--- a
+++ b/Smoking.ipynb
@@ -0,0 +1,1870 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "toc_visible": true,
+      "mount_file_id": "1GlsKowXVX2qDb5s3jKit3KDki7VUaAxW",
+      "authorship_tag": "ABX9TyPXntpjthNXQd6yOVHnRJUs",
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/nribot/smoking/blob/main/Smoking.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Instrucciones\n",
+        "* Leer archivo con los datos\n",
+        "* Preprocesado de los datos: eleimiar columnos que no nos interesen, limpiar * valores perdidos, cambiar etiqueta de las clases a 0, 1, 2, 3, .... en caso de * que sean strings, codificar o transformar columnas que sean texto, ....\n",
+        "* Separar entre X e Y\n",
+        "* Separar en entrenamiento y test (si no nos lo dan por defecto)\n",
+        "* Normalizar\n",
+        "* Entrenar los modelos que queramos de clasificación: Predicciones, evaluación * (alguna métrica de clasificación que hemos visto o varias de ellas)\n",
+        "* Comparar los resultados de todos los modeos y quedarnos con el mejor.\n",
+        "* Añadir validación cruzada a los hiperparámetros que considere oportuno!!!"
+      ],
+      "metadata": {
+        "id": "zUhHa46Z4lkT"
+      }
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 32,
+      "metadata": {
+        "id": "iNqljQXq4ax8"
+      },
+      "outputs": [],
+      "source": [
+        "# Para visualizar gráficas en notebooks\n",
+        "%matplotlib inline \n",
+        "\n",
+        "# Para acceder al archivo guardado en drive\n",
+        "from google.colab import drive\n",
+        "\n",
+        "# Librerías utilizadas\n",
+        "import random\n",
+        "import matplotlib.pyplot as plt\n",
+        "import numpy as np\n",
+        "import pandas as pd\n",
+        "from joblib import Parallel, delayed\n",
+        "from sklearn import datasets\n",
+        "from sklearn.ensemble import RandomForestClassifier\n",
+        "from sklearn.metrics import accuracy_score\n",
+        "from sklearn.metrics import ConfusionMatrixDisplay\n",
+        "from sklearn.metrics import roc_auc_score\n",
+        "from sklearn.model_selection import GridSearchCV\n",
+        "from sklearn.model_selection import ParameterGrid\n",
+        "from sklearn.model_selection import train_test_split\n",
+        "from sklearn.neighbors import KNeighborsClassifier\n",
+        "from sklearn.preprocessing import StandardScaler"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "### Carga de datos\n",
+        "\n",
+        "\n",
+        "Datos obtenidos de https://www.kaggle.com/datasets/kukuroo3/body-signal-of-smoking\n",
+        "\n",
+        "La variable de salida es `smoking` que tiene dos valores en este dataset, según la documentación:\n",
+        "* 0 = no han fumado nunca\n",
+        "* 1 = fumaban anteriormente (pero ya no)\n",
+        "\n",
+        "Había una tercera categoría, fumadores activos, que se ha eliminado ya del dataset."
+      ],
+      "metadata": {
+        "id": "qZqHXxMn4-vc"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "drive.mount('/content/drive')\n",
+        "\n",
+        "data = pd.read_csv('drive/MyDrive/Datasets/smoking.csv')\n",
+        "\n",
+        "data.head()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 334
+        },
+        "id": "EN7gozHH49ej",
+        "outputId": "9f434344-4fe1-48ba-95c2-ab63ce919d01"
+      },
+      "execution_count": 33,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
+          ]
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "   ID gender  age  height(cm)  weight(kg)  waist(cm)  eyesight(left)  \\\n",
+              "0   0      F   40         155          60       81.3             1.2   \n",
+              "1   1      F   40         160          60       81.0             0.8   \n",
+              "2   2      M   55         170          60       80.0             0.8   \n",
+              "3   3      M   40         165          70       88.0             1.5   \n",
+              "4   4      F   40         155          60       86.0             1.0   \n",
+              "\n",
+              "   eyesight(right)  hearing(left)  hearing(right)  ...  hemoglobin  \\\n",
+              "0              1.0            1.0             1.0  ...        12.9   \n",
+              "1              0.6            1.0             1.0  ...        12.7   \n",
+              "2              0.8            1.0             1.0  ...        15.8   \n",
+              "3              1.5            1.0             1.0  ...        14.7   \n",
+              "4              1.0            1.0             1.0  ...        12.5   \n",
+              "\n",
+              "   Urine protein  serum creatinine   AST   ALT   Gtp  oral  dental caries  \\\n",
+              "0            1.0               0.7  18.0  19.0  27.0     Y              0   \n",
+              "1            1.0               0.6  22.0  19.0  18.0     Y              0   \n",
+              "2            1.0               1.0  21.0  16.0  22.0     Y              0   \n",
+              "3            1.0               1.0  19.0  26.0  18.0     Y              0   \n",
+              "4            1.0               0.6  16.0  14.0  22.0     Y              0   \n",
+              "\n",
+              "   tartar  smoking  \n",
+              "0       Y        0  \n",
+              "1       Y        0  \n",
+              "2       N        1  \n",
+              "3       Y        0  \n",
+              "4       N        0  \n",
+              "\n",
+              "[5 rows x 27 columns]"
+            ],
+            "text/html": [
+              "\n",
+              "  <div id=\"df-d44c4682-b99f-4e8d-b63c-ca95a53c3a07\">\n",
+              "    <div class=\"colab-df-container\">\n",
+              "      <div>\n",
+              "<style scoped>\n",
+              "    .dataframe tbody tr th:only-of-type {\n",
+              "        vertical-align: middle;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe tbody tr th {\n",
+              "        vertical-align: top;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe thead th {\n",
+              "        text-align: right;\n",
+              "    }\n",
+              "</style>\n",
+              "<table border=\"1\" class=\"dataframe\">\n",
+              "  <thead>\n",
+              "    <tr style=\"text-align: right;\">\n",
+              "      <th></th>\n",
+              "      <th>ID</th>\n",
+              "      <th>gender</th>\n",
+              "      <th>age</th>\n",
+              "      <th>height(cm)</th>\n",
+              "      <th>weight(kg)</th>\n",
+              "      <th>waist(cm)</th>\n",
+              "      <th>eyesight(left)</th>\n",
+              "      <th>eyesight(right)</th>\n",
+              "      <th>hearing(left)</th>\n",
+              "      <th>hearing(right)</th>\n",
+              "      <th>...</th>\n",
+              "      <th>hemoglobin</th>\n",
+              "      <th>Urine protein</th>\n",
+              "      <th>serum creatinine</th>\n",
+              "      <th>AST</th>\n",
+              "      <th>ALT</th>\n",
+              "      <th>Gtp</th>\n",
+              "      <th>oral</th>\n",
+              "      <th>dental caries</th>\n",
+              "      <th>tartar</th>\n",
+              "      <th>smoking</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>0</td>\n",
+              "      <td>F</td>\n",
+              "      <td>40</td>\n",
+              "      <td>155</td>\n",
+              "      <td>60</td>\n",
+              "      <td>81.3</td>\n",
+              "      <td>1.2</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>...</td>\n",
+              "      <td>12.9</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>0.7</td>\n",
+              "      <td>18.0</td>\n",
+              "      <td>19.0</td>\n",
+              "      <td>27.0</td>\n",
+              "      <td>Y</td>\n",
+              "      <td>0</td>\n",
+              "      <td>Y</td>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>1</td>\n",
+              "      <td>F</td>\n",
+              "      <td>40</td>\n",
+              "      <td>160</td>\n",
+              "      <td>60</td>\n",
+              "      <td>81.0</td>\n",
+              "      <td>0.8</td>\n",
+              "      <td>0.6</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>...</td>\n",
+              "      <td>12.7</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>0.6</td>\n",
+              "      <td>22.0</td>\n",
+              "      <td>19.0</td>\n",
+              "      <td>18.0</td>\n",
+              "      <td>Y</td>\n",
+              "      <td>0</td>\n",
+              "      <td>Y</td>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>2</td>\n",
+              "      <td>M</td>\n",
+              "      <td>55</td>\n",
+              "      <td>170</td>\n",
+              "      <td>60</td>\n",
+              "      <td>80.0</td>\n",
+              "      <td>0.8</td>\n",
+              "      <td>0.8</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>...</td>\n",
+              "      <td>15.8</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>21.0</td>\n",
+              "      <td>16.0</td>\n",
+              "      <td>22.0</td>\n",
+              "      <td>Y</td>\n",
+              "      <td>0</td>\n",
+              "      <td>N</td>\n",
+              "      <td>1</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>3</td>\n",
+              "      <td>M</td>\n",
+              "      <td>40</td>\n",
+              "      <td>165</td>\n",
+              "      <td>70</td>\n",
+              "      <td>88.0</td>\n",
+              "      <td>1.5</td>\n",
+              "      <td>1.5</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>...</td>\n",
+              "      <td>14.7</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>19.0</td>\n",
+              "      <td>26.0</td>\n",
+              "      <td>18.0</td>\n",
+              "      <td>Y</td>\n",
+              "      <td>0</td>\n",
+              "      <td>Y</td>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>4</td>\n",
+              "      <td>F</td>\n",
+              "      <td>40</td>\n",
+              "      <td>155</td>\n",
+              "      <td>60</td>\n",
+              "      <td>86.0</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>...</td>\n",
+              "      <td>12.5</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>0.6</td>\n",
+              "      <td>16.0</td>\n",
+              "      <td>14.0</td>\n",
+              "      <td>22.0</td>\n",
+              "      <td>Y</td>\n",
+              "      <td>0</td>\n",
+              "      <td>N</td>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "<p>5 rows × 27 columns</p>\n",
+              "</div>\n",
+              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-d44c4682-b99f-4e8d-b63c-ca95a53c3a07')\"\n",
+              "              title=\"Convert this dataframe to an interactive table.\"\n",
+              "              style=\"display:none;\">\n",
+              "        \n",
+              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
+              "       width=\"24px\">\n",
+              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
+              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
+              "  </svg>\n",
+              "      </button>\n",
+              "      \n",
+              "  <style>\n",
+              "    .colab-df-container {\n",
+              "      display:flex;\n",
+              "      flex-wrap:wrap;\n",
+              "      gap: 12px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert {\n",
+              "      background-color: #E8F0FE;\n",
+              "      border: none;\n",
+              "      border-radius: 50%;\n",
+              "      cursor: pointer;\n",
+              "      display: none;\n",
+              "      fill: #1967D2;\n",
+              "      height: 32px;\n",
+              "      padding: 0 0 0 0;\n",
+              "      width: 32px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert:hover {\n",
+              "      background-color: #E2EBFA;\n",
+              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+              "      fill: #174EA6;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert {\n",
+              "      background-color: #3B4455;\n",
+              "      fill: #D2E3FC;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert:hover {\n",
+              "      background-color: #434B5C;\n",
+              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
+              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
+              "      fill: #FFFFFF;\n",
+              "    }\n",
+              "  </style>\n",
+              "\n",
+              "      <script>\n",
+              "        const buttonEl =\n",
+              "          document.querySelector('#df-d44c4682-b99f-4e8d-b63c-ca95a53c3a07 button.colab-df-convert');\n",
+              "        buttonEl.style.display =\n",
+              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "\n",
+              "        async function convertToInteractive(key) {\n",
+              "          const element = document.querySelector('#df-d44c4682-b99f-4e8d-b63c-ca95a53c3a07');\n",
+              "          const dataTable =\n",
+              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
+              "                                                     [key], {});\n",
+              "          if (!dataTable) return;\n",
+              "\n",
+              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
+              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
+              "            + ' to learn more about interactive tables.';\n",
+              "          element.innerHTML = '';\n",
+              "          dataTable['output_type'] = 'display_data';\n",
+              "          await google.colab.output.renderOutput(dataTable, element);\n",
+              "          const docLink = document.createElement('div');\n",
+              "          docLink.innerHTML = docLinkHtml;\n",
+              "          element.appendChild(docLink);\n",
+              "        }\n",
+              "      </script>\n",
+              "    </div>\n",
+              "  </div>\n",
+              "  "
+            ]
+          },
+          "metadata": {},
+          "execution_count": 33
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "original_dim = data.shape\n",
+        "print(\"El dataset contiene\", data.shape[0], \"observaciones de\", data.shape[1], \"variables.\")"
+      ],
+      "metadata": {
+        "id": "tpRRlhfj9giM",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "301fee90-3d39-4db6-9ec0-4b8ab3cf16b5"
+      },
+      "execution_count": 34,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "El dataset contiene 55692 observaciones de 27 variables.\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Examinamos el tipo de las columnas y si hay nulos:"
+      ],
+      "metadata": {
+        "id": "gZ4BBVUz91Ht"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "data.info()"
+      ],
+      "metadata": {
+        "id": "v4ng3IL_6Pd1",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "13e57a78-4601-41fe-d852-1e973cf3142f"
+      },
+      "execution_count": 35,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "<class 'pandas.core.frame.DataFrame'>\n",
+            "RangeIndex: 55692 entries, 0 to 55691\n",
+            "Data columns (total 27 columns):\n",
+            " #   Column               Non-Null Count  Dtype  \n",
+            "---  ------               --------------  -----  \n",
+            " 0   ID                   55692 non-null  int64  \n",
+            " 1   gender               55692 non-null  object \n",
+            " 2   age                  55692 non-null  int64  \n",
+            " 3   height(cm)           55692 non-null  int64  \n",
+            " 4   weight(kg)           55692 non-null  int64  \n",
+            " 5   waist(cm)            55692 non-null  float64\n",
+            " 6   eyesight(left)       55692 non-null  float64\n",
+            " 7   eyesight(right)      55692 non-null  float64\n",
+            " 8   hearing(left)        55692 non-null  float64\n",
+            " 9   hearing(right)       55692 non-null  float64\n",
+            " 10  systolic             55692 non-null  float64\n",
+            " 11  relaxation           55692 non-null  float64\n",
+            " 12  fasting blood sugar  55692 non-null  float64\n",
+            " 13  Cholesterol          55692 non-null  float64\n",
+            " 14  triglyceride         55692 non-null  float64\n",
+            " 15  HDL                  55692 non-null  float64\n",
+            " 16  LDL                  55692 non-null  float64\n",
+            " 17  hemoglobin           55692 non-null  float64\n",
+            " 18  Urine protein        55692 non-null  float64\n",
+            " 19  serum creatinine     55692 non-null  float64\n",
+            " 20  AST                  55692 non-null  float64\n",
+            " 21  ALT                  55692 non-null  float64\n",
+            " 22  Gtp                  55692 non-null  float64\n",
+            " 23  oral                 55692 non-null  object \n",
+            " 24  dental caries        55692 non-null  int64  \n",
+            " 25  tartar               55692 non-null  object \n",
+            " 26  smoking              55692 non-null  int64  \n",
+            "dtypes: float64(18), int64(6), object(3)\n",
+            "memory usage: 11.5+ MB\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "### Examen y tranformación de los datos"
+      ],
+      "metadata": {
+        "id": "TZUCuEFnn7_L"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Visualizamos las columnas categóricas, incluyendo la variable de salida.\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "pu-6JhiUzhFi"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "categorical = ['gender', 'oral', 'tartar', 'smoking']\n",
+        "\n",
+        "for i in categorical:\n",
+        "  idx = categorical.index(i)\n",
+        "  ax1 = plt.subplot(2,2, idx+1)\n",
+        "  ax1.pie(data[i].value_counts(), \n",
+        "          labels=data[i].unique(),\n",
+        "          autopct = '%1.1f%%'\n",
+        "          )\n",
+        "  ax1.set_title(i)"
+      ],
+      "metadata": {
+        "id": "AnoVGVYY1d5c",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 428
+        },
+        "outputId": "15f8d052-c1a7-4f11-88cf-4239d24c3d95"
+      },
+      "execution_count": 36,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 4 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Vemos que la categoría `oral` solo tiene un valor, la eliminamos junto con la variable `ID`."
+      ],
+      "metadata": {
+        "id": "TBwMqQKW3Bdk"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "data = data.drop(labels=['ID', 'oral'], axis=1)\n",
+        "data.shape"
+      ],
+      "metadata": {
+        "id": "3XORX_tb3ZoO",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "6d03c6dd-2b5c-4bba-a5af-1e3e9c0694a5"
+      },
+      "execution_count": 37,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "(55692, 25)"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 37
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Además, vemos que el dataset tiene mucha más presencia de personas no fumadoras y de mujeres, vamos a examinar si hay alguna relación."
+      ],
+      "metadata": {
+        "id": "PudaPLh_3L0s"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "CrosstabResult=pd.crosstab(index=data['gender'],columns=data['smoking'])\n",
+        "print(CrosstabResult)"
+      ],
+      "metadata": {
+        "id": "PbU4k_io9-Ih",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "9f64cb4b-ccd6-4d03-c956-343ca5caf2ed"
+      },
+      "execution_count": 38,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "smoking      0      1\n",
+            "gender               \n",
+            "F        19432    859\n",
+            "M        15805  19596\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Parece que sí hay una clara distribución por sexo: la gran mayoría de fumadores previos son hombres."
+      ],
+      "metadata": {
+        "id": "i8Gz1K0IMV9h"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Las columnas 'gender' y 'tartar' solo contienen dos categorías; las cambiamos a variables numéricas.\n",
+        "\n",
+        "* Gender: 0 = male, 1 = female\n",
+        "* Tartar  0 = N, 1 = Y"
+      ],
+      "metadata": {
+        "id": "zGuKNh-662rm"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "data['gender'].replace('M', 0, inplace=True)\n",
+        "data['gender'].replace('F', 1, inplace=True)\n",
+        "data.replace('N', 0, inplace=True)\n",
+        "data.replace('Y', 1, inplace=True)\n",
+        "#data.loc[:,['gender', 'tartar']].head()"
+      ],
+      "metadata": {
+        "id": "948jwuEZ7APh"
+      },
+      "execution_count": 39,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Examinamos ahora las variables numéricas."
+      ],
+      "metadata": {
+        "id": "pn6N3tmNuckj"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "data.hist(bins=30, figsize=(15, 10));"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 766
+        },
+        "id": "UmmsWKgytgxE",
+        "outputId": "50a9dbac-5d43-4872-e5a8-4ff367ec7ff5"
+      },
+      "execution_count": 40,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 1500x1000 with 25 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Observamos que hay muchas características que tienen la mayoría de observaciones concentradas en la izquierda, pero que luego hay algunos pocos valores muy altos que hacen que el histograma se desplace a la izquierda.\n",
+        "\n",
+        "Valores muy distintos a los normales en marcadores de interés médico pueden indicar la presencia de una enfermedad, pero también es práctica habitual indicar valores faltantes con el máximo valor que pueda acoger el programa (9, 99, 999, etc)."
+      ],
+      "metadata": {
+        "id": "Xtk_fMX2ytkL"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Buscamos el valor máximo de cada columna:"
+      ],
+      "metadata": {
+        "id": "H5rJbhH-CTGp"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "data.max().sort_values(ascending=False)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "bsvC7wyhB3db",
+        "outputId": "ca1bedf6-6a85-496b-cb3f-b81299f428e2"
+      },
+      "execution_count": 41,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "ALT                    2914.0\n",
+              "LDL                    1860.0\n",
+              "AST                    1311.0\n",
+              "Gtp                     999.0\n",
+              "triglyceride            999.0\n",
+              "HDL                     618.0\n",
+              "fasting blood sugar     505.0\n",
+              "Cholesterol             445.0\n",
+              "systolic                240.0\n",
+              "height(cm)              190.0\n",
+              "relaxation              146.0\n",
+              "weight(kg)              135.0\n",
+              "waist(cm)               129.0\n",
+              "age                      85.0\n",
+              "hemoglobin               21.1\n",
+              "serum creatinine         11.6\n",
+              "eyesight(right)           9.9\n",
+              "eyesight(left)            9.9\n",
+              "Urine protein             6.0\n",
+              "hearing(left)             2.0\n",
+              "hearing(right)            2.0\n",
+              "tartar                    1.0\n",
+              "gender                    1.0\n",
+              "dental caries             1.0\n",
+              "smoking                   1.0\n",
+              "dtype: float64"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 41
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Las columnas `Gtp` y `triglyceride` tienen valores máximos de 999, mientras `eyesight(left)` y `eyesgiht(right)` tienen valores máximos de 9.9.\n",
+        "Vamos a examinarlas con más detalle."
