnOI2KSBrQC/ggIO0PIvIHLzoQWObZIJ4BBkVr\nmm1UOOYY+O03f7xyZVi1Kn7yGIZhxIACV1KLyFygJ/AysAU33XWYqraNvXiFI+YrqQPZudPZIg57\nE7t69IDLLnMrWZKSSkYGwzCMYpLfSupIehBXeeX+BOwHGgKXRE+8Msqxx8LChdC9u4vPng033OAW\n0hmGYZQDIvXFVBlo5C1yK7WUaA8ikEDfBEeOQEpKyctgGIZRBIrVgxCRC3F+mD7x4u1EZGp0RSzj\nvPCC//jcc6FxY3j44fjJYxiGEQUisUEsBLoDn6tqey9tqaqeWgLyFYq49SAgtIezUmRXNwzDCEVx\nbRCZqro7KM2efMHs3Amnn+6Pm7dXwzDKOJEoiOUicgWQJCKniMg/ga9jLFfZo1YtmDfPud4A6NMH\nfvzRDT9ZT8IwjDJIJAriJqAVzlHfJGAPcGsshSrT7N3rPg8cgJNOgpEjYc4cf/7TT8OUKfGRzTAM\noxBENIuprBBXG0Qgs2ZB167OPfiRIy7txhtdj2L6dBdXdXnbt7v1FIZhGHGgSDvKFTRTKUruvssn\nvXq5z507Yf58WLQI7rorb7k33oBbb4VffnG9imHDyvZ2XoZhlCvy8+Z6JvALbljpW8CeXIWlShW3\nkC6Ur6bjj3duwvfvd8NQ77zjehJm3DYMo5SQnw2iLnAP0Bp4Guc7aYeqfhErF+Dllj59YOZMWLDA\nv5v69u3w6qvu+B1vB9aPPoLvv4cWLWDHjvjIahiG4RHpSupKOO+r/wc8pKrPxlqwolBqbBAF8cAD\nMLqALbb79YP0dLj3Xht2MgwjZhR5HYSIVBKRi4EJwI04z6qh9o82CsNDDzkj9bRpLj56NCxZkrvM\n1KnOlfjo0fDttzBwYHi34h9/DN98E1uZDcNIOML2IETkDdzw0jTgbVVdVpKCFYUy04MIZO1aNx1W\nBP7xD/jrX/OWOe44N+T0xBNuFtSoUdClC1Ss6AzcjRu7OubPh5o1S/4aDMMos+TXg8hPQRzFeW+F\n3CunBVBVrRZVKaNAmVQQgRw44HoNn33mbBHXXw8vvRS67GefQd++eXsV333nhqaWLoWMDL/Re8AA\nl7Z2bWyvwTCMMkWRFERZpMwriGCyspxn2NNOg/POczvZ7Ylgt9dTT3XKANwQ1THHwJ13uviMGX6l\nkZlpnmcNI8Epri8mI14kJ8OyZW7h3UMPwe7dzt7wyiv+MjffnPc8n3IA1yPxKQdw3mZF3HBUxYrw\n8stu06MDB+DoUVi/Hi6+2K0Iz8qCt95y6YZhJBymIEo7rVpB9er+eN++MHy46wmMGuVsFunp8IU3\n8/iEE/LWceKJedN8jgVfeAF+/3tIS4O6deG662DyZKeU+vWDIUNc3DCMhCNuQ0wish7YC2QDWcFd\nHBER3PqLvsAB3Dani/Krs9wNMRWWUaPgoovgzDP9aWec4XxBVa4cWR0VK/rdg/i4804YMcIZy3ft\ngqZNXfr337v1HCLw7rvh7SWGYZRaSqUNwlMQ6aoackWYiPTFOQrsC5wOPK2qp4cq6yPhFYSP7dud\nQqhSxZ82bx7cfTd06wbr1jk3H8HUrw+bNkXWxgcfuKGoQL7/Htq1K7rchmGUOGXVBtEfeEMd84Aa\nIhJi/MTIQ+3auZUD+HsS998Pzz/v3vb374fly6FHD3jvPf/+2i1bFtzGxRfnVQbt28P777uV4U2b\nuuNQnHSSm7L78cdw8GDhr88wjBIhnj2In4DfcFNoX1TVcUH5HwFjVPUrLz4b+IuqLggqNwIYAdCo\nUaOOGzZsKAnxyye7d8P48XDDDc6I3a1b3jJNmjhDNsBrrzkHg8E0bOjWZwA89hjcfjv861/Qpg10\n7AhVq+Yuv3o11KuXV6kZhhFziuTNtQQ4S1U3icjxwCwRWaWqcwtbiadYxoEbYoq2kAlF9epw223u\nuGtXt/nRpk3OK62q81J76BB8+aV7yLdr52ZZgVMq06bBLbf4lQPAn//sjOS+2VYNGuRtt1kzmDQJ\nLr/ctaPq3JGMHOmGvVatcnVUrBjTyzcMIzelYh2EiDwI7FPVxwPSXsTtgz3Ji68GuqpqRrh6zAYR\nZ3bscMNbgUyY4BTNHXfkf27XrnDKKW7o6513nLI44QQYOhTGjHEL/Q4ccDOuZs1yyumf/4zZpRhG\nolDqjNQikgZUUNW93vEsYLSqfhJQ5nzgT/iN1M+oaqf86jUFUQrIyHCL76ZOdbOe+vVzPYt58+DD\nD6FOHfeABxfv37/obfXq5abpNm3qZlIdPuxsI6NHu6EsnzypqaFdkGRluXPS0ooug2GUcUqjgjgR\nv9O/ZOAtVf27iPwBQFVf8Ka5Pgv0wU1zvSbY/hCMKYhSTnY2VKjgFt5lZroH95AhbjFeIIF2jkjJ\nyIDFi92K8zZt4IcfXLqIUw6//pr3nM6d3WyvTz8tytUYRrmg1NkgVPVHoG2I9BcCjhXnQdYoLyQl\n+T99xxMmuCm3K1c620PNms41yLRpcNVVbk3HhRfCww+7B//GjS4E41sgWLeumyWVmQl/+5tL++03\nmD3bzdYK5Ouv3eeyZU4pDR3qZlc1aRLtKzeMMkmpsEFEC+tBlDP273eG6ZQU54OqYkXX61ixAk4+\n2W3TeuutUKOGUzDgZl7NmeM2afrEG7H09VpmznTK5bnn4O23nc3Dxx13OOXQt6+b8utbWHjokGu3\nQmmeEW4YRaesroMwEp20NL8zwWrVnHIAt06jYkW47DLYvNkpjD//2eX5lMonn/jr8fmSeu4556Zk\n4cLcygHgxRfd57Rprgcj4pwjVq4MTz/tpgCD6+XMnu1fRb53L+zb59Z0PP64fxaWYZQDrAdhlA8O\nHXLrMq64wimIJ590fqqeeMJNlR00qPhtvPCCG666/343hOVbed6qlVtwCHDPPW5fj6ws/zCaj+xs\nNxMreB2IYcSRUmekjhWmIIwcsrPdLn3t27v4rl1umGjRIv8CwCuvdE4OA9dtgLN33HuvP969u9t/\nozBMn+42ddqyxa3hEHHDWE8+6WZOhVrT8dFHrnfy1FOFa8swikGpM1IbRsxJSvIrB3B2CnDrLaZO\ndXtmNGni1m7UquXyMjLcau7q1d3Q0aOPwn//6/bjOPHE0MbxcJx3nv/47LNhbsAa0Ecfdb2bChXc\nGpFevZwBfuJEl//kk6H3IV+yxO0emJbm5LPdA40YYz0Iw4iEffucAhkxwg0TzZzp3vQfesjlBw4z\nAXTo4Hor4RgyxK8QgmnUyG3q1LWr62106OCUWOPGLr99e2cDycpy8XHjXG8o3NDV3r1uD5Gbb85t\nbF+82CnAG22yYCJjQ0yGESt++sm97fscJHbt6mZRvfyyM4T/5z/ODuJj2DD3cPet08iPZ57xuyip\nXDmvY8Pjj4dt2/zxP/zBuWofN86lp6U5Q/q0af56unVzXn179nQuTtascUZ8X48lO9spttNOK+o3\nYpQx8lMQqGq5CR07dlTDiBv/+Y/q1q150xs1Uv3d71S3bXPxBx90c51GjVLdv1913Trf3CfVihX9\nx1dc4T+OJJx0kvu87rqCy3bp4j6bNcst65//7C/z6aex/86MuAMs0DDPVOtBGEZJs3u322Bp+HD/\nTKcnnnA9kObNnTfc+fNh4EBnuxDxu2IXcY/vs85ydovXXnNDXuBWhPfsmX/bwRtCVark1ox8+KGb\n1puZCXfd5fKuucZtFlWQ+/enn3ZTgzt3zlt2+nQnk+19XmqxISbDKOucfrozZj/8sPNl1aWLWxdy\n5IjbErZhQ+fn6uSTw9fxu9/B//5X+La//94NPWVmuplY06Y520VGhjPA/+53/rK//73zxCvi3JsM\nGgT33ef8YxmlElMQhpEoTJnilMkJJ7gNm2bPdqvDL7jAGaX79nUOFKtUcQb3Zs0K30Z6uluguHlz\nZOUHDoR//ztv+gsvuJlkBw+6cMUV4etQdQsiW7UqvLxGvpgNwjAMx9GjuePbtqneeafqwIGqJ5+s\nWreu6vDh4W0XlSsXzi4Crv6uXVUvu0w1M9O1u3p13nJ9+6r+/HNouV980V/u+edd2g8/qP7xj6pZ\nWUX/Pg4fzl1nAoLZIAzDKBTTprk3+k6d4JFHXK/h3XfdMNOQIaHPefttt49HerpzZ3LffW61+dSp\nrj5ww2Q+d++huO8+t7vgWWc5e4aIPwQyYwace647vuMOaNHC7x04kB07nH3kmGPczoVffQXXXuvP\n37LF9bbCefxNAGyIyTCM6KDqlERKirNnNGvm7BP79rkFhuCmze7a5V+A+OmnTik89ljR2rzySuf1\nN5A6ddwiw2Dq1oUNG9xw1MGDziYCbhLAjBlu/UpmJiR7a4RXrXLKpXVrtxDxyBFnuM/OdhtV9enj\n31uknGLO+gzDiA4ibiaUiN9+kZTkVw7gFuP5lAO4WUyPPupmZC1dCmvXOqN1RoabJeWjbdvcK859\nBCsHCK0cwPUIRo1yiwl9ygFcL6NrV3d83XX+XkmLFi5tzBg3eys1FS69FAYPdu5WPvzQKY5163K3\nM2aMs+cE8sgj7tpDrYIvq4QbeyqLwWwQhlHGyM52dpGNG1V37HBpQ4c6u8DkyapNm6r++KNqq1Yu\nbfZs1dGjw9s7LrlE9YYbCm8nadq0YDvLhg3OZvHaa/602bPd2pdFi3KXvfFG1Xnz8r/25cv9NqHD\nh1U3bYrpVx0O8rFBxP2hHs1gCsIwygH796suXpw7bc8e94D24XuwPvKIaoMGqt9+685TVZ06VfXK\nK/0P661bVR9/PDJFUb++qztwwWBgGDdOtUYNf9ynuAJDgwb+42uvdTL99JPqkSOqu3apvvmm6r/+\n5fIff9y117Oni2dnq+7erfr11/l/R1995RY5LlpU7K/bFIRhGInHunW5Z0VlZKhefrlqp06qJ56o\nOnOm6t69qhMm+B/ovtXuqqodO4ZWEo0b+48nTixY6Zxyiv84v96PT7n4VsSPHKn6xRdOlp9+Ut23\nzymYQ4dUx451ZaZMKfbXVKoUBNAQmAOsAJYDt4Qo0xXYDSz2wv2R1G0KwjCMIvHBB6pz5+ZOW7TI\nKYkbbnCK5uOP3SOze3f/A/3oUdUVK1Rbt877sC9IGRQ1+IbgAkNGRpEvPT8FEQ9331nAHaq6SESq\nAgtFZJaqrggq96WqXhAH+QzDSDQGDMib1r49BM6KbNjQzXLKznbOE++4w2/oXrrUlTlyxO1mmJ0N\nF13knDk2aOCM8f/6l3OoeP31sH69m8b7xhvuvL/9zU3xjYTXX8+b9s03oa+hmMR9mquIfAg8q6qz\nAtK6AncWVkHYNFfDMEqEgwfdjKfizFg6eNDNuvryS7jqKud596GH3F4h1au7NRwdOrj1Ga+/Dm+9\n5abqjhnjZmoFsmpV0VbFU4rXQYhIE2Au0FpV9wSkdwXeBzYCm3HKYnmIKnJhCsIwjHLLkSPOXcpp\np7mezXHHub0+qlZ1e4VUKNqqhVK5o5yIVMEpgVsDlYPHIqCxqu4Tkb7AFOCU4Dq8ekYAIwAaNWoU\nQ4kNwzDiSMWKbmU7lNh+HXFZKCciKTjlMFFVPwjOV9U9qrrPO54GpIjIcaHqUtVxqpququm1a9eO\nqdyGYRiJRIkrCBER4BVgpao+GaZMXa8cItIJJ+fOkpPSMAzDiMcQU2fgKmCpiCz20u4BGgGo6gvA\nQGCkiGQBB4FBGm9rumEYRoJR4gpCVb8C8jX9q+qzwLMlI5FhGIYRCnPWZxiGYYTEFIRhGIYRElMQ\nhmEYRkhMQRiGYRghMQVhGIZhhMQUhGEYhhESUxCGYRhGSExBGIZhGCExBWEYhmGExBSEYRiGERJT\nEIZhGEZITEEYhmEYITEFYRiGYYTEFIRhGIYRElMQhmEYRkhMQRiGYRghMQVhGIZhhMQUhGEYhhES\nUxCGYRhGSOKiIESkj4isFpG1IjIqRH4lEXnHy/9WRJqUvJSGYRiJTYkrCBFJAp4DzgNaAoNFpGVQ\nsWuB31T1ZOAp4NGSldIwDMOIRw+iE7BWVX9U1SPA20D/oDL9gde94/eAHiIiJSijYRhGwpMchzbr\nA78ExDcCp4cro6pZIrIbOBbYEVyZiIwARnjRfSKyuohyHReq/nKOXXNiYNdc/inO9TYOlxEPBRFV\nVHUcMK649YjIAlVNj4JIZQa75sTArrn8E6vrjccQ0yagYUC8gZcWsoyIJAPVgZ0lIp1hGIYBxEdB\nfAecIiJNRaQiMAiYGlRmKjDUOx4IfKaqWoIyGoZhJDwlPsTk2RT+BMwAkoDxqrpcREYDC1R1KvAK\n8KaIrAV+xSmRWFPsYaoyiF1zYmDXXP6JyfWKvZgbhmEYobCV1IZhGEZITEEYhmEYIUl4BVGQ24+y\niog0FJE5IrJCRJaLyC1eei0RmSUia7zPml66iMgz3vewREQ6xPcKio6IJInI9yLykRdv6rlsWeu5\ncKnopZcLly4iUkNE3hORVSKyUkTOLO/3WURu837Xy0Rkkoiklrf7LCLjRWSbiCwLSCv0fRWRoV75\nNSIyNFRb4UhoBRGh24+yShZwh6q2BM4AbvSubRQwW1VPAWZ7cXDfwSleGAE8X/IiR41bgJUB8UeB\npzzXLb/hXLlA+XHp8jTwiao2B9rirr3c3mcRqQ/cDKSramvcZJdBlL/7/BrQJyitUPdVRGoBD+AW\nI3cCHvAplYhQ1YQNwJnAjID43cDd8ZYrRtf6IdALWA2c4KWdAKz2jl8EBgeUzylXlgJuXc1soDvw\nESC4FabJwfccN5PuTO842Ssn8b6GQl5vdeCnYLnL833G72mhlnffPgLOLY/3GWgCLCvqfQUGAy8G\npOcqV1BI6B4Eod1+1I+TLDHD61K3B74F6qhqhpe1BajjHZeX72Is8GfgqBc/FtilqllePPC6crl0\nAXwuXcoSTYHtwKvesNrLIpJGOb7PqroJeBz4GcjA3beFlO/77KOw97VY9zvRFUS5R0SqAO8Dt6rq\nnsA8da8U5Waes4hcAGxT1YXxlqUESQY6AM+rantgP/5hB6Bc3ueaOIeeTYF6QBp5h2LKPSVxXxNd\nQUTi9qPMIiIpOOUwUVU/8JK3isgJXv4JwDYvvTx8F52BfiKyHucluDtufL6G57IFcl9XeXDpshHY\nqKrfevH3cAqjPN/nnsBPqrpdVTOBD3D3vjzfZx+Fva/Fut+JriAicftRJhERwa1IX6mqTwZkBbox\nGYqzTfjSr/ZmQ5wB7A7oypYJVPVuVW2gqk1w9/IzVR0CzMG5bIG811ymXbqo6hbgFxFp5iX1AFZQ\nju8zbmjpDBE5xvud+6653N7nAAp7X2cAvUWkptfz6u2lRUa8jTDxDkBf4H/AOuCv8ZYnitd1Fq77\nuQRY7IW+uLHX2cAa4FOglldecDO61gFLcTNE4n4dxbj+rsBH3vGJwHxgLfBvoJKXnurF13r5J8Zb\n7iJeaztggXevpwA1y/t9Bh4CVgHLgDeBSuXtPgOTcDaWTFxP8dqi3FdguHfta4FrCiODudowDMMw\nQpLoQ0yGYRhGGExBGIZhGCExBWEYhmGExBSEYRiGERJTEIZhGEZITEEYRiEQkWwRWRwQouYBWESa\nBHruNIx4U+JbjhpGGeegqraLtxCGURJYD8IwooCIrBeRx0RkqYjMF5GTvfQmIvKZ56N/tog08tLr\niMhkEfnBC7/3qkoSkZe8vQ5mikjluF2UkfCYgjCMwlE5aIjp8oC83ap6KvAszqsswD+B11W1DTAR\neMZLfwb4QlXb4nwnLffSTwGeU9VWwC7gkhhfj2GExVZSG0YhEJF9qlolRPp6oLuq/ug5SdyiqseK\nyA6c//5MLz1DVY8Tke1AA1U9HFBHE2CWus1gEJG/ACmq+nDsr8ww8mI9CMOIHhrmuDAcDjjOxuyE\nRhwxBWEY0ePygM9vvOOvcZ5lAYYAX3rHs4GRkLOHdvWSEtIwIsXeTgyjcFQWkcUB8U9U1TfVtaaI\nLMH1AgZ7aTfhdnu7C7fz2zVe+i3AOBG5FtdTGInz3GkYpQazQRhGFPBsEOmquiPeshhGtLAhJsMw\nDCMk1oMwDMMwQmI9CMMwDCMkpiAMwzCMkJiCMAzDMEJiCsIwDMMIiSkIwzAMIyT/D6SufNjzpNfP\nAAAAAElFTkSuQmCC\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "cS6oqzXxT3AJ",
        "colab_type": "code",
        "outputId": "5052ab12-d61a-4bb0-9e61-7491436b3525",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 283
        }
      },
      "source": [
        "model = build_model()\n",
        "model.compile(loss='mse',\n",
        "                optimizer=optimizer,\n",
        "                metrics=['mae', 'mse'])\n",
        "\n",
        "early_stop = tf.keras.callbacks.EarlyStopping(\n",
        "      monitor='val_loss', patience=10)\n",
        "\n",
        "history = model.fit(normed_train_data, train_labels, epochs=EPOCHS,\n",
        "                    validation_split = 0.2, verbose=0,\n",
        "                    callbacks=[early_stop] )\n",
        "\n",
        "plot_history(history)\n"
      ],
      "execution_count": 21,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAAEKCAYAAAAIO8L1AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nrkJggg==\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "XylL5FAZaFqE",
        "colab_type": "code",
        "outputId": "8c39aecd-b183-47df-d268-0fc6194466cd",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 89
        }
      },
      "source": [
        "loss, mse, mae = model.evaluate(normed_test_data, test_labels)\n",
        "print(\"Testing set Mean Abs Error: {:5.2f} MPG\".format(mae))\n",
        "print(\"Testing set Mean Sqr Error: {:5.2f} MPG\".format(mse))"
      ],
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "78/78 [==============================] - 0s 159us/sample - loss: 5.7236 - mae: 1.8296 - mse: 5.7236\n",
            "Testing set Mean Abs Error:  5.72 MPG\n",
            "Testing set Mean Sqr Error:  1.83 MPG\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "skSie-dmWH7X",
        "colab_type": "text"