+      ],
+      "metadata": {
+        "id": "zv1_A-qzv8Xg"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "plt.boxplot(data.select_dtypes(include=['floating']),\n",
+        "            vert=False,\n",
+        "            labels = data.select_dtypes(include=['floating']).columns\n",
+        "            );\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 430
+        },
+        "id": "qjO8RqvDBJt5",
+        "outputId": "3e1b4ea9-b854-44c8-c618-8bd24017fbcd"
+      },
+      "execution_count": 42,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "iVBORw0KGgoAAAANSUhEUgAAApwAAAGdCAYAAAC//6OdAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAACgL0lEQVR4nOzdd1hUR9sH4N9h6WVB6SqyCIKoqCBqrGCLlRc0lhgbBls0GhtGosYuamyJJmrUgC3GRJEYWywvKooRRMQSBEQQYlBsLCAd5vvDb8/LsruwwC4gPvd1nYs9M3NmnjOQ7OOpHGOMgRBCCCGEEDXRqOsACCGEEEJIw0YJJyGEEEIIUStKOAkhhBBCiFpRwkkIIYQQQtSKEk5CCCGEEKJWlHASQgghhBC1ooSTEEIIIYSoFSWchBBCCCFErTTrOgDS8JWWluLff/+FkZEROI6r63AIIYQQogTGGLKzs9GkSRNoaNTsGCUlnETt/v33X9jY2NR1GIQQQgiphrS0NDRr1qxGfVDCSdTOyMgIwNs/WKFQWMfREEIIIUQZWVlZsLGx4b/Ha4ISTqJ2ktPoQqGQEk5CCCHkHaOKy+HopiFCCCGEEKJWdISTNBgP4+6iKP0+8g2bg2nqwsjICC1btqzrsAghhJD3HiWcpEFITEzE6D4dcGuaIdx25SDmaSkAICEhgU86HR0dkZiYWJdh1hvW1tYQCAR4/fo1CgsLUVpaCsYYXy8QCAAA2traMDU1hZOTExITE5GXl4fGjRvD2NgYAoEAzs7OePHiBS5evIji4mLY2tri448/RkxMDN68eQMzMzMUFhbi8uXLyM3NRePGjTF9+nTY2tri6dOniI2NxZs3b9CtWze0bdsWERERKCwsRFxcHJ48eQIA8PT0RHZ2Nv7++28AwODBg5GWloZHjx6hRYsW+M9//oNXr17h+fPnMDc3R9OmTdGlSxfs2rULSUlJEIlEcHFxwfPnz/k2VlZWKCwsxM8//4ycnBz06NED06ZNw549e6S2efnyJQwMDLB+/XqkpaWhefPmOHXqFIyNjWv/l0YIIe8wjpX9liEN1tOnTxEYGIhTp07hn3/+gbGxMRwcHDBu3DhMnDgR+vr64DgOx48fh4+Pj0rHzsrKgrGxMcRiscqv4czNzcWDBw+Ql5eHWSN64dY0Q8T12oVb6SUYN24coqOj4ebmRo9jIiplb2+Phw8f1nUYhBCiVqr8/qZrON8Djx49gqurK86dO4e1a9ciJiYG169fx8KFC3Hy5ElcuHChrkOstgcPHqBjx45ISUnhy5xbtYKzszO/Tslm/WVqalqj7fX19fnPHTp0gJ2dHQBAU/N/J29EIpFUGwnJUdzOnTvL9NuuXTupZ86Zm5sDAFxdXQEASUlJcHBwqFHshBDyPqGE8z0wY8YMaGpq4ubNmxg1ahScnZ3RokULeHt749SpU/Dy8uK/lIcNGwaO4/j15cuXo0OHDti1axdsbGygr6+PUaNGQSwW190OVcHAgQPrOoQGr7KksWzyV97Lly+hoaEBHR0dqfKyvzeO46T6aN68Of+PiNzcXAwaNAja2tq4ffs2Hj9+DG1tbVhbW0NPTw/6+vooLS3FkCFDYGFhgdu3b4PjOGhra6NZs2YYPHgwIiMjYWFhwY/JcRzOnTuH0tJSPv7U1FR4eXkhMzMTWVlZAN4mne/KfweEEFLXKOFs4F6+fIlz585h5syZMDAwkNuG4zhERUUBAIKCgpCens6vA8DDhw/x66+/4o8//sDZs2cRExODGTNmKByzoKAAWVlZUou65OXlAQCSk5Pllj9//lxtY5O3tLW1K6wfOXJkhfWlpaUoKCiQKsvNzeU/M8akjlKmpqZKXW/q6OiIOXPm8H3NmzcPaWlpyMvLQ25uLlJTU7FkyRKMGzeO72/evHl4/PgxdHV1AQATJkzA0KFD+foPPvgAANC6dWsUFxdj586dCAgIQHJyMqKjo/Hhhx8CAIYMGVLhvhFCCHmLEs4G7uHDh2CMwcnJSarczMwMhoaGMDQ0xJdffsmfMjQxMYGVlRW/DgD5+fnYv38/OnTogF69emHbtm345Zdf8PTpU7ljBgYGwtjYmF/U+ZYhyan0pUuXyi0n6idJ7hVxd3evcp8vXryQWq/osoi8vDz4+fnx62U/S7Rt2xYtWrSQaZOZmQkAaNGiBfT09Ph6yT9U1q1bB+Dt0cy2bdsCANLT07FkyRIAb5NfQgghlaOE8z0VGRmJ27dvo02bNjJHl8pr3rw5mjZtyq937doVpaWliI+Pl9s+ICAAYrGYX9LS0lQae1mSI1+rVq2SW07Ur2yiJs/Nmzer3KeZmZnUekX3Nurp6WHv3r38etnPEvfu3cOjR49k2piYmAB4e51z2cRZ8g+uRYsWAXh7k9C9e/cAvL3Df/Xq1QDe/rdBCCGkcvRYpAbOwcEBHMfJJIeSoz2VJQvVoaOjI3NNnrpI4pfcLFK+3NzcnE6rq1lhYWGF9b/99luF9RoaGtDS0pL6h0/Zm4E4jpM6Yt28eXOkpaXxSWhCQgIuXrzI97V582bY2NjgxYsX4DgOZmZmWL16NX+ZCMdx2Lx5M2xtbZGfnw8A2L9/P9zc3Pj6v/76C1ZWVvj777+hqamJ6dOnY9SoUbCzs0PHjh1x7tw5AMCpU6eUmSJCCHnv0RHOBs7U1BT9+/fH9u3b8ebNmwrbamlpoaSkRKY8NTUV//77L7/+119/QUNDQ+Y0fX109uzZug6hwXv58mWF9cXFxQrrTE1N5V7DWfb3xhiT6qPsNZz6+vo4c+YMCgsL0a5dO9ja2qKwsBDp6en8NZwcx+HUqVPIyMhA+/btwRhDYWEh/vnnH5w+fRqdO3dGRkYGPyZjDP379+fvUi8uLoaNjQ3++OMPqdez2tvb0/M4CSFESZRwvgd++OEHFBcXw93dHUeOHEFcXBzi4+Nx8OBBPHjwgH88jEgkwsWLF/H06VO8fv2a315XVxcTJ05EbGwswsPDMXv2bIwaNQpWVlZ1tUu8Vq1aITo6GpaWlnxZ3IMHiIuL49fpUbP1V2XJamXK3lx0584d/uaxsgnq48eP+c+xsbH8Z8k/riIjI2X6vXv3Ln+XOvC/a0ol29NzOAkhpGrolPp7wN7eHjExMVi7di0CAgLwzz//QEdHB61bt8aCBQv4O843bdqEefPmYffu3WjatCl/GtPBwQHDhw/H4MGD8erVKwwdOhQ//PBDHe7R/+jr68PNzQ179uzhy8aOHcu/acjIyAjA26ST3jT0P/SmIXrTECGE1CZ60xCp0PLlyxEaGorbt29Xuw91vmlI4sWLF/gj5Fd0aKYPmDnSu9QJIYSQGlLl9zcd4SQNgpmZGSZNVfxsUEIIIYTUHbqGkxBCCCGEqBWdUidqVxun1AkhhBCiWqr8/qYjnIQQQgghRK0o4SSEEEIIIWpFCSchhBBCCFErSjgJIYQQQoha0WORSIPxMO4uitLvQ8u6DRycXeo6HEIIIYT8P0o4SYOQmJiI0X064NY0Q7jtysGRKw/g6OhY63EYGBjAxMQE2dnZKC4uhoGBAQQCAYqKiqCjowN9fX00a9YMurq6SEpKQnZ2NkQiEdq1a4cePXrAxsYG3bp1Q0REBJ48eYJnz57h5cuX0NDQgKenJzw9Pfm3AJWUlCA8PBzp6emwtrZGz549+ToAyMvLg7+/PxITE9GyZUt888030NPTU2pbCXntACi1rSLl++zWrRsuXbqEAwcO8G/9mTVrFrS1tWvyq3hnFBYW4ocffkBSUhLs7e0xY8aMerHvNY1L2b8xdfdRn8ZRlXctXqI+79TfAiPvjYiICKahocEGDx4sVZ6cnMwAsJiYGL5s4sSJDIDCxdbWVulxxWIxA8DEYrGK9kRWdHQ0c7XSYGyZkLlaaVQYe31fNDU1FdZZWFiwY8eOsWPHjjGRSCRVJxKJ2LFjxxhjjHl7e8vd3tvbu9JtJeS1Mzc3ZxYWFpVuq4i8PjmOk4lTQ0OD+fv7q/zvpL7x9/eX+X1ramrW+b7XNC5l/8bU3Ud9GkdV3rV4ifrUxt+CKr+/KeF8j/j5+bEvvviCGRoasidPnvDl8hLOzMxMlp6ezi8AWFBQEL+ekZGh9LjqTDjfvHnDoqOj2dWrVxtMwqmtrc1/bt++Pfvggw8YANaqVSupJM3Ly4tdv36dZWdns+vXrzMvLy/GcRzr1KkT38+iRYvYw4cP2aJFi6T6VbSt5H9Ux44dkxkjMDCQ3z4wMFDhtoqU7/PgwYNS++3n58dOnjzJ2rVrx5fVdeKlTv7+/gwAs7S0ZLt372bp6els9+7dzNLSsk73vaZxyfvbqcrfiar6UEZtjaMq71q8RH1q62+BEk5SZdnZ2czQ0JA9ePCAjR49mq1Zs4avk5dwlgeAHT9+vFpjqzPhjI6OZgDYwYMH39mEs0mTJkxLS0umXF9fnxUWFrKSkhLm5eXFRCIRGzx4MOM4jq8rq6SkhA0ePJhPNgsKCqTqc3Nz+b5zcnJktvXy8mJ2dnasoKCAiUQi5uXlxUpKShhjjBUXFzORSMSGDh3Khg4dyuzs7FhxcbHMtpKy8iTbS/osLi5mtra2jOM4ZmFhwYYMGcJvX1JSwoYMGcIEAgHT1NSU2Y+GoKCggGlqajJLS0tWVFQkVVdUVMQsLS3rZN9rGlf533NZyvydqKoPZdTWOKryrsVL1Kc2/xYo4SRVtnfvXubu7s4YY+yPP/5g9vb2rLS0lDGm+oQzPz+ficVifklLS1Nbwnn16lUGgK1ateqdTTgBsD59+sgtDwsLY4y9vRwCAJs9e7ZMXVkfffQRA8A++eQTmbqwsDB+25kzZ8rUS8bYsmULA8CuX78us+3169f5dmXHl1cmb2xJn2Vj2b17t8z2knVJPA2NZI53794tt37Xrl11su81jav877m8yv5OVNWHMmprHFV51+Il6lObfwuqTDjpsUjvib1792LcuHEAgIEDB0IsFuPy5ctqGSswMBDGxsb8YmNjo5ZxACAlJQUAsHTpUrWNURusra3llqenpwMA2rZtCwDIz8+XqSvr9evXAAB3d3eFfQFvb7IqTzJGUlKS1Hr5OCTlZfuTV1bRfpRtN3ToUJnysmNL4mlIJPs0dOhQufWS8tre95rGJe/3V1Zlfyeq6kMZtTWOqrxr8RL1eVf/FijhfA/Ex8cjMjISY8aMAQBoampi9OjR2Lt3r1rGCwgIgFgs5pe0tDS1jAMAIpEIALBq1Sq1jVEbFP2PQZKI3rt3DwCgq6srU1dWo0aNAAA3b95U2BcAtGzZUqZeMoa9vb3Uevk4JOVl+5NXVtF+lG138uRJmfKyY0viaUgk+3Ty5Em59ZLy2t73msYl7/dXVmV/J6rqQxm1NY6qvGvxEvV5Z/8WanyMlNR7kpsABAIBv2hoaDA9PT2WmZlJ13DW8ULXcNI1nGXRNZx0Dac871q8RH3oGk5SL0m+JDZt2sTu3r0rtdjb27MdO3ZQwlnPlrJ3k7dr167Cu9QjIiJYVlYWi4iIkHuX+sKFC1l8fDxbuHChzF3q8raVd5e6pN3atWv57deuXatwW0XK91n+LvVPP/2U/f777+/lXeq7du1iT548Ybt27apXd6lXJy55fztV+TtRVR/KqK1xVOVdi5eoT239LVDCSZR2/Phxpq2tzTIzM2XqFi5cyNzd3fmE85dffmExMTFSi+QoWn1NOBviY5Gq+xxOOzu7aj+Hs+y2EvLaWVhYyDyHU962itBzOKW9T8/hrMrfiar6qE/jqMq7Fi9Rn9r4W1Dl9zfHGGMgDZaXlxdKS0tx6tQpmbrIyEh06dIFsbGxaN++vdzt09LS0KxZM3Ach+PHj8PHx6fKMWRlZcHY2BhisRhCobDK2yvj6tWrmD3Sg3/T0J5TUejYsaNaxqoIvWmocvSmIWn0piH19lGfxlGVdy1eoj7q/ltQ5fc3JZxE7Woj4dyzZw9+WDpN6tWW8m6MIYQQQohyVPn9Te9SJw2Cj48PBKWFiGmmj19Hd4QDJZuEEEJIvUFHOIna1cYRTkIIIYSoliq/v+k5nIQQQgghRK0o4SSEEEIIIWpFCSchhBBCCFErSjgJIYQQQohaUcJJCCGEEELUihJOQgghhBCiVvQcTtJgPIy7i6L0+9CybgMHZ5e6DocQQggh/48STtIgJCYmYnSfDvybhmKelqp9TE1NTejp6SEvLw/FxcUA3r7asnv37sjPz8fff/8NbW1tGBkZITs7GxzHoX379mjbti00NTVhZGSE8+fP48GDB8jKyoK+vj7s7e0xZcoU2NnZSb2irOzryywsLAAAGRkZNX6VmbL9KvuaQ1W+Zq0mr9+s6avdKnotqLLqyysr6TWIhJB6ocZvYyf1XkREBNPQ0GCDBw+WqQsJCWFdunRhQqGQGRoastatW7MvvviCMcaYh4cHA6Bw8fDwUGp8sVjMADCxWKzCvXrrzZs3LDo6ml29epW5WmkwtkzIXK00Koz7XVlEIhE7duwYO3bsGBOJRJW2qypl+/X392eamppSdZqamszf37/S/lQZm7y+VDmmhLe3t9z58Pb2VroPZedM3dQxP4SQ94cqv78p4XwP+Pn5sS+++IIZGhqyJ0+e8OUXLlxgWlpabMOGDezBgwcsPj6eHT9+nM2YMYMxxtjLly9Zeno6S09PZ5GRkQwAu3DhAl/28uVLpcZXZ8IZHR3NALCDBw82uITT2NiYAWAcxzEvLy8WGBjIOI5jPXr0YD169GAAWGBgIPPy8mIcx1UpiTh27JhUvwD4fjmO4/uVxGJpacl2797N0tPT2e7du5mlpSUDwCdQZfu7fv06y87OZtevX69xbBX1pcoxJSTJpra2Nlu0aBF7+PAhW7RoEdPW1lY66fT391dqztRNHfNDCHm/UMJJlJadnc0MDQ3ZgwcP2OjRo9maNWv4ui+++IJ5enoq1U9ycjIDwGJiYqocQ20knADqbcIpSVYqWnR1ddnAgQNlyrW0tJi+vj7Ly8tjIpGIeXl5sZKSElZSUsK8vLyYnZ0dKyws5D8XFxdXOmfFxcV8X4WFhQr7zcnJYRzHMYFAwPLz86X6KCoqYpaWlkxTU5Pl5uZK9VFW2f6qGltFfRUUFKhsTInc3Fz+91VQUCBVV1BQwP8ec3NzFfZRUFDANDU1maWlJSsqKpKqKztn5ftXNWXnsSrzQwh5/1DCSZS2d+9e5u7uzhhj7I8//mD29vastLSUMcZYYGAgMzc3Z3fv3q20n6oknPn5+UwsFvNLWlqa2hLOq1ev1vuEs6LF3Nyc/7x9+3aF7bZs2cIAsOvXr/P7HhERwQCwsLAwqc+VCQsL4/sq+7l8vzNnzuTHl9fvrl27pNqV7aOs6sZWUV/y5qO6Y0pI9mPRokVy6xcuXMjvryKSuHbv3i23XjJnW7ZsUTqu6lB2HqsyP4SQ948qE056LFIDt3fvXowbNw4AMHDgQIjFYly+fBkAMGvWLHTq1AkuLi4QiUT4+OOP8dNPP6GgoKBGYwYGBsLY2JhfbGxsarwfiqSkpKit79pgZGTEf67oppSkpCQAQNu2bfkyyef09HSpz5WRtGnbtq3U5/L9JiYmymxT1tChQ6Xale2jrOrGVlFf8uajumNKSPZj8uTJcuv9/Pyk2skjiUsyN+VJyiXt1EXZeazK/BBCSE1QwtmAxcfHIzIyEmPGjAHw9q7q0aNHY+/evQDe3lF96tQpPHz4EEuWLIGhoSHmz5+Pzp07Izc3t9rjBgQEQCwW80taWppK9kcekUiktr5rQ3Z2Nv85Ly9PYTt7e3sAwL179/gyyWdra2upz5WRtLl3757U5/L9tmzZUmabsk6ePCnVrmwfZVU3tor6kjcf1R1TQrIfe/bskVsv+e+m7LyUJ4lLMjflScol7dRF2XmsyvwQQkiNqOCIK6mnJDcvCAQCftHQ0GB6enosMzNT7jaPHj1impqa7KeffpIqp2s46RrOsugaTvnoGk5CSENC13CSSkm+3DZt2sTu3r0rtdjb27MdO3bI3a60tJQJhUK2bds2qfL6nnC+D3epr127lr9LvXv37gwAW7t2bY3vBF+7di0DwLp3787fpS7pVxKLpaUl27VrF3vy5AnbtWtXhXepR0REsKysLBYREVHj2CrqS5VjSpS9S33hwoUsPj6eLVy4sNp3qVc0Z+qmjvkhhLxfKOEklTp+/DjT1taWeyRz4cKFzN3dnS1btoz5+/uzsLAw9ujRI3br1i3m6+vL9PT02IMHD6S2qa8Jp+Q5nOfPn29wCaednZ1Sz+GUtKsqZfutyXM4VRmbvL5UOaZEQ38OZ03nhxDy/lDl9zfHGGMgDY6XlxdKS0tx6tQpmbrIyEh06dIFW7duRXh4OCIjI/Hs2TM0atQIrq6uWLx4MXr06CG1TUpKCuzs7BATE4MOHTpUKZasrCwYGxtDLBZDKBTWZLcU2rNnD35YOo3eNFRF9KYh+ehNQ4QQotrvb0o4idrVRsL54sUL/BHyKzo004eRXUd6lzohhBBSQ5RwkndKbSSchBBCCFEtVX5/02ORCCGEEEKIWlHCSQghhBBC1IoSTkIIIYQQolaUcBJCCCGEELWihJMQQgghhKgVJZyEEEIIIUStKOEk77bCXCRHhAKFuXUdCSGEEEIUoITzHcdxHEJDQ5VuHxwcDBMTE7XFU9tunD4Iu3MTEXnmYF2HQgghhBAFKOF8RyxfvlzuKyXT09MxaNAgpfsZPXo0EhISVBhZ3eE4Dp999hkAYPr0z8BxHJ4+fVrHURFCCCGkvHc+4SwqKqrrECqk7visrKygo6OjdHs9PT3+ndnvMo7j5JZbW1vDwMCglqMhhBBCSEVqPeE8evQoXFxcoKenB1NTU/Tr1w9v3rzh6/fs2QNnZ2fo6uqiVatW+OGHH/i6lJQUcByHI0eOwMPDA7q6ujh06JDco39bt26FSCTi1319feHj44O1a9fC0tISJiYmWLlyJYqLi+Hv74/GjRujWbNmCAoKqjD+0tJSbNiwAQ4ODtDR0UHz5s2xZs2aCuOrbL8A4Msvv4SjoyP09fXRokULLF26lE9Wg4ODsWLFCsTGxoLjOHAch+DgYADSp9Ql44eEhKB3797Q19dH+/btcf36dX6c8qfUJXN34MABiEQiGBsb4+OPP0Z2drbUPgcGBsLOzg56enpo3749jh49WuE8qZOiZFMiNzeXkk5CCCGkHtGszcHS09MxZswYbNiwAcOGDUN2djbCw8MheZ37oUOH8PXXX2P79u1wdXVFTEwMpkyZAgMDA0ycOJHvZ9GiRdi0aRNcXV2hq6uLXbt2KTX+f//7XzRr1gxXrlzBtWvX4Ofnh4iICPTq1Qs3btzAkSNHMG3aNPTv3x/NmjWT20dAQAB2796NLVu2oEePHkhPT8eDBw+k2pSPT5n9MjIyQnBwMJo0aYK7d+9iypQpMDIywsKFCzF69Gjcu3cPZ8+exYULFwAAxsbGCvdz8eLF2LhxI1q2bInFixdjzJgxePjwITQ15f+6k5KSEBoaipMnT+L169cYNWoU1q1bxyfSgYGBOHjwIHbu3ImWLVviypUrGDduHMzNzeHh4aHU3KtK+WRz8OBBAMLh4+ODmJ0hfHlubi6ePn0KKyurWo2PEEIIIXKwWhQdHc0AsJSUFLn19vb27Oeff5YqW7VqFevatStjjLHk5GQGgG3dulWqzbJly1j79u2lyrZs2cJsbW359YkTJzJbW1tWUlLClzk5ObGePXvy68XFxczAwIAdPnxYbnxZWVlMR0eH7d69W269ovgq2y95vvnmG9axY8cK95ExxgCw48ePS42/Z88evv7+/fsMAIuLi2OMMRYUFMSMjY2l+tXX12dZWVl8mb+/P+vSpQtjjLH8/Hymr6/PIiIipMb18/NjY8aMkRt7fn4+E4vF/JKWlsYAMLFYrHB/lQWAX+zs7NiK6cMZWyZ8+7NcvaWlZY3HI4QQQt5XYrFYZd/ftXqEs3379ujbty9cXFwwYMAAfPjhhxgxYgQaNWqEN2/eICkpCX5+fpgyZQq/TXFxsczRPHd392qN36ZNG2ho/O8qAktLS7Rt25ZfFwgEMDU1RUZGhtzt4+LiUFBQgL59+1Y4Ttn4lN2vI0eO4LvvvkNSUhJycnJQXFwMoVBY5X0EgHbt2vGfra2tAQAZGRlo1aqV3PYikQhGRkZS20jm4OHDh8jNzUX//v2ltiksLISrq6vc/gIDA7FixYpqxV4VGzZswN8XDyusz8zMVHsMhBBCCKlcrSacAoEA58+fR0REBM6dO4dt27Zh8eLFuHHjBvT19QEAu3fvRpcuXWS2K6v89XkaGhr8aXkJeTfraGlpSa1zHCe3rLS0VG78enp6Feyd/PhycnIAVLxf169fx9ixY7FixQoMGDAAxsbG+OWXX7Bp0yalxiuv7D5JTkEr2qfy7SXbSNpL4j916hSaNm0q1U7RzUoBAQGYN28ev56VlQUbG5sq7IFyFi5cCN8B8pNeAA3q8U+EEELIu6xWE07gbTLTvXt3dO/eHV9//TVsbW1x/PhxzJs3D02aNMGjR48wduzYKvVpbm6Op0+fgjHGJ1i3b99WeewtW7aEnp4eLl68iMmTJyu1jaWlZaX7FRERAVtbWyxevJgve/z4sVQbbW1tlJSUVD/4amrdujV0dHSQmpqq9PWaOjo6VbpzvrqSk5NRWNiaXy9/fac6/gYIIYQQUnW1mnDeuHEDFy9exIcffggLCwvcuHEDz58/h7OzMwBgxYoVmD17NoyNjTFw4EAUFBTg5s2beP36tdQRs/I8PT3x/PlzbNiwASNGjMDZs2dx5syZap+SVkRXVxdffvklFi5cCG1tbXTv3h3Pnz/H/fv34efnp3C7yvarZcuWSE1NxS+//IJOnTrh1KlTOH78uFQfIpEIycnJuH37Npo1awYjI6NaSeqMjIywYMECzJ07F6WlpejRowfEYjGuXbsGoVAodTNXbSj7jwoAOH36DFZPM5R5+L2+vj7dMEQIIYTUE7X6WCShUIgrV65g8ODBcHR0xJIlS7Bp0yb+weWTJ0/Gnj17EBQUBBcXF3h4eCA4OBh2dnYV9uvs7IwffvgB33//Pdq3b4/IyEgsWLBALfuwdOlSzJ8/H19//TWcnZ0xevRohdd8SlS2X//5z38wd+5cfP755+jQoQMiIiKwdOlSqT4++ugjDBw4EL1794a5uTkOH1Z87aKqrVq1CkuXLkVgYCCcnZ0xcOBAnDp1qtLfi7qUv3yiPH19falHbRFCCCGkbnGssm9vQmooKysLxsbGEIvFKj3qzHEcXK00cGuaIdx25SDmaSnS09PpyCYhhBCiAqr8/n7n3zRE3l+MMZy7lYLjFnNx7lYKGGOUbBJCCCH1EB3hJGqnriOchBBCCFEfOsJJCCGEEELeGZRwEkIIIYQQtaKEkxBCCCGEqBUlnIQQQgghRK0o4SSEEEIIIWpFCSchhBBCCFErSjjJu60wF8kRoUBhbl1HQgghhBAFKOFUQCQSYevWrXUdRq1bvnw5OnToUNdhKIXjOLjZGsHu3ES42RpJvWOdEEIIIfVHg004PT09MWfOHJny4OBgmJiYVLp9VFQUpk6dqvrAakl1E8cFCxbg4sWLqg9IxRQll5R0EkIIIfWPZl0HUN8UFhZCW1sb5ubmdR2KXJL41MXQ0BCGhoZq618VKksqOY4DvUCLEEIIqT8a7BFOZfn6+sLHxwdr1qxBkyZN4OTkBED2lDrHcdizZw+GDRsGfX19tGzZEidOnJDq6969exg0aBAMDQ1haWmJ8ePH48WLFwrHlhxtDQ0NRcuWLaGrq4sBAwYgLS2NbyM5Urlnzx7Y2dlBV1cXAJCamgpvb28YGhpCKBRi1KhRePbsGd/vihUrEBsbC47jwHEcgoODAQCZmZmYPHkyzM3NIRQK0adPH8TGxsqMV35+Nm7cCGtra5iammLmzJkoKiqq1nzXVPlk08fHR+qnonaEEEIIqTvvfcIJABcvXkR8fDzOnz+PkydPKmy3YsUKjBo1Cnfu3MHgwYMxduxYvHr1CsDbRK5Pnz5wdXXFzZs3cfbsWTx79gyjRo2qcOzc3FysWbMG+/fvx7Vr15CZmYmPP/5Yqs3Dhw9x7NgxhISE4Pbt2ygtLYW3tzdevXqFy5cv4/z583j06BFGjx4NABg9ejTmz5+PNm3aID09Henp6XzdyJEjkZGRgTNnziA6Ohpubm7o27cvvx/yhIWFISkpCWFhYdi3bx+Cg4P5BFaegoICZGVlSS3qUP4oJh3VJIQQQuonOqUOwMDAAHv27Kn0VLWvry/GjBkDAFi7di2+++47REZGYuDAgdi+fTtcXV2xdu1avv1PP/0EGxsbJCQkwNHRUW6fRUVF2L59O7p06QIA2LdvH5ydnREZGYnOnTsDeHsaff/+/fxp/vPnz+Pu3btITk6GjY0NAGD//v1o06YNoqKi0KlTJxgaGkJTUxNWVlb8WFevXkVkZCQyMjKgo6MDANi4cSNCQ0Nx9OhRhdesNmrUCNu3b4dAIECrVq0wZMgQXLx4EVOmTJHbPjAwECtWrKhwLgkhhBDy/qAjnABcXFyUui6yXbt2/GcDAwMIhUJkZGQAAGJjYxEWFsZfA2loaIhWrVoBAJKSkhT2qampiU6dOvHrrVq1gomJCeLi4vgyW1tbqWtK4+LiYGNjwyebANC6dWuZ7cqLjY1FTk4OTE1NpeJMTk6uMMY2bdpAIBDw69bW1vx+yxMQEACxWMwvZS8RIIQQQsj7p8Ee4RQKhRCLxTLlmZmZMDY2liozMDBQqk8tLS2pdY7jUFpaCgDIycmBl5cX1q9fL7OdtbW1smHLpWx8lcnJyYG1tTUuXbokU1fRnfsV7bc8Ojo6/BFUdeI4DiumD5daJ4QQQkj902ATTicnJ5w7d06m/NatWwpPb9eEm5sbjh07BpFIBE1N5ae1uLgYN2/e5E+fx8fHIzMzE87Ozgq3cXZ2RlpaGtLS0vijnH///TcyMzPRunVrAIC2tjZKSkpkYnz69Ck0NTUhEomquIf1A2NMKrEMDQ3F19MMERoaKtOOEEIIIfVDgz2l/tlnnyEhIQGzZ8/GnTt3EB8fj82bN+Pw4cOYP3++ysebOXMmXr16hTFjxiAqKgpJSUn4888/MWnSJJnErywtLS3MmjULN27cQHR0NHx9ffHBBx/wCag8/fr1g4uLC8aOHYtbt24hMjISEyZMgIeHB9zd3QG8vcs+OTkZt2/fxosXL1BQUIB+/fqha9eu8PHxwblz55CSkoKIiAgsXrwYN2/eVPmcqEtlySQlm4QQQkj90mATzhYtWuDKlSt48OAB+vXrhy5duuDXX3/Fb7/9hoEDB6p8vCZNmuDatWsoKSnBhx9+CBcXF8yZMwcmJibQ0FA8zfr6+vjyyy/xySefoHv37jA0NMSRI0cqHIvjOPz+++9o1KgRevXqhX79+qFFixZS23300UcYOHAgevfuDXNzcxw+fBgcx+H06dPo1asXJk2aBEdHR3z88cd4/PgxLC0tVTYXtUFRUknJJiGEEFL/cIy+oetMcHAw5syZg8zMzLoORa2ysrJgbGwMsVgMoVCo0r5fpKch/Phe9BzmBzNrm8o3IIQQQohSVPn93WCv4STvBzNrGwybsbyuwyCEEEJIBRrsKXVCCCGEEFI/UMJZh3x9fRv86XRCCCGEEEo4CSGEEEKIWlHCSQghhBBC1IoSTkIIIYQQolaUcBJCCCGEELWihJM0DIW5SI4IBQpz6zoSQgghhJTz3iecnp6emDNnTl2HUS2+vr7w8fFRuv2lS5fAcVyFd8YHBwfDxMSkxrHVthunD8Lu3EREnjlY16EQQgghpJz3PuEk0kaPHo2EhIS6DkMp0dHR4DgOHMfhs88+AwBMn/4ZNDQ0EB8fX8fREUIIIUSC3jREpOjp6UFPT6+uw6gUx3EK6xhjaNWqFf+ZEEIIIXWLjnACKC0txcKFC9G4cWNYWVlh+fLlfF1mZiYmT54Mc3NzCIVC9OnTB7GxsXz98uXL0aFDB/z0009o3rw5DA0NMWPGDJSUlGDDhg2wsrKChYUF1qxZIzVmamoqvL29YWhoCKFQiFGjRuHZs2dSbVavXg0LCwsYGRlh8uTJWLRoETp06KBwPwoKCjB79mxYWFhAV1cXPXr0QFRUlEy7a9euoV27dtDV1cUHH3yAe/fu8XXlT6lL9u/AgQMQiUQwNjbGxx9/jOzsbCVnV/UqSjZr0pYQQggh6kEJJ4B9+/bBwMAAN27cwIYNG7By5UqcP38eADBy5EhkZGTgzJkziI6OhpubG/r27YtXr17x2yclJeHMmTM4e/YsDh8+jL1792LIkCH4559/cPnyZaxfvx5LlizBjRs3ALxNcL29vfHq1StcvnwZ58+fx6NHjzB69Gi+z0OHDmHNmjVYv349oqOj0bx5c+zYsaPC/Vi4cCGOHTuGffv24datW3BwcMCAAQOkYgUAf39/bNq0CVFRUTA3N4eXlxeKiooU9puUlITQ0FCcPHkSJ0+exOXLl7Fu3boqz7MqREdHV3kbOr1OCCGE1DH2nvPw8GA9evSQKuvUqRP78ssvWXh4OBMKhSw/P1+q3t7enu3atYsxxtiyZcuYvr4+y8rK4usHDBjARCIRKykp4cucnJxYYGAgY4yxc+fOMYFAwFJTU/n6+/fvMwAsMjKSMcZYly5d2MyZM6XG7d69O2vfvj2/PnHiRObt7c0YYywnJ4dpaWmxQ4cO8fWFhYWsSZMmbMOGDYwxxsLCwhgA9ssvv/BtXr58yfT09NiRI0cYY4wFBQUxY2Njvl7e/vn7+7MuXbrIm07GGGP5+flMLBbzS1paGgPAxGKxwm2UBUBm0dLSYq5WGowtEzJXKw2ZeoFAUONxCSGEkPeNWCxW2fc3HeEE0K5dO6l1a2trZGRkIDY2Fjk5OTA1NYWhoSG/JCcnIykpiW8vEolgZGTEr1taWqJ169bQ0NCQKsvIyAAAxMXFwcbGBjY2Nnx969atYWJigri4OABvj8p17txZKq7y62UlJSWhqKgI3bt358u0tLTQuXNnvk+Jrl278p8bN24MJycnmTZlld8/yfwoEhgYCGNjY34pu5/q8J///If/bGPTTKa+pKREreMTQgghpGJ00xDeJmZlcRyH0tJS5OTkwNraGpcuXZLZpux1jvK2V9Tnu6iq+xIQEIB58+bx61lZWWpNOk+cOIG2pm8/p6X9I1MvEAjUNjYhhBBCKkdHOCvg5uaGp0+fQlNTEw4ODlKLmZlZtft1dnZGWloa0tLS+LK///4bmZmZaN26NQDAyclJ5oYfeTcASdjb20NbWxvXrl3jy4qKihAVFcX3KfHXX3/xn1+/fo2EhAQ4OztXe3/K09HRgVAolFpU5ebNmzJlFV1/CgD3799X2fiEEEIIqTo6wlmBfv36oWvXrvDx8cGGDRvg6OiIf//9F6dOncKwYcPg7u5e7X5dXFwwduxYbN26FcXFxZgxYwY8PDz4PmfNmoUpU6bA3d0d3bp1w5EjR3Dnzh20aNFCbp8GBgb47LPP4O/vj8aNG6N58+bYsGEDcnNz4efnJ9V25cqVMDU1haWlJRYvXgwzM7MqPUC+LnXs2LHK2zg5OakhEkIIIYQoixLOCnAch9OnT2Px4sWYNGkSnj9/DisrK/Tq1QuWlpY16vf333/HrFmz0KtXL2hoaGDgwIHYtm0b32bs2LF49OgRFixYgPz8fIwaNQq+vr6IjIxU2O+6detQWlqK8ePHIzs7G+7u7vjzzz/RqFEjmXZffPEFEhMT0aFDB/zxxx/Q1tau9v7UNsaY0o87YvQcTkIIIaTOcYy+kd8Z/fv3h5WVFQ4cOFDXoVRJVlYWjI2NIRaLVXp6PTo6mj8i7GqlgVvTDOG2Kwe3nzHExcXRkU1CCCGkBlT5/U1HOOup3Nxc7Ny5EwMGDIBAIMDhw4dx4cIF/vmg5O3pdcm/l16kp+H48b04d8sPZtbqvSueEEIIIVVDRzjrqby8PHh5eSEmJgb5+flwcnLCkiVLMHz48LoOrcrUdYSTEEIIIepDRzjfA3p6erhw4UJdh0EIIYQQUmP0WCRCCCGEEKJWlHASQgghhBC1ooSTEEIIIYSoFSWchBBCCCFErSjhJIQQQgghakV3qZP3VmJiIrKzs8EV50M3JxX5hs3BNHUBAEZGRmjZsmUdR0gIIYQ0DJRwkneWWCxG7969ERMTI1P33XffYdasWQq3TUxMhKOjIwDptxTFPC3l2yQkJChMOrt164br169XOWZNTU0YGRmhpKQEhoaG+OCDDyAWi5GbmwsDAwO4u7ujX79+8PT0BACEh4fjyZMneP78OczNzdG0aVP07NkTAoGgymPXRGFhIX744QckJSXB3t4eM2bMUPvrUEtKSvj9f/r0KV69egUNDQ14enrC09OzynMg6S89PR3W1tZVnkdl5qCyNlWdx7LtRSIRXFxc8PLlS6n4q7NfymxT0/lShqIxlBlb3X+TFcVQG3NDSIPDSIM1ceJE5u3tLbfO1taWAWAAmK6uLrO1tWUjR45kFy9elGqXnJzMALCYmJhqxyEWixkAJhaLq91Hefb29nz8FS2KREdHMwDs4MGD7O+LhxlbJmR/XzzMoqOj2cGDBxkAFh0dLXdbZcat6SIUCpmFhYXcOpFIxI4dO6ayuayMv78/09TUlIpBU1OT+fv7q23MY8eOMZFIpHB+LCwsqjQH8vqryjwqMweVtanqPMprXz5+f3//Ku+XMnNR0/lShqIxlNkndf9NVrT/tTE3hNQXqvz+poSzAass4Vy5ciVLT09njx8/ZpcvX2ZTpkxhHMex1atX8+3qY8KpbLJZUdIpSTijo6MZexLD2DLh25/l68qpjWSz7MJxHBs0aBDbvXs3GzRoEAPA3N3dGcdxtfIF5+/vzwAwS0tLtnv3bpaens52797NLC0tGQC1JJ3Hjh1jHMcxd3d3fh7atWvHunbtyjiOY61ateLnRpk5kPTn5eXFrl+/zrKzs9n169eZl5eXUn0oMweVtenUqVOV5rFsf5999hk/B40bN2YA2NixY/n5cXd3V3q/lJmLms6XMhSNocw+qftvsrL9B6DWuSGkPqGEkyilsoRzy5YtMuVff/0109DQYA8ePGCM1b+EMzMzU25idvz4cfbmzRu5dd99951MP9VJOLt27arW5FJLS4vp6OhIlenr67PCwkLGGGMlJSXMy8uLiUQiNnToUGZnZ8eKi4trPKeKFBQUME1NTWZpacmKioqk6oqKipilpSXT1NRkBQUFKhuzuLiY37/mzZszPT09NnToUFZSUsLvv52dHRsyZAjT19evdA4k/Xl5ebGSkhKpurL9KepD2TkQCAQK20iOVFtYWCg1j2XHzM/Pl4q/bHtbW1tmaWnJRCKRVPyK9kuZuRCJRDWaL2UoiqO4uJjfp/JjSMa2tbVV699kRXNUWFjI9PT0pP6bLB+fuv+bJKS2UcJJlFKdhPPly5eM4zi2fv16xlj1Es78/HwmFov5JS0tTWV/sN27d6/wKGbnzp3l1kdHR0stktPmV69elUk4r169yoC3p9vLblPbRzclS1hYGL9/ERERDADbvn27TJ2qbdmyhQFgu3fvllu/a9cuBkDu31F1hYWFMQDs+++/5/f/+vXrfH35/a9sDiT9le2jLEl/ivpQdg4qajNy5EgGgI0aNarCPiTzWHZMefGXHfPHH3+UG7+8/VJ2LmoyX8pQFIekvLJ9UuffZEVzJKlTtP+qmBtC6htVJpx00xCR0rhxY1hYWCAlJaXafQQGBmLFihWqC6qM1NRUmbJmzZrxnz/88ENERkbKtOnYsaPc/lJSUtDdro1MGQCMGzeuBpGqTnp6Ov+5bdu2AAA9PT2ZOlVLSkoCAAwdOlRuvaRc0k4VJPsj2T/gf/tc9nPZ+ormQFJXto+yJOWK+lB2DipqY2BgIPVTUR+SscqOGRYWJhO/vDHLxy9vv5SdC2Xa1OTvTlEckvLK9qlsm/Jq+jdZ0RzJm0t58anzv0lC3mX0HE4igzEGjuOqvX1AQADEYjG/pKWlqSy25s2by5T9888//Odz587J3S46OlpqOXjwIABAJBLJtJWUHTx4UGqbumJtbc1/vnfvHgAgLy9Ppk7V7O3tAQAnT56UWy8pl7RTBcn+SPYP+N8+l/1ctr6iOZDUle2jLEm5oj6UnYOK2rx580bqp6I+JGOVHVNe/PLGLB+/vP1Sdi6UaVOTvztFcUjKK9unsm3Kq+nfZEVzJG8u5cWnzv8mCXmn1fyAK6mvqnNK/cWLF4zjOPbNN98wxugazrLoGs7/oWs46RrO6qJrOAl5d9A1nEQp1Uk4ly5dygQCAUtMTGSM1b+Ek7H38y71Xbt21fld6rt27WJPnjxhu3btqpO71D/44IMa36UeERHBsrKyWERERLXuUlc0B5W1KXuXujLzWLa/6dOnMwDMxcWFv0v9k08+kbqjW9n9UmYuajpfylA0hjL7pO6/ycr2H4Ba54aQ+oQSTqKUiRMnMk9PTxYTEyO1pKamSj0WKTU1VeqxSOvWreP7kCScv/zyi0w/5f+Vr0h9fA5neHg4f/PBu/YcTjs7O3oOpwqew1mVeayPz+G0s7OT+8zKyvZLmbmo6XwpQ9EYyuxTXTyHUxJDbcwNIfWFKr+/OcYYA2mQfH19sW/fPplyPz8/XLhwAY8fPwYAaGtrw8rKCh988AGmT5+O3r17821TUlJgZ2cnt/+0tDSpG3YUycrKgrGxMcRiMYRCYTX3RlZN3jS0Z88eTJkyBQC9aUgZ9KYhetMQvWmI3jRE3j+q/P6mhJOonboSzpp48eIFQkND0apVKxhoa9C71AkhhJByKOEk75T6mHASQgghpGKq/P6mxyIRQgghhBC1ooSTEEIIIYSoFSWchBBCCCFErSjhJIQQQgghakUJJyGEEEIIUStKOAkhhBBCiFpRwkkIIYQQQtRKs64DIESdHsbdRVH6feQbNodhI3N6mDshhBBSByjhJO+svLw8zJs3DxEREYiPjwcAWFtbIzIyEubm5khMTMToPh2kXluZkJAAR0dHpfo3NTVF48aN0apVK3h4eGDWrFlqf52jRH1/dV59j48QQkg9U+O3sZN6Z+LEiczb21umPCwsjAFgr1+/5j8DYBzHMaFQyDp06MD8/f3Zv//+K7XdsmXLWPv27asdj1gsZgCYWCyudh/leXt78/HLW4yNjVl0dDRztdJgbJmQndqztsL2yiwaGhrM399fZfugyLFjx5hIJJIaWyQSsWPHjql9bGXU9/gIIYSohiq/v+kazvdcfHw8/v33X0RFReHLL7/EhQsX0LZtW9y9e7euQ1PIx8cHv//+u1RZ48aNwXEcvy4Wi+Hh4cGv29nZ1Xjc0tJSfPPNN1i4cGGN+1IkJCQEI0aMgIuLC65fv47s7Gxcv34dLi4uGDFiBEJCQtQ2dkOIjxBCSP1E71JvgHx9fZGZmYnQ0FCp8kuXLqF37954/fo1bt++zX82MTHh2+Tl5cHV1RVmZma4evUqAGD58uUIDQ3F7du3qxWPKt/FmpeXB319fakySb9//fUXunbtKlXnaqUhdUq9pjiOg0AgwJs3b1R+er2kpAQODg5wcXFBaGgoNDT+9+/B0tJS+Pj44N69e0hMTKyT09f1PT5CCCGqRe9SJ2qjp6eH6dOn49q1a8jIyKhWHwUFBcjKypJaVMXf319qvU2bNvx/BCUlJSobRxHGGIqLi/HDDz+ovO/w8HCkpKTgq6++kkrmAEBDQwMBAQFITk5GeHi4ysduCPERQgipv+imoQbq5MmTMDQ0lCpTNiFr1aoVACAlJQUWFhZVHjswMBArVqyo8nbKSExMlFpfv349/zklJUUtY8qTlJSk8j7T09MBAG3btpVbLymXtKtt9T0+Qggh9Rcd4Wygevfujdu3b0ste/bsUWpbyVUWZa+JrIqAgACIxWJ+SUtLq1Y/8pR/rNGXX37JfxaJRCobpzL29vYq79Pa2hoAcO/ePbn1knJJu9pW3+MjhBBSf1HC2UAZGBjAwcFBamnatKlS28bFxQGofgKno6MDoVAotajKN998I7V+//59/pR9bVw3yHEcNDU1MWPGDJX33bNnT4hEIqxduxalpdLXm5aWliIwMBB2dnbo2bOnysduCPERQgipvyjhJFLy8vLw448/olevXjA3N6/rcGTo6enB29tbqszY2BiNGzdGt27dpMrLXlJw6NAhlYzPGMPcuXPV8jxOgUCATZs24eTJk/Dx8ZG6C9zHxwcnT57Exo0b6+yGnPoeHyGEkPqLruF8z2VkZCA/Px/Z2dmIjo7Ghg0b8OLFC5nH2+Tl5cncpW5kZKSWU8uVCQ0NlXk00uvXr6XaGBsb4+TJk5g98u2jkZKTk2s8roaGBubPn48NGzbUuC9Fhg8fjqNHj2L+/PlSCbSdnR2OHj2K4cOHq21sZdT3+AghhNRPlHC+55ycnMBxHAwNDdGiRQt8+OGHmDdvHqysrKTaJSQkwNXVVaqsb9++uHDhQm2GywsNDa30TUNlr1ldsmQJALwTbxoaPnw4vL296+2bfOp7fIQQQuofeg4nUTtVPserKl68eIE/Qn5Fh2b6gJkjvUudEEIIqQJVfn9TwknUrq4STkIIIYRUHz34nRBCCCGEvDMo4SSEEEIIIWpFCSchhBBCCFErSjgJIYQQQohaUcJJCCGEEELUihJOQgghhBCiVvTgd/JeSUxMRHZ2Nr/OFedDNycV+YbNwTR15W5jZGREz+8khBBCaoASzipavnw5QkNDZV7zWBFPT0906NABW7duVVtcqopDJBJhzpw5mDNnTq3FVVsSExNl3jLkaqWBW9MM4bYrBzFPSxVum5CQUOOkc8uWLZg3b16N+ihv4MCBCAkJwa5du5CUlAR7e3vMmDED2traKCwsxA8//CBTrkhJSQm9PUgOmhdCCKk5Sjj/n7JJ4YIFCzBr1qzaCUrFQkJCoKWlVddh1BnJkc2DBw/C2dkZAKCXmQBcmYZDhw4hz0T2lZdxcXEYN26c1FHR6uA4rkbbK3L27Fno6+tLlfn7+8PV1RUxMTEoLi6WKp87d67cd8GHhIRg/vz5SElJ4ctEIhE2bdr0Xr8fneaFEEJUg67hVBJjDMXFxTA0NISpqWldh1MlhYWFAIDGjRvDyMiojqNRvdzcXNy6dQu5ublKtXd2doabmxvc3Nzg3KrV27JWrfiysoskMa0JdSWb5e3Zswe7d++GtrY2oqKioK2tjd27dyM9PR27d++GqakpvvnmGyxcuFBqu5CQEIwYMQIuLi64fv06srOzcf36dbi4uGDEiBEICQmplfjrG5oXQghRIUbYxIkTGQCpJSgoiAFgp0+fZm5ubkxLS4uFhYWxZcuWsfbt2/PbFhUVsVmzZjFjY2PWuHFjtnDhQjZhwgTm7e3Nt/Hw8GBffPEFY4yxFStWsDZt2sjE0L59e7ZkyRJ+fe/evax169ZMW1ubWVlZsZkzZ/J1r1+/Zn5+fszMzIwZGRmx3r17s9u3b/P1khh3797NRCIR4zhOJg7GGHv27BkbOnQo09XVZSKRiB08eJDZ2tqyLVu2KD2WMsRiMQPAxGJxlbZTVnR0NAPAoqOjq97uSQxjy4Rvf9agb0U2b94s87elziU3N5cJBALGcRzT1NRkBQUFfCxFRUXM0tJSqry4uJiJRCLm5eXFSkpKpGIvKSlhXl5ezM7OjhUXF1dr/99VNC+EEKLa7286pQ7g22+/RUJCAtq2bYuVK1cCAO7fvw8AWLRoETZu3IgWLVqgUaNGuHTpktS269evx6FDhxAUFARnZ2d8++23CA0NRe/eveWO9emnn2LFihWIiopCp06dAAAxMTG4c+cOf8Rkx44dmDdvHtatW4dBgwZBLBbj2rVrfB8jR46Enp4ezpw5A2NjY+zatQt9+/ZFQkICGjduDAB4+PAhjh07hpCQEIXXm/n6+uLff/9FWFgYtLS0MHv2bGRkZEi1UWas8goKClBQUMCvZ2VlyW2nKnl5eQDenv6uiKRe0l6VfSui6ms2K+Pv74+SkhKMHz8eBw4cwA8//MBfj6upqYmVK1di2rRpfHl4eDhSUlJw+PBhaGhIn/DQ0NBAQEAAunXrhvDwcHh6etbqvtQlmhdCCFEtSjgBGBsbQ1tbG/r6+rCysgIAPHjwAACwcuVK9O/fX+G227ZtQ0BAAIYNGwYA2L59O06fPq2wfbNmzTBgwAAEBQXxCWdQUBA8PDzQokULAMDq1asxf/58fPHFF/x2krZXr15FZGQkMjIyoKOjAwDYuHEjQkNDcfToUUydOhXA29Po+/fvh7m5udw4EhIScObMGURGRvJ97927V+oUsrJjlRcYGIgVK1YonANVk1xfN27cOKXbd+/eXS1917XExEQAbxPdAwcOICkpSap+6NChAMCXp6enAwDatm0rtz9JuaTd+4LmhRBCVIsSzkq4u7srrBOLxXj27Bk6d+7MlwkEAnTs2BGlpYrveJ4yZQo+/fRTbN68GRoaGvj555+xZcsWAEBGRgb+/fdf9O3bV+62sbGxyMnJkbmONC8vTyq5sLW1VZhsAm+P2GlqaqJjx458WatWrWBiYlLlscoLCAiQOrKXlZUFGxsbhe1rSiQSAZC+GUgeyQ1Akvaq7FuRsvNbG1q2bIlz585h8+bNAAB7e3up+pMnT0qVW1tbAwDu3buHDz74QKa/e/fuSbV7X9C8EEKIalHCWQkDAwOV9+nl5QUdHR0cP34c2traKCoqwogRIwAAenp6FW6bk5MDa2trmVP7AKSSRVXErexY5eno6PBHRGuDZM4kNwMp214dfZe3efPmWj2t/s0332Dnzp04ePAgNDU1MWPGDL6uuLgYX3/9tVR5z549IRKJsHbtWoSGhkqdPi4tLUVgYCDs7OzQs2fPWtuH+oDmhRBCVIvuUv9/2traKCkpqdI2xsbGsLS0RFRUFF9WUlKCW7duVbidpqYmJk6ciKCgIAQFBeHjjz/mExsjIyOIRCJcvHhR7rZubm54+vQpNDU14eDgILWYmZkpHXurVq1QXFyM6Ohoviw+Ph6ZmZkqH+t9Nnfu3Foba/fu3Thw4AB0dHTAGIO2tjaCg4Px77//4scff0SzZs3w7NkzzJ07l38ep0AgwKZNm3Dy5En4+PhI3Y3t4+ODkydPYuPGje/dcydpXgghRLXoCOf/E4lEuHHjBlJSUmBoaFjhKfGyZs2ahcDAQDg4OKBVq1bYtm0bXr9+XemjcCZPnsyfoi17QxDw9uHy06dPh4WFBQYNGoTs7Gxcu3YNs2bNQr9+/dC1a1f4+Phgw4YNcHR0xL///otTp05h2LBhFV4CUJaTkxMGDhyIadOmYceOHdDU1MScOXOkjv6paix1a9WqFaKjo9Hq/x9xpIjksUll/0Ggl5kAZwBxDx4gT86D36t7s1BZjLFaeTTSlClTALz9B02nTp0QExODadOm8fWamprw9/eXeQ7n8OHDcfToUcyfPx/dunXjy+3s7HD06NH39nmTNC+EEKI6lHD+vwULFmDixIlo3bo18vLyEBQUpNR2X375JZ4+fYoJEyZAIBBg6tSpGDBgQKVHPlq2bIlu3brh1atX6NKli1TdxIkTkZ+fjy1btmDBggUwMzPjT7lzHIfTp09j8eLFmDRpEp4/fw4rKyv06tULlpaWVdrnoKAgTJ48GR4eHrC0tMTq1auxdOlSvl6VY6mTvr6+Uqe7JTeCSRIz4H9vGho7dmyFbxqq6fNLGWP1+k1Dw4cPh7e3N71RpxyaF0IIUQ2OMcbqOoiGpLS0FM7Ozhg1ahRWrVqlsB1jDC1btsSMGTNq/dE5tS0rKwvGxsYQi8UQCoV1FseLFy8QGhqKVq1a8W/noXepE0IIIfKp8vubjnDW0OPHj3Hu3Dl4eHigoKAA27dvR3JyMj755BOF2zx//hy//PILnj59ikmTJtVitO83MzMzTJ48WU5NNzllhBBCCFEVSjhrSENDA8HBwViwYAEYY2jbti0uXLhQ4SN0LCwsYGZmhh9//BGNGjWqxWgJIYQQQmofJZw1ZGNjI3PTT2XoKgZCCCGEvE/osUiEEEIIIUStKOEkhBBCCCFqRQknIYQQQghRK0o4CSGEEEKIWlHCSQghhBBC1IruUidESYmJicjOzgYg/4Hx9IB4QgghRD5KOKuB4zgcP34cPj4+1e7D09MTHTp0wNatW1UWV225dOkSevfujdevX8PExKSuw1GopKSEfyWhiYkJTpw4gbi4OFy7dg3FxcVSbX/77Tf+9aHyJCYmwtHRkV+XvBLTbVeO1CsxExISKkw6LS0tkZGRUe19srS0hEgkgoGBAczNzSEQCCASidCnTx906dIFixYtQmJiIlq2bIlvvvkGenp61R6LEEIIURVKOOV4+vQp1qxZg1OnTuHJkyewsLBAhw4dMGfOHPTt27euw5PxriSAtSkkJATz589HSkqKUu1HjhwJQPEzUiVHNg8ePAhnZ2foZSYAV6bh0KFDyDNxRFxcHMaNG8e3k4fjuKrthBzPnj3Ds2fPZMrXrl0rtX7u3Dl8//338Pb2RmhoaI3HJYQQQmqCruEsJyUlBR07dsR///tffPPNN7h79y7Onj2L3r17Y+bMmXUdnloxxmSO/L2LQkJCMGLECLi4uKBnz55V2raypNDZ2Rlubm5wbtXq7XqrVm/XK3izlDL9qtL27duxaNEiaGtr4/fff6/RkXhCCCFEFSjhLGfGjBngOA6RkZH46KOP4OjoiDZt2mDevHn466+/+HYvXrzAsGHDoK+vj5YtW+LEiRNS/Vy+fBmdO3eGjo4OrK2tsWjRogqTuYKCAixYsABNmzaFgYEBunTpgkuXLvH1jx8/hpeXFxo1agQDAwO0adMGp0+fRkpKCnr37g0AaNSoETiOg6+vLwCgtLQUgYGBsLOzg56eHtq3b4+jR4/yfV66dAkcx+HMmTPo2LEjdHR0cPXqVRQUFGD27NmwsLCArq4uevTogaioKBXMrvqVlJRg/vz5GDp0KA4fPozw8HAIBAKZdv/973+hpaUlt4+yc6QKlpaWKu1PEW1tbejp6WHjxo1YvXo1srOz+aQzLy+vVmIghBBC5KGEs4xXr17h7NmzmDlzJgwMDGTqy56uXrFiBUaNGoU7d+5g8ODBGDt2LF69egUAePLkCQYPHoxOnTohNjYWO3bswN69e7F69WqFY3/++ee4fv06fvnlF9y5cwcjR47EwIEDkZiYCACYOXMmCgoKcOXKFdy9exfr16+HoaEhbGxscOzYMQBAfHw80tPT8e233wIAAgMDsX//fuzcuRP379/H3LlzMW7cOFy+fFlq7EWLFmHdunWIi4tDu3btsHDhQhw7dgz79u3DrVu34ODggAEDBvD7V5mCggJkZWVJLbUlPDwcKSkp+Oqrr/Dll18CgNzfJcdxGDVqFABAX19fqm7kyJG4deuW1BIXFwcAChM3SXlcXJzMtjW5ZrMqCgsLkZeXh5SUFISHh0NbWxtz5swBAPj7+9dKDIQQQohcjPBu3LjBALCQkJAK2wFgS5Ys4ddzcnIYAHbmzBnGGGNfffUVc3JyYqWlpXyb77//nhkaGrKSkhLGGGMeHh7siy++YIwx9vjxYyYQCNiTJ0+kxunbty8LCAhgjDHm4uLCli9fLjeesLAwBoC9fv2aL8vPz2f6+vosIiJCqq2fnx8bM2aM1HahoaFS+6KlpcUOHTrElxUWFrImTZqwDRs2KByvrGXLljEAMotYLJbbXpV+/vlnBoBlZ2ezDz/8kAFgenp6MrH8/PPP7JtvvpEbZ0XLwYMH3w70JIaxZcK3PxljBw8erHJf6lx+/vlnxhhj8fHxDAD78MMP1T73hBBCGhaxWKyy72+6aagMpuCGEXnatWvHfzYwMIBQKOSPZMXFxaFr165S1+11794dOTk5+Oeff9C8eXOpvu7evYuSkhKpu6CBt0cKTU1NAQCzZ8/GZ599hnPnzqFfv3746KOPpGIo7+HDh8jNzUX//v2lygsLC+Hq6ipV5u7uzn9OSkpCUVERunfvzpdpaWmhc+fO/FG+ygQEBGDevHn8elZWFmxsbJTatqasra0BAPfu3UPLli1x7tw5aGlpyRyZtLa2xqlTpwC8PcKZm5srVR8dHS21LrkpSCQSyR1XUi65qaisjh07Vnd3qk0yD3v37gUAelwTIYSQOkUJZxktW7YEx3F48OBBpW3LX//HcRxKS0sVtK5YTk4OBAIBoqOjZa43NDQ0BABMnjwZAwYMwKlTp3Du3DkEBgZi06ZNmDVrlsI+AeDUqVNo2rSpVJ2Ojo7UurxTzjWho6MjM0Zt6dmzJ0QiEdauXYvDhw/j+++/x5s3b2TaMcbw66+/AoBMsvnbb7/Bzc1Nbv+KHjMkKZfcVFSWhYVFrZxW19bWhkAggKWlJXr27InCwkL+sVvffPON2scnhBBCFKFrOMto3LgxBgwYoDBJyczMVKofZ2dnXL9+XeqI6bVr12BkZIRmzZrJtHd1dUVJSQkyMjLg4OAgtVhZWfHtbGxsMH36dP6RP7t37wbwNtEA3t4wI9G6dWvo6OggNTVVps+Kjjba29tDW1sb165d48uKiooQFRWF1q1bK7X/dUkgEGDTpk04efIkxowZg549e0rNi0SfPn1QVFQkt4+KnsdZHfIeY6QOkms458+fj6+++gpGRkYoLCyEt7c3PY+TEEJInaIjnOV8//336N69Ozp37oyVK1eiXbt2KC4uxvnz57Fjxw6lTivPmDEDW7duxaxZs/D5558jPj4ey5Ytw7x586ChIZvjOzo6YuzYsZgwYQI2bdoEV1dXPH/+HBcvXkS7du0wZMgQzJkzB4MGDYKjoyNev36NsLAw/tStra0tOI7DyZMnMXjwYOjp6cHIyAgLFizA3LlzUVpaih49ekAsFuPatWsQCoWYOHGi3NgNDAzw2Wefwd/fH40bN0bz5s2xYcMG5Obmws/Pr2aTW0uGDx+Oo0ePVuk5nBKKLquQHAW9desWAEAvMwHOAOIePEDe09JK/y4YY7X2aKSyR73pOZyEEELqA0o4y2nRogVu3bqFNWvWYP78+UhPT4e5uTk6duyIHTt2KNVH06ZNcfr0afj7+6N9+/Zo3Lgx/Pz8sGTJEoXbBAUFYfXq1Zg/fz6ePHkCMzMzfPDBBxg6dCiAt0cvZ86ciX/++QdCoRADBw7Eli1b+PFWrFiBRYsWYdKkSZgwYQKCg4OxatUqmJubIzAwEI8ePYKJiQnc3Nzw1VdfVRj/unXrUFpaivHjxyM7Oxvu7u74888/0ahRIyVnse4NHz4c3t7eKnvTkOQyiylTpgD435uGxo4dK/WmISMjI4V9MMboTUOEEELeSxyryp0yhFRDVlYWjI2NIRaLIRQK6zqcannx4gVCQ0PRqlUr6Ovr07vUCSGENHiq/P6mhJOoXUNIOAkhhJD3jSq/v+mmIUIIIYQQolaUcBJCCCGEELWihJMQQgghhKgVJZyEEEIIIUStKOEkhBBCCCFqRQknIYQQQghRK3rwO3kvPYy7i6L0+8g3bA7DRub0/ExCCCFEjap0hJMxhqlTp6Jx48bgOA63b99WS1DLly9Hhw4d1NJ3Wb6+vvDx8amwjaenJ+bMmaP2WEQiEbZu3ar2cd4XOTk56NOnDziOk1lWrFiBUX06wPnKNPh594Sjo6PcdrW5CAQCGBkZwdTUFA4ODmjWrBlcXV3RuXNnNG/eHEKhEFZWVvDw8EC/fv3g4+ODTZs2IS8vD5cuXcLhw4dx6dIlmffGl5SUyNTLKyOEEELUqUpHOM+ePYvg4GBcunQJLVq0gJmZWY0D4DgOx48fl0r8FixYIPU+aEKqonPnzoiKilJYv3z5crhavf231urVqzFkcsWv+qwNpaWlyMnJAQC8evUKAPDkyROpNtnZ2Xj27Bm//vvvv2PBggVSbUQiETZt2oThw4cjJCRE5n3y5ubm4DhO6vWaZbchhBBC1KFKRziTkpJgbW2Nbt26wcrKCpqa6jkjb2hoCFNTU7X0TVSHMSbzTvK6VlmyWV5F77d/l3zxxRe4fv06XFxcMGLECCxcuBAjRoyAi4sLrl+/juzsbAQGBuL58+fIyMhAYGAgsrOzpbYJCQmp690ghBDSQCmdcPr6+mLWrFlITU0Fx3EQiUQA3h717NGjB0xMTGBqaoqhQ4ciKSmJ366wsBCff/45rK2toaurC1tbWwQGBgIA38ewYcOk+ix/Sl1y6nvjxo2wtraGqakpZs6ciaKiIr5Neno6hgwZAj09PdjZ2eHnn39W+jT1ihUrYG5uDqFQiOnTp6OwsFBh29evX2PChAlo1KgR9PX1MWjQICQmJkq1OXbsGNq0aQMdHR3+6FFZGRkZ8PLy4mM9dOhQpTFeunQJnTt3hoGBAUxMTNC9e3c8fvxYan7KmjNnDjw9Pfn17OxsjB07FgYGBrC2tsaWLVtkLhc4cOAA3N3dYWRkBCsrK3zyySdSR8IuXboEjuNw5swZdOzYETo6Orh69WqlsdeWnJwcucnmqVOncO3atTqISPWMjY2l1rW1tSEQCPD999/Dzc0NoaGhGDJkCLZs2YIhQ4YgNDQUH3zwAfT09LBr1y4MHToUQ4cOxY8//gg9PT188MEHCA0NxdChQ7FgwQI6vU4IIUQtlE44v/32W6xcuRLNmjVDeno6/8X+5s0bzJs3Dzdv3sTFixehoaGBYcOGobS0FADw3Xff4cSJE/j1118RHx+PQ4cO8YmlpI+goCCpPuUJCwtDUlISwsLCsG/fPgQHByM4OJivnzBhAv79919cunQJx44dw48//iiVLCly8eJFxMXF8de0hYSEYMWKFQrb+/r64ubNmzhx4gSuX78OxhgGDx7MJ7/R0dEYNWoUPv74Y9y9exfLly/H0qVLpWL19fVFWloawsLCcPToUfzwww8VxlpcXAwfHx94eHjgzp07uH79OqZOnQqO4yrdP4l58+bh2rVrOHHiBM6fP4/w8HDcunVLqk1RURFWrVqF2NhYhIaGIiUlBb6+vjJ9LVq0COvWrUNcXBzatWsnU19QUICsrCyppTaMHz9ebvngwYPBGKuVGNSt/LXNhYWFKCkpQXFxMX744QdoaGhg4MCBKC4uxqBBg6Ch8fY/8fDwcKSkpGDx4sX46quvkJycjPDwcACAhoYGAgICpMoIIYQQVVL6nLixsTGMjIwgEAhgZWXFl3/00UdS7X766SeYm5vj77//Rtu2bZGamoqWLVuiR48e4DgOtra2fFtzc3MAgImJiVSf8jRq1Ajbt2+HQCBAq1atMGTIEFy8eBFTpkzBgwcPcOHCBURFRcHd3R0AsGfPHqXuPNbW1sZPP/0EfX19tGnTBitXroS/vz9WrVrFf1lLJCYm4sSJE7h27Rq6desGADh06BBsbGwQGhqKkSNHYvPmzejbty+WLl0KAHB0dMTff/+Nb775Br6+vkhISMCZM2cQGRmJTp06AQD27t0LZ2dnhTFmZWVBLBZj6NChsLe3B4AK25eXnZ2Nffv24eeff0bfvn0BvE3ymzRpItXu008/5T+3aNEC3333HTp16oScnBwYGhrydStXrkT//v0VjhcYGFhh0q4uZY+sS7Ro0QIApK5jfJdVlDhL9l9PT0/qJ/D2DAAAtG3blu9DUiYpL19GCCGEqEqNn8OZmJiIMWPGoEWLFhAKhfzRy9TUVABvj+bdvn0bTk5OmD17Ns6dO1etcdq0aQOBQMCvW1tb80cF4+PjoampCTc3N77ewcEBjRo1qrTf9u3bQ19fn1/v2rUrcnJykJaWJtM2Li4Ompqa6NKlC19mamoKJycnxMXF8W26d+8utV337t2RmJiIkpISvo+OHTvy9a1atYKJiYnCGBs3bgxfX18MGDAAXl5e+Pbbb6uUGDx69AhFRUXo3LkzX2ZsbAwnJyepdtHR0fDy8kLz5s1hZGQEDw8PAP/7XUpIknpFAgICIBaL+UXeXKqDJBkv69GjRwD+d/nGu66io9qS/c/Ly5P6Cbz97wUA7t27h3v37kmVScrLlxFCCCGqUuOE08vLC69evcLu3btx48YN3LhxAwD46yDd3NyQnJyMVatWIS8vD6NGjcKIESOqPI6WlpbUOsdx/Gn790FQUBCuX7+Obt264ciRI3B0dMRff/0F4O0p0fJHvspe36qMN2/eYMCAARAKhTh06BCioqJw/PhxAJC5ptXAwKDCvnR0dCAUCqWW2nDgwAG55adPn67S5Qf1WflHkUmu4dTU1MSMGTNQWlqKs2fPQlNTE2fOnOH/G+nZsydEIhHWrFmDtWvXws7ODj179gTw9g75wMBAqTJCCCFElWqUcL58+RLx8fFYsmQJ+vbtC2dnZ7x+/VqmnVAoxOjRo7F7924cOXIEx44d4x/9oqWlVeMbFZycnFBcXIyYmBi+7OHDh3JjKS82NlbqSNBff/0FQ0ND2NjYyLR1dnZGcXExn1QD/5uD1q1b823K36By7do1ODo68pcDFBcXIzo6mq+Pj49HZmZmpbG6uroiICAAERERaNu2LX7++WcAby9NKH/Es2xi0qJFC2hpaUldIysWi5GQkMCvP3jwAC9fvsS6devQs2dPtGrVSqlrYOsTQ0ND/jKFsoYMGSJz1PldJRaLpdYl13DOnDkT0dHR8PHxwalTpzB37lycOnUKPj4+uH79OnJzczF16lScPHkSJ0+exJQpU5Cbm4vr16/Dx8cHJ0+exMaNG6XOIhBCCCGqUqOEs1GjRjA1NcWPP/6Ihw8f4r///S/mzZsn1Wbz5s04fPgwHjx4gISEBPz222+wsrLiTyGLRCJcvHgRT58+VSpBlKdVq1bo168fpk6disjISMTExGDq1KnQ09Or9MhWYWEh/Pz88Pfff+P06dNYtmwZPv/8c5nrNwGgZcuW8Pb2xpQpU3D16lXExsZi3LhxaNq0Kby9vQEA8+fPx8WLF7Fq1SokJCRg37592L59O/+8RCcnJwwcOBDTpk3DjRs3EB0djcmTJ0tdb1decnIyAgICcP36dTx+/Bjnzp1DYmIifx1nnz59cPPmTezfvx+JiYlYtmwZf4oUAIyMjDBx4kT4+/sjLCwM9+/fh5+fHzQ0NPj5ad68ObS1tbFt2zY8evQIJ06cwKpVq6r2i6gHyl4bq4zVq1erMZra8+2336Jbt264d+8ejh49ig0bNuDo0aO4e/cuunXrBqFQiK+++goWFhawsLDAV199BaFQKLUNPYeTEEKIutToQZoaGhr45ZdfMHv2bLRt2xZOTk747rvvpB7HY2RkhA0bNiAxMRECgQCdOnXC6dOn+YRu06ZNmDdvHnbv3o2mTZtW++aO/fv3w8/PD7169YKVlRUCAwNx//596OrqVrhd37590bJlS/Tq1QsFBQUYM2YMli9frrB9UFAQvvjiCwwdOhSFhYXo1asXTp8+zZ/yd3Nzw6+//oqvv/4aq1atgrW1NVauXCl1t3dQUBAmT54MDw8PWFpaYvXq1fxNRvLo6+vjwYMH2LdvH16+fAlra2vMnDkT06ZNAwAMGDAAS5cuxcKFC5Gfn49PP/0UEyZMwN27d/k+Nm/ejOnTp2Po0KEQCoVYuHAh0tLS+PkxNzdHcHAwvvrqK3z33Xdwc3PDxo0b8Z///Keyqa93IiMjkZOTg//85z8ICwuTqf/oo4/w6NrbywXqy3M4NTQ0oK+vD21tbTRq1Aj5+fkwNzeHlpYWnj59iszMTOjr68PJyQlaWlowNDREz549MWPGDNy4cQPp6emwtrZGz549+aOUw4cPh7e3N8LDw6XqAciU0ZFNQggh6sSxhvK8mHL++ecf2NjY4MKFC/yd2eR/3rx5g6ZNm2LTpk3w8/NT61hZWVkwNjaGWCyutes5K/LixQv8EfIrOjTTB8wc6V3qhBBCiByq/P5Wz6uC6sB///tf5OTkwMXFBenp6Vi4cCFEIhF69epV16HVCzExMXjw4AE6d+4MsViMlStXAgB/KcD7xMzMDJOmzqjrMAghhJD3RoNJOIuKivDVV1/h0aNHMDIyQrdu3XDo0CGZu9vfZxs3bkR8fDy0tbXRsWNHhIeHw8zMrK7DIoQQQkgD12BPqZP6o76dUieEEEJI5VT5/V3j53ASQgghhBBSEUo4CSGEEEKIWlHCSQghhBBC1IoSTkIIIYQQolaUcBJCCCGEELVqMI9FIqQyD+Puoij9PrSs28DB2aWuwyGEEELeG3SEsxZ4enpizpw5dR0GgLfvrt+6dWtdh6FWqamp4DhOamnSpAlG9ekA5yvTMKpPB5l6eYuRkRH8/PyQl5dX17tECCGEvNMo4WyggoODYWJiIlMeFRWFqVOn1n5AtURLSwu2trYy5enp6VXuKycnBz/99BP09fXh4+OjgugIIYSQ9xMlnDVUWFhY1yFUibm5OfT19es6DLXQ0tJCcXGxWvr+/fffKekkhBBCqokSziry9PTE559/jjlz5sDMzAwDBgzAvXv3MGjQIBgaGsLS0hLjx4/HixcvFPZx4MABuLu7w8jICFZWVvjkk0+QkZHB169cuRJNmjTBy5cv+bIhQ4agd+/eKC0tBQBs3rwZLi4uMDAwgI2NDWbMmIGcnBwAwKVLlzBp0iSIxWL+9PDy5csByJ5ST01Nhbe3NwwNDSEUCjFq1Cg8e/aMr1++fDk6dOiAAwcOQCQSwdjYGB9//DGys7NVMZ0qk5qaKpVsDho0CIwxREdHq2yM33//nU6vE0IIIdVACWc17Nu3D9ra2rh27RrWrVuHPn36wNXVFTdv3sTZs2fx7NkzjBo1SuH2RUVFWLVqFWJjYxEaGoqUlBT4+vry9YsXL4ZIJMLkyZMBAN9//z0iIiKwb98+aGi8/ZVpaGjgu+++w/3797Fv3z7897//xcKFCwEA3bp1w9atWyEUCpGeno709HQsWLBAJo7S0lJ4e3vj1atXuHz5Ms6fP49Hjx5h9OjRUu2SkpIQGhqKkydP4uTJk7h8+TLWrVuncP8KCgqQlZUltahbmzZtpNZPnz4NAHyCqKurq5Jx/P39VdIPIYQQ8l5hpEo8PDyYq6srv75q1Sr24YcfSrVJS0tjAFh8fDy/zRdffKGwz6ioKAaAZWdn82VJSUnMyMiIffnll0xPT48dOnSowrh+++03Zmpqyq8HBQUxY2NjmXa2trZsy5YtjDHGzp07xwQCAUtNTeXr79+/zwCwyMhIxhhjy5YtY/r6+iwrK4tv4+/vz7p06aIwlmXLljEAMotYLK5wH2pCQ0NDaiyJgwcP8mWuVhqMLRMyVysNufEps5T/XRNCCCENlVgsVtn3Nx3hrIaOHTvyn2NjYxEWFgZDQ0N+adWqFYC3RwbliY6OhpeXF5o3bw4jIyN4eHgAeHtaWKJFixbYuHEj1q9fj//85z/45JNPpPq4cOEC+vbti6ZNm8LIyAjjx4/Hy5cvkZubq/R+xMXFwcbGBjY2NnxZ69atYWJigri4OL5MJBLByMiIX7e2tpa6BKC8gIAAiMVifklLS1M6pupSdF2qSCQCoLojnC1btlRJP4QQQsj7hBLOajAwMOA/5+TkwMvLC7dv35ZaEhMT0atXL5lt37x5gwEDBkAoFOLQoUOIiorC8ePHAcjegHTlyhUIBAKkpKRIXZ+YkpKCoUOHol27djh27Biio6Px/fffy+1DFbS0tKTWOY7jryWVR0dHB0KhUGpRt/v370utDx48GACgp6cHAMjPz1fJON98841K+iGEEELeJ/Tg9xpyc3PDsWPHIBKJoKlZ+XQ+ePAAL1++xLp16/gjizdv3pRpd+TIEYSEhODSpUsYNWoUVq1ahRUrVgB4e4S0tLQUmzZt4q/p/PXXX6W219bWRklJSYWxODs7Iy0tDWlpaXwsf//9NzIzM9G6devKd74ead68OTQ1NfnE/MyZM+A4TqVjeHt78wksIYQQQpRHRzhraObMmXj16hXGjBmDqKgoJCUl4c8//8SkSZPkJnzNmzeHtrY2tm3bhkePHuHEiRNYtWqVVJt//vkHn332GdavX48ePXogKCgIa9euxV9//QUAcHBwQFFREd/HgQMHsHPnTqk+RCIRcnJycPHiRbx48ULuqfZ+/frBxcUFY8eOxa1btxAZGYkJEybAw8MD7u7uKpyl2lFUVKRU0l8d3t7eCA0NVUvfhBBCSENHCWcNNWnSBNeuXUNJSQk+/PBDuLi4YM6cOTAxMeGPPpZlbm6O4OBg/Pbbb2jdujXWrVuHjRs38vWMMfj6+qJz5874/PPPAQADBgzAZ599hnHjxiEnJwft27fH5s2bsX79erRt2xaHDh1CYGCg1DjdunXD9OnTMXr0aJibm2PDhg0ysXAch99//x2NGjVCr1690K9fP7Ro0QJHjhxR8SzVnqKiIjx+/FimXN7vojKGhob49NNPkZubS8kmIYQQUgMcY4zVdRCkYcvKyoKxsTHEYnGtXM8pz4sXL/BHyK/o0EwfRnYd6V3qhBBCSCVU+f1NCSdRu/qQcBJCCCGkalT5/U2n1AkhhBBCiFpRwkkIIYQQQtSKEk5CCCGEEKJWlHASQgghhBC1ooSTEEIIIYSoFSWchBBCCCFErejVloQAeBh3F0Xp95Fv2ByGjczRsmXLug6JEEIIaTAo4SS4dOkSevfujdevX8PExATBwcGYM2cOMjMz6zo0lSgpKcF///tfrF27FpcuXeLLDQwM8PDhQ2RnZ2N0nw64Nc0QbrtyEPO0FAkJCXB0dFSqf11dXXh6esLW1hYaGhowMTGBQCCAp6cnPD09IRAI1LRnhBBCyLuBHvzegJRPHKu7XV5eHrKzs2FhYaGSuOrywe8hISH49NNPIRaLFbbR1dWFs0khbk0zxGmbRRgy+SuVjW9hYYEdO3Zg+PDhKuuTEEIIqQ304HeiVnp6eipLNutSSEgIPvroowqTTQDIz8/nP9vZ2dV4XG1tbQBA06ZNkZGRgREjRiAkJKTG/RJCCCHvKko468jRo0fh4uICPT09mJqaol+/frh8+TK0tLTw9OlTqbZz5sxBz549AQCPHz+Gl5cXGjVqBAMDA7Rp0wanT59GSkoKevfuDQBo1KgROI6Dr68vAKCgoACzZ8+GhYUFdHV10aNHD0RFRSmMLTg4WOYI6R9//IFOnTpBV1cXZmZmGDZsmOomQw1KSkowb948mfLXr19XuO9jx46t8diFhYWwsLDAs2fPMHjwYOjp6WHBggUoKSmpcd+EEELIu4gSzjqQnp6OMWPG4NNPP0VcXBwuXbqE4cOHo2PHjmjRogUOHDjAty0qKsKhQ4fw6aefAgBmzpyJgoICXLlyBXfv3sX69ethaGgIGxsbHDt2DAAQHx+P9PR0fPvttwCAhQsX4tixY9i3bx9u3boFBwcHDBgwAK9evVIq3lOnTmHYsGEYPHgwYmJicPHiRXTu3Flh+4KCAmRlZUkttS08PByPHz+WKrOzs4OJiQkKCgrUPr6HhweKi4vh4OCA3NxcJCcnIzw8XO3jEkIIIfUR3TRUB9LT01FcXIzhw4fD1tYWAODi4gIA8PPzQ1BQEPz9/QG8PbKYn5+PUaNGAQBSU1Px0Ucf8e1btGjB99u4cWMAb68blByhfPPmDXbs2IHg4GAMGjQIALB7926cP38ee/fu5cepyJo1a/Dxxx9jxYoVfFn79u0Vtg8MDJRqWxfS09NlyjZs2AAASElJUfv4BgYGAKRP18uLiRBCCHkf0BHOOtC+fXv07dsXLi4uGDlyJHbv3o3Xr18DAHx9ffHw4UP89ddfAN6e3h41ahSfwMyePRurV69G9+7dsWzZMty5c6fCsZKSklBUVITu3bvzZVpaWujcuTPi4uKUivf27dvo27ev0vsXEBAAsVjML2lpaUpvqyrW1tYyZQsXLgQAiEQitY//5s0bAG9vSKooJkIIIeR9QAlnHRAIBDh//jzOnDmD1q1bY9u2bXByckJycjIsLCzg5eWFoKAgPHv2DGfOnOFPpwPA5MmT8ejRI4wfPx53796Fu7s7tm3bptZ49fT0qtReR0cHQqFQaqltPXv25I8eSyQnJyMzMxM6OjpqH//y5cvQ1NTEw4cPoa+vDzs7O/46XEIIIeR9QwlnHeE4Dt27d8eKFSsQExMDbW1tHD9+HMDbpPLIkSP48ccfYW9vL3V0EgBsbGwwffp0hISEYP78+di9ezeA/90dXfbmFHt7e2hra+PatWt8WVFREaKiotC6dWulYm3Xrh0uXrxYo/2tbQKBAJs3b5Ypb9SoETp16qRwu0OHDtV4bG1tbWRkZMDS0hKnT59GXl4eNm7cSM/jJIQQ8t6ihLMO3LhxA2vXrsXNmzeRmpqKkJAQPH/+HM7OzgCAAQMGQCgUYvXq1Zg0aZLUtnPmzMGff/6J5ORk3Lp1C2FhYfx2tra24DgOJ0+exPPnz5GTkwMDAwN89tln8Pf3x9mzZ/H3339jypQpyM3NhZ+fn1LxLlu2DIcPH8ayZcsQFxfH36xU3w0fPhzHjh2DsbFxhe3KnvZOTk6u8biFhYUAgCdPnsDCwgJHjx6l53ASQgh5vzFS6/7++282YMAAZm5uznR0dJijoyPbtm2bVJulS5cygUDA/v33X6nyzz//nNnb2zMdHR1mbm7Oxo8fz168eMHXr1y5kllZWTGO49jEiRMZY4zl5eWxWbNmMTMzM6ajo8O6d+/OIiMj+W3CwsIYAPb69WvGGGNBQUHM2NhYatxjx46xDh06MG1tbWZmZsaGDx+u9P6KxWIGgInFYqW3UaXi4mJ27tw55unpyQDwi4GBAUtPT2e7d+9mrlYajC0TMlcrDQaAJSQkSLWtaNHV1WUDBw5k06ZNY5999hkLCAhgS5YsYRcuXGDFxcV1ss+EEEJITany+5veNFRP+fn54fnz5zhx4kRdh1JjdfmmIWW8ePECf4T8ig7N9AEzR3qXOiGEEALVfn/TY5HqGbFYjLt37+Lnn39uEMnmu8DMzAyTps6o6zAIIYSQBosSznrG29sbkZGRmD59Ovr371/X4RBCCCGE1BglnPXMpUuX6joEQgghhBCVorvUCSGEEEKIWlHCSQghhBBC1IoSTkIIIYQQolaUcBJCCCGEELWihJMQQgghhKgVJZzk3VaYi+SIUKAwt64jIYQQQogCDSLh9PT0xJw5c2p93JSUFHAch9u3b6u878LCQjg4OCAiIqLCdsHBwTAxMalS376+vvDx8alyTGfPnkWHDh1QWlpa5W3VgeM4uNkawe7cRLjZGoHjuLoOiRBCCCFyNIiEs67Y2NggPT0dbdu2VXnfO3fuhJ2dHbp161Zhu9GjRyMhIUHl44tEImzdulWqbODAgdDS0sKhQ4dUPl5VKUouKekkhBBC6h9KOKupsLAQAoEAVlZW0NRU7fPzGWPYvn07/Pz8KmxXVFQEPT09WFhYqHT8ivj6+uK7776rtfHkqSyppKSTEEIIqV8aTMJZWlqKhQsXonHjxrCyssLy5cv5uszMTEyePBnm5uYQCoXo06cPYmNj+fqkpCR4e3vD0tIShoaG6NSpEy5cuCDVv0gkwqpVqzBhwgQIhUJMnTpV5pT6pUuXwHEcLl68CHd3d+jr66Nbt26Ij4+X6mv16tWwsLCAkZERJk+ejEWLFqFDhw58fXR0NJKSkjBkyBC+TDLWkSNH4OHhAV1dXRw6dEjuKfXK+pfYuHEjrK2tYWpqipkzZ6KoqAjA20sUHj9+jLlz54LjOKkEzsvLCzdv3kRSUpIyvxaVK59MSi4NKH+JACWdhBBCSP3RYBLOffv2wcDAADdu3MCGDRuwcuVKnD9/HgAwcuRIZGRk4MyZM4iOjoabmxv69u2LV69eAQBycnIwePBgXLx4ETExMRg4cCC8vLyQmpoqNcbGjRvRvn17xMTEYOnSpQpjWbx4MTZt2oSbN29CU1MTn376KV936NAhrFmzBuvXr0d0dDSaN2+OHTt2SG0fHh4OR0dHGBkZyfS9aNEifPHFF4iLi8OAAQNk6pXpHwDCwsKQlJSEsLAw7Nu3D8HBwQgODgYAhISEoFmzZli5ciXS09ORnp7Ob9e8eXNYWloiPDxc4f4XFBQgKytLalEHxliF64QQQgipJ1gD4OHhwXr06CFV1qlTJ/bll1+y8PBwJhQKWX5+vlS9vb0927Vrl8I+27Rpw7Zt28av29raMh8fH6k2ycnJDACLiYlhjDEWFhbGALALFy7wbU6dOsUAsLy8PMYYY126dGEzZ86U6qd79+6sffv2/PoXX3zB+vTpI3esrVu3SpUHBQUxY2Njfl2Z/idOnMhsbW1ZcXExXzZy5Eg2evRoqf3dsmULk8fV1ZUtX75cbh1jjC1btowBkFnEYrHCbZRVtj/GGFsxfThjy4Rvf8qpJ4QQQkj1iMVilX1/N5gjnO3atZNat7a2RkZGBmJjY5GTkwNTU1MYGhryS3JyMn9aOCcnBwsWLICzszNMTExgaGiIuLg4mSOc7u7uVY7F2toaAJCRkQEAiI+PR+fOnaXal1/Py8uDrq6u3L4ri0GZ/gGgTZs2EAgEUnFKYqyMnp4ecnMVP4YoICAAYrGYX9LS0pTqlxBCCCENk2rvdqlDWlpaUuscx6G0tBQ5OTmwtrbGpUuXZLaRXPu4YMECnD9/Hhs3boSDgwP09PQwYsQIFBYWSrU3MDCociySawmr8ighMzMz3L17V26dsjFURtF8KePVq1cwNzdXWK+jowMdHZ0axacMjuOwYvpwqXVCCCGE1D8N5ginIm5ubnj69Ck0NTXh4OAgtZiZmQEArl27Bl9fXwwbNgwuLi6wsrJCSkqKWuJxcnJCVFSUVFn5dVdXVzx48KBa1yQq078ytLW1UVJSIlOen5+PpKQkuLq6VrlPVSg/J6GhoVI/FbUjhBBCSN1p8Alnv3790LVrV/j4+ODcuXNISUlBREQEFi9ejJs3bwIAWrZsiZCQENy+fRuxsbH45JNP1PZw81mzZmHv3r3Yt28fEhMTsXr1aty5c0fq6Fzv3r2Rk5OD+/fvq6V/ZYhEIly5cgVPnjzBixcv+PK//voLOjo66Nq1a5VjU5XKkklKNgkhhJD6pcEnnBzH4fTp0+jVqxcmTZoER0dHfPzxx3j8+DEsLS0BAJs3b0ajRo3QrVs3eHl5YcCAAXBzc1NLPGPHjkVAQAAWLFgANzc3JCcnw9fXV+qaTVNTUwwbNqxaD1hXpn9lrFy5EikpKbC3t5c6fX748GGMHTsW+vr6VY5NlRQllZRsEkIIIfUPx+gbus71798fVlZWOHDgAF92584d9O/fH0lJSTA0NFR5/9Xx4sULODk54ebNm7Czs1N6u6ysLBgbG0MsFkMoFNYoBpmY0tMQfnwveg7zg5m1jUr7JoQQQt5nqvz+bjA3Db0rcnNzsXPnTgwYMAACgQCHDx/GhQsX+GeGSrRr1w7r169HcnIyXFxcVN5/daSkpOCHH36oUrKpbmbWNhg2Y3ldh0EIIYSQCtARzlqWl5cHLy8vxMTEID8/H05OTliyZAmGDx9e+cb1oP/qUOcRTkIIIYSohyq/vynhJGpHCSchhBDy7lHl93eDv2mIEEIIIYTULUo4CSGEEEKIWlHCSQghhBBC1IoSTkIIIYQQolaUcJJ3W2EukiNCgcLcuo6EEEIIIQq8Vwmnp6cn5syZU+vjpqSkgOM43L59W+V9FxYWwsHBAREREdUeizGGqVOnonHjxhVuu3PnTnh5eakgatXgOA5utkawOzcRbrZGVX59JyGEEEJqx3uVcNYVGxsbpKeno23btirve+fOnbCzs0O3bt2q3cfZs2cRHByMkydP8nFyHIfQ0FCpdp9++ilu3bqF8PDwGkZdc4qSS0o6CSGEkPqHEk41KywshEAggJWVFTQ1VftiJ8YYtm/fDj8/vxr1k5SUBGtra3Tr1q3COLW1tfHJJ5/gu+++q9F4NVVZUklJJyGEEFK/vHcJZ2lpKRYuXIjGjRvDysoKy5cv5+syMzMxefJkmJubQygUok+fPoiNjeXrk5KS4O3tDUtLSxgaGqJTp064cOGCVP8ikQirVq3ChAkTIBQKMXXqVJnT3JcuXQLHcbh48SLc3d2hr6+Pbt26IT4+Xqqv1atXw8LCAkZGRpg8eTIWLVqEDh068PXR0dFISkrCkCFDKtzne/fuYdCgQTA0NISlpSXGjx+PFy9eAAB8fX0xa9YspKamguM4iEQiiEQiAMCwYcP4MgkvLy+cOHECeXl5Ss64apVPJn18fKR+KmpHCCGEkLrz3iWc+/btg4GBAW7cuIENGzZg5cqV/HvGR44ciYyMDJw5cwbR0dFwc3ND37598erVKwBATk4OBg8ejIsXLyImJgYDBw6El5cXUlNTpcbYuHEj2rdvj5iYGCxdulRhLIsXL8amTZtw8+ZNaGpq4tNPP+XrDh06hDVr1mD9+vWIjo5G8+bNsWPHDqntw8PD4ejoCCMjI4VjZGZmok+fPnB1dcXNmzdx9uxZPHv2DKNGjQIAfPvtt1i5ciWaNWuG9PR0REVFISoqCgAQFBTEl0m4u7ujuLgYN27cUDhmQUEBsrKypBZ1KP+SLHppFiGEEFI/qfYc7zugXbt2WLZsGQCgZcuW2L59Oy5evAg9PT1ERkYiIyMDOjo6AN4mjqGhoTh69CimTp2K9u3bo3379nxfq1atwvHjx3HixAl8/vnnfHmfPn0wf/58fj0lJUVuLGvWrIGHhwcAYNGiRRgyZAjy8/Ohq6uLbdu2wc/PD5MmTQIAfP311zh37hxycnL47R8/fowmTZpUuL/bt2+Hq6sr1q5dy5f99NNPsLGxQUJCAp+wSk77l2ViYiJTpq+vD2NjYzx+/FjhmIGBgVixYkWFcRFCCCHk/fHeHeFs166d1Lq1tTUyMjIQGxuLnJwcmJqawtDQkF+Sk5ORlJQE4O0RzgULFsDZ2RkmJiYwNDREXFyczBFOd3f3KsdibW0NAMjIyAAAxMfHo3PnzlLty6/n5eVBV1e3wjFiY2MRFhYmtU+tWrUCAH6/qkpPTw+5uYofQxQQEACxWMwvaWlp1RqHEEIIIQ3De3eEU0tLS2qd4ziUlpYiJycH1tbWuHTpksw2JiYmAIAFCxbg/Pnz2LhxIxwcHKCnp4cRI0agsLBQqr2BgUGVY5Fcc1haWqr0vpiZmeHu3bsVtsnJyYGXlxfWr18vUydJcqvq1atXMDc3V1ivo6PDHyVWJ47jsGL6cKl1QgghhNQ/713CqYibmxuePn0KTU1NqZtkyrp27Rp8fX0xbNgwAG+TOUWny2vKyckJUVFRmDBhAl9W9lpKAHB1dcWOHTvAGFOYbLm5ueHYsWMQiURVukteS0sLJSUlMuVJSUnIz8+Hq6ur0n2pUvl9DQ0NxdfTDGUe4UTXcxJCCCH1x3t3Sl2Rfv36oWvXrvDx8cG5c+eQkpKCiIgILF68GDdv3gTw9prPkJAQ3L59G7Gxsfjkk0+qdESyKmbNmoW9e/di3759SExMxOrVq3Hnzh2pZKt3797IycnB/fv3FfYzc+ZMvHr1CmPGjEFUVBSSkpLw559/YtKkSXITSgmRSISLFy/i6dOneP36NV8eHh6OFi1awN7eXjU7Wg2VJZOUbBJCCCH1CyWc/4/jOJw+fRq9evXCpEmT4OjoiI8//hiPHz+GpaUlAGDz5s1o1KgRunXrBi8vLwwYMABubm5qiWfs2LEICAjAggUL4ObmhuTkZPj6+kpds2lqaophw4bh0KFDCvtp0qQJrl27hpKSEnz44YdwcXHBnDlzYGJiAg0Nxb/+TZs24fz587CxsZE6mnn48GFMmTJFNTtZA4qSSko2CSGEkPqHY/QN/c7o378/rKyscODAAb7szp076N+/P5KSkmBoaKjW8e/fv48+ffogISEBxsbGSm+XlZUFY2NjiMViCIVClcZ0/IflGJaxBcct5mLYjOUq7ZsQQgh5n6ny+5uu4ayncnNzsXPnTgwYMAACgQCHDx/GhQsX+GeGSrRr1w7r169HcnIyXFxc1BpTeno69u/fX6VkU916DvPD8eNvfxJCCCGkfqIjnPVUXl4evLy8EBMTg/z8fDg5OWHJkiUYPnx45RvXM+o8wkkIIYQQ9aAjnO8BPT09mddmEkIIIYS8i+imIUIIIYQQolaUcBJCCCGEELWihJMQQgghhKgVJZyEEEIIIUStKOEkhBBCCCFqRQknebcV5iI5IhQozK3rSAghhBCiACWcSgoODoaJiUmVtvH19YWPj0+1xxw/fjzWrl1bYZuUlBRwHIfbt28r3W919gUAXrx4AQsLC/zzzz9V3lYdOI6Dm60R7M5NhJutETiOg6enZ12HRQghhJByKOFU0ujRo5GQkKDyfkUiEbZu3SpTHhsbi9OnT2P27NkVbm9jY4P09HS0bdtWpXHJS5bNzMwwYcIELFu2TKVjVQfHcXLLL1++rLCOEEIIIXWDEk4l6enpwcLCotbG27ZtG0aOHFnh+9ELCwshEAhgZWUFTc3aeYb/pEmTcOjQIbx69apWxpNHmYSSkk5CCCGk/ninEs7S0lIEBgbCzs4Oenp6aN++PY4ePQrGGBwcHLBx40ap9rdv3wbHcXj48CEAIDMzE5MnT4a5uTmEQiH69OmD2NhYvn1sbCx69+4NIyMjCIVCdOzYETdv3gQg/zT06tWrYWFhASMjI0yePBmLFi1Chw4dZOLeuHEjrK2tYWpqipkzZ6KoqAgA4OnpicePH2Pu3LngOI5PkkpKSnD06FF4eXlJ9SMSibBq1SpMmDABQqEQU6dOlXtK/cSJE2jZsiV0dXXRu3dv7Nu3DxzHITMzU6q/P//8E87OzjA0NMTAgQORnp4OAFi+fDn27duH33//nY/r0qVLAIA2bdqgSZMmOH78eOW/MDUon0hqa2sDgNxLF+j0OiGEEFI/vFMJZ2BgIPbv34+dO3fi/v37mDt3LsaNG4crV67g008/RVBQkFT7oKAg9OrVCw4ODgCAkSNHIiMjA2fOnEF0dDTc3NzQt29f/mjd2LFj0axZM0RFRSE6OhqLFi2ClpaW3FgOHTqENWvWYP369YiOjkbz5s2xY8cOmXZhYWFISkpCWFgY9u3bh+DgYAQHBwMAQkJC0KxZM6xcuRLp6el8wnfnzh2IxWK4u7vL9Ldx40a0b98eMTExWLp0qUx9cnIyRowYAR8fH8TGxmLatGlYvHixTLvc3Fxs3LgRBw4cwJUrV5CamooFCxYAABYsWIBRo0bxSWh6ejq6devGb9u5c2eEh4fLnRcAKCgoQFZWltSiLoMHD+Y/M8ak6i5fvqy2cQkhhBBSBewdkZ+fz/T19VlERIRUuZ+fHxszZgx78uQJEwgE7MaNG4wxxgoLC5mZmRkLDg5mjDEWHh7OhEIhy8/Pl9re3t6e7dq1izHGmJGREd++vKCgIGZsbMyvd+nShc2cOVOqTffu3Vn79u359YkTJzJbW1tWXFzMl40cOZKNHj2aX7e1tWVbtmyR6uf48eNMIBCw0tJSqXJbW1vm4+MjVZacnMwAsJiYGMYYY19++SVr27atVJvFixczAOz169f8vgBgDx8+5Nt8//33zNLSUip2b29vuXMxd+5c5unpKbeOMcaWLVvGAMgsYrFY4TbKKt/niunDGVsmfPtTTj0hhBBCqkcsFqvs+/udOcL58OFD5Obmon///jA0NOSX/fv3IykpCU2aNMGQIUPw008/AQD++OMPFBQUYOTIkQDeni7PycmBqamp1PbJyclISkoCAMybNw+TJ09Gv379sG7dOr5cnvj4eHTu3FmqrPw68PYUtEAg4Netra2RkZFR4b7m5eVBR0dH7nWI8o56lo+rU6dOlcalr68Pe3v7KsUloaenh9xcxY8hCggIgFgs5pe0tDSl+iWEEEJIw1Q7d5qoQE5ODgDg1KlTaNq0qVSdjo4OAGDy5MkYP348tmzZgqCgIIwePRr6+vr89tbW1vy1iGVJrs1cvnw5PvnkE5w6dQpnzpzBsmXL8Msvv2DYsGHVjrv8KXmO41BaWlrhNmZmZsjNzUVhYSF/jaKEgYFBtWOpLC5W7pS0Iq9evYK5ubnCeh0dHf53om6nT5/G15PezlH5BN3Dw6NWYiCEEEJIxd6ZhLN169bQ0dFBamqqwkRi8ODBMDAwwI4dO3D27FlcuXKFr3Nzc8PTp0+hqakJkUikcBxHR0c4Ojpi7ty5GDNmDIKCguQmnE5OToiKisKECRP4sqioqCrvl7a2NkpKSqTKJDce/f3333JvQqqIk5MTTp8+LVWmqrgk7t27V2