      },
      "source": [
        "Evaluación del entrenamiento con MAE"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CE_4ZyUyF9t0",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "model = build_model()\n",
        "model.compile(loss='mae',\n",
        "                optimizer=optimizer,\n",
        "                metrics=['mae', 'mse'])\n",
        "\n",
        "early_stop = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=10)\n",
        "\n",
        "history = model.fit(normed_train_data, train_labels, epochs=EPOCHS,\n",
        "                    validation_split = 0.2, verbose=0,\n",
        "                    callbacks=[early_stop] )\n",
        "\n",
        "\n"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "fyNghoi97tyg",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 283
        },
        "outputId": "6968e41d-4c40-4705-d46d-5ad94ee4d8d4"
      },
      "source": [
        "plot_history(history)"
      ],
      "execution_count": 28,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAAEKCAYAAAAIO8L1AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nxvhlCcIYY4xfliCMMcb4ZQnCGGOMX/8PHy8AsQ34+2cAAAAASUVORK5CYII=\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "O-r0WJONIMf7",
        "colab_type": "code",
        "outputId": "e64da04a-f608-4ddf-a63b-9d007249448e",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 89
        }
      },
      "source": [
        "loss, mse, mae = model.evaluate(normed_test_data, test_labels)\n",
        "print(\"Testing set Mean Abs Error: {:5.2f} MPG\".format(mae))\n",
        "print(\"Testing set Mean Sqr Error: {:5.2f} MPG\".format(mse))"
      ],
      "execution_count": 29,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "78/78 [==============================] - 0s 157us/sample - loss: 1.8136 - mae: 1.8136 - mse: 6.5030\n",
            "Testing set Mean Abs Error:  6.50 MPG\n",
            "Testing set Mean Sqr Error:  1.81 MPG\n"
          ],
          "name": "stdout"
        }
      ]
    }
  ]
}