c35DDGpBLLwsJCANoIDQ2VaSvvHxeEEEIIqX3vzCl1IyMjLFiwAHPnzsW+ffuQlJSEW7duYdu2bdi3bx8AQCAQwNfXFwEBAWjZsiW6du3Kb9+vXz907doVPj4+OHfuHFJSUhAREYHFixfj5s2byMvLw+eff45Lly7h8ePHuHbtGqKiouDs7Cw3nlmzZmHv3r3Yt28fEhMTsXr1aty5c6fKj+MRiUS4cuUKnjx5ghcvXgAAzM3N4ebmhqtXr1Z5nqZNm4YHDx7gyy+/REJCAn799Vf+JqWqxCYSiXDnzh3Ex8fjxYsX/J31ubm5iI6Oxocffljl2FRFmSOxyh6tJYQQQoj6vTMJJwCsWrUKS5cuRWBgIJydnTFw4ECcOnUKdnZ2fBs/Pz8UFhZi0qRJUttyHIfTp0+jV69emDRpEhwdHfHxxx/j8ePHsLS0hEAgwMuXLzFhwgQ4Ojpi1KhRGDRoEFasWCE3lrFjxyIgIAALFiyAm5sbkpOT4evrC11d3Srt08qVK5GSkgJ7e3up09STJ0/GoUOHqtQXANjZ2eHo0aMICQlBu3btsGPHDv4u9aqc5p4yZQqcnJzg7u4Oc3NzXLt2DQDw+++/o3nz5ujZs2eVY1MlRQmlh4cHJZuEEEJIPcOxBvbtHB4ejr59+yItLQ2Wlpa1Onb//v1hZWWFAwcO1LivvLw8ODk54ciRI1JHaqtjzZo12Llzp0pu3vnggw8we/ZsfPLJJ0pvk5WVBWNjY4jFYgiFwhrHUNaL9DSEH9+LnsP8YGZto9K+CSGEkPeZKr+/35lrOCtTUFCA58+fY/ny5Rg5cqTak83c3Fzs3LkTAwYMgEAgwOHDh3HhwgWcP39eJf3r6elh//79/Gn2qvjhhx/QqVMnmJqa4tq1a/jmm2/w+eef1zimFy9eYPjw4RgzZkyN+1IVM2sbDJuxvK7DIIQQQkgFGswRzuDgYPj5+aFDhw44ceKEzJ3sqpaXlwcvLy/ExMQgPz8fTk5OWLJkCYYPH67WcZUxd+5cHDlyBK9evULz5s0xfvx4BAQE1NrrL8tT5xFOQgghhKiHKr+/G0zCSeovSjgJIYSQd48qv7/fqZuGCCGEEELIu4cSTkIIIYQQolaUcBJCCCGEELWihJMQQgghhKgVJZzk3VaYi+SIUKAwt64jIYQQQogClHCqWHBwMExMTKq0ja+vL3x8fKo95vjx47F27Vp+XSQSYevWrVXq48cff4SNjQ00NDQUbvv333+jWbNmePPmTbVjVSWO4+BmawS7cxPhZmsEjuPq7B3vhBBCCFGMEk4VGz16NBISElTer6IkMjY2FqdPn8bs2bOr3XdWVhY+//xzfPnll3jy5AmmTp0KT09PzJkzR6pd69at8cEHH2Dz5s3VHktVFL0X/vLly1V+nz0hhBBC1IsSThXT09ODhYVFrY23bds2jBw5EoaGhtXuIzU1FUVFRRgyZAisra2hr6+vsO2kSZOwY8cOFBcXV3u8mlImoaSkkxBCCKk/GmTCWVpaisDAQNjZ2UFPTw/t27fH0aNHwRiDg4MDNm7cKNX+9u3b4DgODx8+BABkZmZi8uTJMDc3h1AoRJ8+fRAbG8u3j42NRe/evWFkZAShUIiOHTvi5s2bAOSfUl+9ejUsLCxgZGSEyZMnY9GiRejQoYNM3Bs3boS1tTVMTU0xc+ZMFBUVAQA8PT3x+PFjzJ07FxzH8clUSUkJjh49Ci8vrwrno6L9CQ4OhouLCwCgRYsW4DgOvr6+uHz5Mr799lt+vJSUFABv3xf/6tUrXL58WYnfhOqVTyS1tbUBQO4lCXR6nRBCCKkfGmTCGRgYiP3792Pnzp24f/8+5s6di3HjxuHKlSv49NNPERQUJNU+KCgIvXr1goODAwBg5MiRyMjIwJkzZxAdHQ03Nzf07dsXr169AgCMHTsWzZo1Q1RUFKKjo7Fo0SJoaWnJjeXQoUNYs2YN1q9fj+joaDRv3hw7duyQaRcWFoakpCSEhYVh3759CA4ORnBwMAAgJCQEzZo1w8qVK5Geno709HQAwJ07dyAWi+Hu7l7hfFS0P6NHj8aFCxcAAJGRkUhPT8e3336Lrl27YsqUKfx4NjY2AN4meB06dEB4eLjC8QoKCpCVlSW1qMvgwYP5z+VfmlVXSTEhhBBCpNXNy7XVqKCgAGvXrsWFCxfQtWtXAG+P3F29ehW7du3Cxo0b8fXXXyMyMhKdO3dGUVERfv75/9q786AorjwO4N9hZAYIt4MMGEVuQVEDRnZiBDaMonFdj01i8IgahCQemxjxwCio2S0srFqXNdFkK4nHroF1U2oSUaNBB8UgXiASXBSWw7ggIuEKCMr89g+LrrQyCDjDNb9P1ZRMv9ev3/tVD/PzdffjS2HWMz09HefPn0dFRQXkcjmAhzOPhw4dwldffYWoqCiUlpZi1apVGD58OADA09NTZ3+2b9+OiIgILFq0CAAQGxuL48ePo76+XlTPzs4OH330EaRSKYYPH46pU6ciNTUVkZGRsLe3h1QqhZWVFZRKpbBPSUkJpFJpu5fwOzKegQMHAgAcHByE9mUyGSwsLETHa+Xs7IySkhKdx4yPj8emTZt0ljPGGGPMuPS7Gc6CggI0NDRg4sSJsLS0FF579+5FYWEhnJ2dMXXqVHzxxRcAgG+//RZNTU149dVXATy8XF5fX4+BAweK9i8qKkJhYSEA4P3338fixYuhVquxZcsWYXtb8vPzMW7cONG2R98DwIgRIyCVSoX3Tk5OqKioaHesjY2NkMvl7d6v2JHxdJa5uTkaGnQvQxQTE4OamhrhdfPmzS4dhzHGGGP9Q7+b4WydOUxJScHgwYNFZa0zfIsXL8b8+fOxbds27Nq1C7NnzxYelKmvr4eTkxM0Gs1jbbfem7lx40bMmTMHKSkpOHr0KOLi4pCcnIyZM2d2ud+PXpKXSCTQarXt7qNQKNDQ0IDm5mbhXsZHdWQ8nVVVVQV3d3ed5XK5XIi1oR05cgSxix6O/dHEOzg4uFv6wBhjjLH29buE09fXF3K5HKWlpToTjpdffhnPPPMMdu7ciWPHjuH06dNCmb+/P8rLyzFgwAAMGzZM53G8vLzg5eWFFStWIDw8HLt27Woz4fT29saFCxfwxhtvCNsuXLjQ6XHJZDK0tLSItrU+eJSXl9fmQ0idGU9HjtcqNzcXr7zySofb0iciEiWWzc3NAGQ4dOjQY3XbSrIZY4wx1v363SV1KysrREdHY8WKFdizZw8KCwtx+fJlbN++HXv27AEASKVSLFy4EDExMfD09BTu9QQAtVoNlUqFGTNm4Pjx4yguLsYPP/yADz74ABcvXkRjYyOWLVsGjUaDkpISnD17FhcuXICPj0+b/Vm+fDk+//xz7NmzBzdu3MCf/vQn5OTkdHrZnmHDhuH06dO4desWKisrATy859Lf3x/p6ek693vSeNo7XmZmJoqLi1FZWSnMthYXF+PWrVtQq9Wd6r8+PfpwUFfrMMYYY6x79LuEEwA+/PBDbNiwAfHx8fDx8cHkyZORkpICV1dXoU5ERASam5uFh3laSSQSHDlyBEFBQVi0aBG8vLzw+uuvo6SkBI6OjpBKpbh79y7eeOMNeHl54bXXXsOUKVN0PiQzd+5cxMTEIDo6Gv7+/igqKsLChQthZmbWqTFt3rwZxcXFcHd3h4ODg7B98eLF2Ldvn879njQeXaKjoyGVSuHr6wsHBweUlpYCAJKSkjBp0iS4uLh0qv/6piuhDA4O5mSTMcYY62UkZKTfzmfOnEFoaChu3rzZbuJlCBMnToRSqcQ//vGPp26rsbER3t7e+Ne//iWaqTWE5uZmeHp64ssvv8T48eM7vF9tbS1sbGxQU1MDa2trvfbp4I6NmFmxDQcHrcDMJRv12jZjjDFmzPT5/d3v7uF8kqamJty5cwcbN27Eq6++avBks6GhAZ988gnCwsIglUqRlJSE77//HidOnNBL++bm5ti7d69wmd2QSktLsW7duk4lm4Y2YWYEDh58+C9jjDHGeiejm+HcvXs3IiIiMGbMGHzzzTePPcmub42NjZg2bRqysrJw7949eHt7Y/369Zg1a5ZBj9ubGHKGkzHGGGOGoc/vb6NLOFn344STMcYY63v0+f3dLx8aYowxxhhjvQcnnIwxxhhjzKA44WSMMcYYYwbFCSdjjDHGGDMoTjgZY4wxxphBGd06nMy4FVy7ivtlP8LUaQQ8fPx6ujuMMcaYUeAZzh4WEhKC995776nb2bBhA6Kiop6+Q+1Yu3Ytli9fbtBj6EtzczPmzJkDiUQivLZu3YrXXhoDn9Nv4bWXxojKHn0VFBT09BAYY4yxfoPX4exhVVVVMDU1hZWV1RPrhoSEYMyYMfjrX/8q2l5eXg4vLy9cvXrVoH/jvLKyEm5ubsjOzoabm1uH9+vudThXr16NrVu3tln2nNIEl9+yhP+n9cgq17bbjkQigVbbfh3GGGOsv+J1OPsRe3v7DiWb7fnss8/wwgsvGDTZBACFQoGwsDDs3LnToMd5Gu0lm51FRDAx4Y8IY4wx9rT427STDh8+DFtbW7S0tAAAsrOzIZFIsHbtWqHO4sWLMW/ePNy9exfh4eEYPHgwLCws4Ofnh6SkJFF7j15S37FjBzw9PWFmZgZHR0e88sorAICFCxciLS0NiYmJwmXf4uJiAEBycjKmTZsmaler1SIhIQEeHh6Qy+UYOnQo/vznPwMAiouLIZFIsH//fkyYMAHm5uZ4/vnncf36dVy4cAFjx46FpaUlpkyZgjt37ojanTZtGpKTk/USS31rbm4WJZunTp3CpUuXAACZmZmQy+U6901JSWlzOxHx5XXGGGPsKXHC2UkTJkxAXV0dsrKyAABpaWlQKBTQaDRCnbS0NISEhODevXsICAhASkoKcnNzERUVhfnz5+P8+fNttn3x4kX88Y9/xObNm5Gfn49jx44hKCgIAJCYmAiVSoXIyEiUlZWhrKwMQ4YMQVVVFfLy8jB27FhRWzExMdiyZQs2bNiAvLw8fPnll3B0dBTViYuLw/r163H58mUMGDAAc+bMwerVq5GYmIgzZ86goKAAsbGxon3GjRuHn376SUh229LU1ITa2lrRqzvs2LFD9D4kJASNjY0AgBs3bmDu3Lk697WxsYGuu0t8fX3110nGGGPMCPFT6p1kY2ODMWPGQKPRYOzYsdBoNFixYgU2bdqE+vp61NTUoKCgAMHBwRg8eDCio6OFfZcvX47vvvsO+/fvx7hx4x5ru7S0FM888wx+97vfwcrKCi4uLnjuueeE48pkMlhYWECpVIr2ISI4OzsL2+rq6pCYmIiPPvoICxYsAAC4u7vjxRdfFB0vOjoaYWFhAIB3330X4eHhSE1Nxfjx4wEAERER2L17t2if1uOUlJRg2LBhbcYoPj4emzZt6kg49aqwsFD4edSoUQAgJMbz5s0D8PAezrYUFxcL437U/fv39dhLxhhjzPjwDGcXBAcHQ6PRgIhw5swZzJo1Cz4+PkhPT0daWhqcnZ3h6emJlpYWfPjhh/Dz84O9vT0sLS3x3XffobS0tM12J06cCBcXF7i5uWH+/PnYt28fGhoa2u1L6wyemZmZsO3atWtoampCaGhou/u2JmUAhNlPPz8/0baKigrRPubm5gDQbr9iYmJQU1MjvG7evNluP/TF3d1d+DknJwcAhKT4n//8J958802d++pKngHA1NRUL/1jjDHGjBUnnF0QEhKC9PR0XLlyBaamphg+fDhCQkKg0WiQlpaG4OBgAMDWrVuRmJiINWvW4NSpU8jOzkZYWBiam5vbbNfKygqXL19GUlISnJycEBsbi9GjR6O6ulpnXxQKBQDg559/Fra1JoVP8utESiKRtLnt0ae0q6qqAAAODg4625XL5bC2tha9usOSJUtE7zUajRALT09P7Nu3T+e+NTU1QgwelZeXp79OMsYYY0aIE84uaL2Pc9u2bUJy2ZpwajQahISEAADOnj2L6dOnY968eRg9ejTc3Nxw/fr1dtseMGAA1Go1EhISkJOTg+LiYpw8eRIAIJPJhIeVWrm7u8Pa2lqUFHl6esLc3Bypqal6HPVDubm5MDU1xYgRI/Te9tOSyWRYtWqV8P63v/0tAgICAACBgYFoamrSue/UqVPb3C6RSODh4aHfjjLGGGNGhhPOLrCzs8OoUaOwb98+IbkMCgrC5cuXcf36dSEJ9fT0xIkTJ/DDDz/g2rVreOutt3D79m2d7R4+fBh/+9vfkJ2djZKSEuzduxdarRbe3t4AHl72zczMRHFxMSorK6HVamFiYgK1Wo309HShHTMzM6xZswarV6/G3r17UVhYiHPnzuHzzz9/6rGfOXNGeLK9N0pISBAlnU+D1+FkjDHG9IMTzi4KDg5GS0uLkHDa29vD19cXSqVSSBDXr18Pf39/hIWFISQkBEqlEjNmzNDZpq2tLQ4cOICXXnoJPj4++OSTT5CUlCTMJkZHR0MqlcLX1xcODg7CvaCLFy9GcnKyKDnasGEDVq5cidjYWPj4+GD27NmP3Y/ZFcnJyYiMjHzqdgwpISEBTU1NCA8PF21v7yn1R924cYOTTcYYY0xP+C8N9QNEhMDAQKxYseKxJEufjh49ipUrVyInJwcDBnR8gYPu/ktDulRWVuLbA/sx5lkLWLkG8N9SZ4wxxtqhz+9vXhapH5BIJPj73/+Oq1evGvQ4v/zyC3bt2tWpZLM3USgUWBS15MkVGWOMMaZXPMPJDK63zHAyxhhjrON4hpP1Ka3/p+muvzjEGGOMsafX+r2tj7lJTjiZwdXV1QEAhgwZ0sM9YYwxxlhn1dXVwcbG5qna4EvqzOC0Wi3+97//wcrKSufi6l1VW1uLIUOG4ObNm3y5voM4Zp3HMesajlvnccw6j2PWNR2JGxGhrq4Ozs7OMDF5uoWNeIaTGZyJiQmeffZZgx6jO/+iUX/BMes8jlnXcNw6j2PWeRyzrnlS3J52ZrMVr8PJGGOMMcYMihNOxhhjjDFmUJxwsj5NLpcjLi4Ocrm8p7vSZ3DMOo9j1jUct87jmHUex6xrujtu/NAQY4wxxhgzKJ7hZIwxxhhjBsUJJ2OMMcYYMyhOOBljjDHGmEFxwskYY4wxxgyKE07WZ3388ccYNmwYzMzMEBgYiPPnz/d0l3rMxo0bIZFIRK/hw4cL5ffu3cPSpUsxcOBAWFpa4g9/+ANu374taqO0tBRTp06FhYUFBg0ahFWrVuHBgwfdPRSDOX36NKZNmwZnZ2dIJBIcOnRIVE5EiI2NhZOTE8zNzaFWq3Hjxg1RnaqqKsydOxfW1tawtbVFREQE6uvrRXVycnIwYcIEmJmZYciQIUhISDD00AzqSXFbuHDhY+fe5MmTRXWMKW7x8fF4/vnnYWVlhUGDBmHGjBnIz88X1dHX51Gj0cDf3x9yuRweHh7YvXu3oYdnMB2JW0hIyGPn2ttvvy2qY0xx27lzJ0aNGiUs3K5SqXD06FGhvNedZ8RYH5ScnEwymYy++OIL+vHHHykyMpJsbW3p9u3bPd21HhEXF0cjRoygsrIy4XXnzh2h/O2336YhQ4ZQamoqXbx4kX7zm9/QCy+8IJQ/ePCARo4cSWq1mrKysujIkSOkUCgoJiamJ4ZjEEeOHKEPPviADhw4QADo4MGDovItW7aQjY0NHTp0iK5cuUK///3vydXVlRobG4U6kydPptGjR9O5c+fozJkz5OHhQeHh4UJ5TU0NOTo60ty5cyk3N5eSkpLI3NycPv300+4apt49KW4LFiygyZMni869qqoqUR1jiltYWBjt2rWLcnNzKTs7m15++WUaOnQo1dfXC3X08Xn873//SxYWFvT+++9TXl4ebd++naRSKR07dqxbx6svHYlbcHAwRUZGis61mpoaodzY4vbNN99QSkoKXb9+nfLz82ndunVkampKubm5RNT7zjNOOFmfNG7cOFq6dKnwvqWlhZydnSk+Pr4He9Vz4uLiaPTo0W2WVVdXk6mpKf373/8Wtl27do0AUEZGBhE9TCpMTEyovLxcqLNz506ytrampqYmg/a9JzyaOGm1WlIqlbR161ZhW3V1NcnlckpKSiIiory8PAJAFy5cEOocPXqUJBIJ3bp1i4iIduzYQXZ2dqKYrVmzhry9vQ08ou6hK+GcPn26zn2MPW4VFRUEgNLS0ohIf5/H1atX04gRI0THmj17NoWFhRl6SN3i0bgRPUw43333XZ37cNyI7Ozs6LPPPuuV5xlfUmd9TnNzMy5dugS1Wi1sMzExgVqtRkZGRg/2rGfduHEDzs7OcHNzw9y5c1FaWgoAuHTpEu7fvy+K1/DhwzF06FAhXhkZGfDz84Ojo6NQJywsDLW1tfjxxx+7dyA9oKioCOXl5aIY2djYIDAwUBQjW1tbjB07VqijVqthYmKCzMxMoU5QUBBkMplQJywsDPn5+fj555+7aTTdT6PRYNCgQfD29sY777yDu3fvCmXGHreamhoAgL29PQD9fR4zMjJEbbTW6S+/Ax+NW6t9+/ZBoVBg5MiRiImJQUNDg1BmzHFraWlBcnIyfvnlF6hUql55ng3oysAY60mVlZVoaWkRfUgAwNHREf/5z396qFc9KzAwELt374a3tzfKysqwadMmTJgwAbm5uSgvL4dMJoOtra1oH0dHR5SXlwMAysvL24xna1l/1zrGtmLw6xgNGjRIVD5gwADY29uL6ri6uj7WRmuZnZ2dQfrfkyZPnoxZs2bB1dUVhYWFWLduHaZMmYKMjAxIpVKjjptWq8V7772H8ePHY+TIkQCgt8+jrjq1tbVobGyEubm5IYbULdqKGwDMmTMHLi4ucHZ2Rk5ODtasWYP8/HwcOHAAgHHG7erVq1CpVLh37x4sLS1x8OBB+Pr6Ijs7u9edZ5xwMtYPTJkyRfh51KhRCAwMhIuLC/bv39/nfoGyvuX1118Xfvbz88OoUaPg7u4OjUaD0NDQHuxZz1u6dClyc3ORnp7e013pU3TFLSoqSvjZz88PTk5OCA0NRWFhIdzd3bu7m72Ct7c3srOzUVNTg6+++goLFixAWlpaT3erTXxJnfU5CoUCUqn0saftbt++DaVS2UO96l1sbW3h5eWFgoICKJVKNDc3o7q6WlTn1/FSKpVtxrO1rL9rHWN755RSqURFRYWo/MGDB6iqquI4/oqbmxsUCgUKCgoAGG/cli1bhsOHD+PUqVN49tlnhe36+jzqqmNtbd2n/5OpK25tCQwMBADRuWZscZPJZPDw8EBAQADi4+MxevRoJCYm9srzjBNO1ufIZDIEBAQgNTVV2KbVapGamgqVStWDPes96uvrUVhYCCcnJwQEBMDU1FQUr/z8fJSWlgrxUqlUuHr1qigxOHHiBKytreHr69vt/e9urq6uUCqVohjV1tYiMzNTFKPq6mpcunRJqHPy5ElotVrhi0+lUuH06dO4f/++UOfEiRPw9vbus5eFO+unn37C3bt34eTkBMD44kZEWLZsGQ4ePIiTJ08+dquAvj6PKpVK1EZrnb76O/BJcWtLdnY2AIjONWOL26O0Wi2ampp653nW+WegGOt5ycnJJJfLaffu3ZSXl0dRUVFka2sretrOmKxcuZI0Gg0VFRXR2bNnSa1Wk0KhoIqKCiJ6uDzG0KFD6eTJk3Tx4kVSqVSkUqmE/VuXx5g0aRJlZ2fTsWPHyMHBoV8ti1RXV0dZWVmUlZVFAOgvf/kLZWVlUUlJCRE9XBbJ1taWvv76a8rJyaHp06e3uSzSc889R5mZmZSenk6enp6i5X2qq6vJ0dGR5s+fT7m5uZScnEwWFhZ9cnmfVu3Fra6ujqKjoykjI4OKioro+++/J39/f/L09KR79+4JbRhT3N555x2ysbEhjUYjWr6noaFBqKOPz2PrcjWrVq2ia9eu0ccff9xnl/chenLcCgoKaPPmzXTx4kUqKiqir7/+mtzc3CgoKEhow9jitnbtWkpLS6OioiLKycmhtWvXkkQioePHjxNR7zvPOOFkfdb27dtp6NChJJPJaNy4cXTu3Lme7lKPmT17Njk5OZFMJqPBgwfT7NmzqaCgQChvbGykJUuWkJ2dHVlYWNDMmTOprKxM1EZxcTFNmTKFzM3NSaFQ0MqVK+n+/fvdPRSDOXXqFAF47LVgwQIierg00oYNG8jR0ZHkcjmFhoZSfn6+qI27d+9SeHg4WVpakrW1NS1atIjq6upEda5cuUIvvvgiyeVyGjx4MG3ZsqW7hmgQ7cWtoaGBJk2aRA4ODmRqakouLi4UGRn52H/8jClubcUKAO3atUuoo6/P46lTp2jMmDEkk8nIzc1NdIy+5klxKy0tpaCgILK3tye5XE4eHh60atUq0TqcRMYVtzfffJNcXFxIJpORg4MDhYaGCskmUe87zyRERJ2fF2WMMcYYY6xj+B5OxhhjjDFmUJxwMsYYY4wxg+KEkzHGGGOMGRQnnIwxxhhjzKA44WSMMcYYYwbFCSdjjDHGGDMoTjgZY4wxxphBccLJGGOMMcYMihNOxhhjjDFmUJxwMsYYY4wxg+KEkzHGGGOMGRQnnIwxxhhjzKD+Dy4Hqk5T0+KhAAAAAElFTkSuQmCC\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "plt.boxplot(data[['eyesight(left)', 'eyesight(right)']], \n",
+        "            labels=['eyesight(left)','eyesight(right)'],\n",
+        "            vert=False)\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 430
+        },
+        "id": "Hf64aNX6ytRY",
+        "outputId": "6143b581-231f-4c17-add3-746b190dbdc2"
+      },
+      "execution_count": 43,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "plt.boxplot(data[['Gtp', 'triglyceride']], vert=False, labels=['Gtp', 'triglyceride'])\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "id": "cI__s29M6kEq",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 430
+        },
+        "outputId": "dc42d3fc-2e3c-4dff-9deb-71751a09aac8"
+      },
+      "execution_count": 44,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlwAAAGdCAYAAADHQK08AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAAAuEklEQVR4nO3de3xU9Z3/8fckQ0ICSbgm4ZIbEQmCVQmKoClWqYjAiq76UKHiHYQi3lBZtahFwSu6KhZYSx9drOxWhG5Ru6UIKpKKBlBRbqKIQgIqkgRzIZfP7w92zm8mmUCAfJNAXs/H4zwI53zP9/s532Fm3sycc+IzMxMAAACciWjqAgAAAE50BC4AAADHCFwAAACOEbgAAAAcI3ABAAA4RuACAABwjMAFAADgGIELAADAMX9TF4CDqqurtWvXLsXFxcnn8zV1OQAAoB7MTMXFxeratasiIur+HIvA1Uzs2rVLKSkpTV0GAAA4Ct988426d+9e53YCVzMRFxcn6eADFh8f38TVAACA+igqKlJKSor3Pl4XAlczEfgaMT4+nsAFAMBx5nCnA3HSPAAAgGMELgAAAMcIXAAAAI4RuAAAABwjcAEAADhG4AIAAHCMwAUAAOAYgQsAAMAxAhcAAIBjBC4AAADHCFwAAACOEbgAAAAcI3ABAAA4RuACAABwjMAFAADgGIELAADAMQIXAACAYwQuAAAAxwhcAAAAjhG4AAAAHCNwAQAAOEbgAgAAcIzABQAA4BiBCwAAwDECFwAAgGMELgAAAMcIXAAAAI4RuAAAABwjcAEAADhG4AIAAHCMwAUAAOAYgQsAAMAxAhcAAIBjBC4AAADHCFwAAACOEbgAAAAcI3ABAAA4RuACAABwjMAFAADgGIELAADAMQIXAACAYwQuAAAAxwhcAAAAjhG4AAAAHCNwAQAAOEbgAgAAcIzABQAA4BiBCwAAwDECFwAAgGMELgAAAMcIXAAAAI4RuAAAABwjcAEAADhG4AIAAHCMwAUAAOAYgQsAAMAxAhcAAIBjBC4AAADHCFwAAACOEbgAAAAcI3ABAAA4RuACAABwjMAFAADgGIELAADAMQIXAACAYwQuAAAAxwhcAAAAjhG4AAAAHCNwAQAAOEbgAgAAcIzABQAA4BiBCwAAwDECFwAAgGMELgAAAMf8TV0AWo6tW7equLj4iPfzVZap9f4dKmubKvO3bvC64uLi1LNnzwbvFwCAAAIXGsXWrVt18sknH9W+ZyRHaO24tuo3Z7/WFVQ3cGUHbdmyhdAFAHCGwIVGEfhka8GCBerdu/cR7Ruzb4v07ji98sorKm13dKGtLhs3btSYMWOO6pM3AADqi8CFRtW7d2/169fvyHbaFSG9K/XOypK6nu6kLgAAXOKkeQAAAMcIXAAAAI4RuAAAABwjcLUwJSUlWrt2rUpKSpq6FDQyHnsAaDoErhZm06ZNys7O1qZNm5q6FDQyHnsAaDoELgAAAMecBK6HHnpIp59++hHtc9555+n22293UU6D15Genq5nn322UeoBGsKsWbOUnZ0tScrOzpbP5zvul5kzZ+rVV1/VypUrVVVVdcjjP3DggJ599llNmjRJzz77rA4cOHBE83es+7tQVVWllStX1nsOgJaq2TxX7AgMHjzYJk+efNh2xcXF9v333x9J1/Xu27UffvjBioqKDtkmLS3NZs2a1aDjFhYWmiQrLCxs0H5rysvLM0mWl5fndJwGHXfnOrNp8Qf/bGBNNR+NSdIJv6Snp9uiRYvCHv+UKVPM7/eHtPf7/TZlypR6zd+x7u/CokWLLD09vd5zALRUjfFcqe/7d4N+wmVmqqysVNu2bdWxY8eG7Nq5wP9YO3TooLi4uCauBmgYPp+vqUtoFKeeeqouv/xyvf766yHr77nnHj355JPq2LGj5s2bp/z8fM2bN08dO3bUk08+qXvuueeQ/R7r/i68/vrruvzyy3XqqacqNzdXxcXFys3NrXMOgJaq2T1X6pvgxo4dW+t/lfPnzzdJ9uabb1q/fv2sVatWtmLFCps2bZqddtpp3r4VFRU2adIkS0hIsA4dOtg999xj1157rV1yySVem+BPuB5++GHr06dPrRpOO+00e+CBB7y/v/zyy3bKKadYVFSUJScn28SJE71tP/74o914443WqVMni4uLs1/84he2fv16b3ugxnnz5ll6err5fL5adZiZ7d6920aMGGGtW7e29PR0W7BgQa1PuA43Vn3wCdch8AnXUXnmmWea/JOnxloWL15sI0eOtIyMDKusrDQzs/LycvP7/ZaUlGQVFRUhc1NRUWFJSUnm9/utvLw87Pwd6/4uVFZWWnp6uo0cOdKqqqpCtlVVVdWaA6ClasznSn3fv+v9q32ee+45bdmyRX379tUjjzwiSfrss88kSffdd5+eeuop9ejRQ+3bt9fKlStD9n388cf1yiuvaP78+erdu7eee+45LVmyRL/4xS/CjnXDDTfo4Ycf1ocffqgzzzxTkrRu3Tp98sknXiJ96aWXdOedd2rmzJkaNmyYCgsL9f7773t9XHHFFYqJidFbb72lhIQEzZkzRxdccIG2bNmiDh06SJK++OILLVq0SK+//roiIyPD1nLddddp165dWrFihVq1aqXbbrtNe/bsCWlTn7FqKi8vV3l5uff3oqKisO0aWmlpqaSDv0OwMQXGC4zfXDTVfDSGO++8s6lLaDSXXnqpVq9erUGDBum9997Teeedp9mzZ6uyslLTp0+X3x/6Uuf3+/XII49o3Lhxmj17dtjzNo91fxfee+89bd++Xa+++qoiIkK/oIiIiNDUqVND5gBoqZrjc6XegSshIUFRUVGKjY1VcnKyJHmXlz/yyCP65S9/Wee+zz//vKZOnapLL71UkvTCCy/ozTffrLN99+7dNXToUM2fP98LXPPnz9fgwYPVo0cPSdL06dN11113afLkyd5+gbarVq3SmjVrtGfPHkVHR0uSnnrqKS1ZskSvvfaabrnlFkkHv0b84x//qM6dO4etY8uWLXrrrbe0Zs0ar++XX3455Jcv13esmmbMmKGHH364zjlwZfv27ZKkMWPGNPrYgfHPOeecJhk7nKaeDzScvn37SpLy8/MlSdu2bZMkjRgxImz7wPpAu5qOdX8XAscWONaaas4B0FI1x+dKg/zy6v79+9e5rbCwULt379ZZZ53lrYuMjFR2draqq6vr3O/mm2/WDTfcoGeeeUYRERH605/+pFmzZkmS9uzZo127dumCCy4Iu+/HH3+s/fv31zqPrLS0NOTFMS0trc6wJR381MPv93tXd0lSVlaW2rVrd8Rj1TR16tSQTyCKioqUkpJSZ/uGkp6eLklasGBBSHB0bePGjRozZow3fnPRVPPRGIL/3bYEGzZskCR16dJFkpSZmSlJWrp0qW666aZa7ZcuXRrSrqZj3d+FwLFt2LBBZ599dq3tNecAaKma43OlQQJXmzZtGqKbECNHjlR0dLQWL16sqKgoVVRU6PLLL5ckxcTEHHLf/fv3q0uXLrW+2pQUEpYaou76jlVTdHS094lYYwrMXe/evdWvX78mG7+5aOr5cOmZZ55pMV8rLl68WDNmzFBGRoZycnIkSRMmTNCUKVP0wAMP6Lrrrgv5WrCyslK/+c1v5Pf7NWHChLB9Huv+LuTk5Cg9PV2PPfaYlixZEvJVSXV1da05AFqq5vhcOaKrFKOioo74/hUJCQlKSkrShx9+6K2rqqrS2rVrD7mf3+/X2LFjNX/+fM2fP19XXXWV9+YYFxen9PR0LV++POy+/fr1U0FBgfx+v0466aSQpVOnTvWuPSsrS5WVlcrLy/PWbd68Wfv27WvwsYCGdscddzR1CY3m97//vZYuXaqnnnrKOx8zKipKd9xxh3bv3q3u3btr7ty52rVrl+bOnavu3btr9+7duuOOOxQVFRW2z2Pd34XIyEg9/fTTWrp0qUaNGhVy5dWoUaNqzQHQUjXH58oRfcKVnp6uDz74QNu3b1fbtm0P+ZVgsEmTJmnGjBk66aSTlJWVpeeff14//vjjYS9Zv+mmm7yveYJPiJcO3lx1/PjxSkxM1LBhw1RcXKz3339fkyZN0pAhQzRw4ECNGjVKTzzxhE4++WTt2rVLb7zxhi699NJDfgUarFevXrrooos0btw4vfTSS/L7/br99ttDPqVpqLEAF8ysRdwaYsOGDXrttdd02WWXhax/4oknJB288eu4ceO89X6/X1OmTPG21+VY93fhsssu02uvvaa77rpLgwYN8tZnZGSEnQOgpWpuz5UjClx33323xo4dq1NOOUWlpaWaP39+vfa79957VVBQoGuvvVaRkZG65ZZbNHTo0MMmy549e2rQoEHau3evBgwYELJt7NixKisr06xZs3T33XerU6dO3leOPp9Pb775pu6//35df/31+u6775ScnKyf//znSkpKOpJD1vz583XTTTdp8ODBSkpK0vTp0/Xggw962xtyLMAFM9OsWbNOuK8XZ8yYobS0NHXp0kU5OTl1vp488cQTmj59umbPnq1t27YpMzNTEyZMqPcnU8e6vwuXXXaZLrnkEr333nvKz88/7BwALVVzeq74zMwae9Dq6mr17t1bV155pX7729/W2c7M1LNnT02YMOGEe7OoqaioSAkJCSosLFR8fLyzcdauXavs7Gzl5eU16jlLxzTurvXS3MHSLe9IXU9vPnUdZ1rSsQJAY6nv+3eDnDR/OF9//bX+/ve/a/DgwSovL9cLL7ygr776Stdcc02d+3z33XdauHChCgoKdP311zdGmQAAAE40SuCKiIjQH/7wB919990yM/Xt21f/+Mc/DnkZfmJiojp16qS5c+eqffv2jVFmi5CVlaW8vDxlZWU1dSloZDz2ANB0GiVwpaSk1Drp/XCa4JvOFiE2Npavk1ooHnsAaDoN+surAQAAUBuBCwAAwDECFwAAgGONcg4XUFJSIkmH/Q0D4cTs26LekjZu2qTSgvrdbLe+Nm7c2KD9AQAQDoELjWLTpk2SDv5S8iN1RnKE1o5rq9GjR2tdAweugLi4OCf9AgAgEbjQSEaNGiXp4K0JYmNjj2hfX2WZNu7foZcvTpX5Wzd4bXFxcerZs2eD9wsAQECT3GketTXWneYBAEDDqe/7NyfNAwAAOEbgAgAAcIzABQAA4BiBCwAAwDECFwAAgGMELgAAAMcIXAAAAI4RuAAAABwjcAEAADhG4AIAAHCMwAUAAOAYgQsAAMAxAhcAAIBjBC4AAADHCFwAAACOEbgAAAAcI3ABAAA4RuACAABwjMAFAADgGIELAADAMQIXAACAYwQuAAAAxwhcAAAAjhG4AAAAHCNwAQAAOEbgAgAAcIzABQAA4BiBCwAAwDECFwAAgGMELgAAAMcIXAAAAI4RuAAAABwjcAEAADhG4AIAAHCMwAUAAOAYgQsAAMAxAhcAAIBjBC4AAADHCFwAAACOEbgAAAAcI3ABAAA4RuACAABwjMAFAADgGIELAADAMQIXAACAYwQuAAAAxwhcAAAAjhG4AAAAHCNwAQAAOEbgAgAAcIzABQAA4BiBCwAAwDECFwAAgGMELgAAAMcIXAAAAI4RuAAAABwjcAEAADhG4AIAAHCMwAUAAOAYgQsAAMAxAhcAAIBjBC4AAADHCFwAAACOEbgAAAAcI3ABAAA4RuACAABwjMAFAADgGIELAADAMQIXAACAYwQuAAAAxwhcAAAAjhG4AAAAHCNwAQAAOEbgAgAAcIzABQAA4BiBCwAAwDECFwAAgGMELgAAAMcIXAAAAI4RuAAAABwjcAEAADhG4AIAAHCMwAUAAOAYgQsAAMAxAhcAAIBjBC4AAADHCFwAAACOEbgAAAAcI3ABAAA4RuACAABwjMAFAADgGIELAADAMQIXAACAYwQuAAAAxwhcAAAAjhG4AAAAHCNwAQAAOEbgAgAAcIzABQAA4BiBCwAAwDECFwAAgGMELgAAAMcIXAAAAI4RuAAAABwjcAEAADhG4AIAAHCMwAUAAOAYgQsAAMAxAhcAAIBjBC4AAADHCFwAAACOEbgAAAAcI3ABAAA4RuACAABwjMAFAADgGIELAADAMQIXAACAYwQuAAAAxwhcAAAAjhG4AAAAHCNwAQAAOEbgAgAAcIzABQAA4BiBCwAAwDECFwAAgGMELgAAAMcIXAAAAI4RuAAAABwjcAEAADhG4AIAAHCMwAUAAOAYgQsAAMAxAhcAAIBjBC4AAADHCFwAAACOEbgAAAAcI3ABAAA4RuACAABwjMAFAADgGIELAADAMQIXAACAYwQuAAAAxwhcAAAAjhG4AAAAHCNwAQAAOEbgAgAAcIzABQAA4BiBCwAAwDECFwAAgGMELgAAAMcIXAAAAI4RuAAAABwjcAEAADjmb+oC0PS2bt2q4uJi+SrL1Hr/DpW1TZX5W4dtGxcXp549ezZyhQAAHN8IXC3c1q1bdfLJJ0uSzkiO0NpxbdVvzn6tK6iuc58tW7YQugAAOAIErhauuLhYkrRgwQL16xIpvTtOr7zyikrbnVyr7caNGzVmzBhvHwAAUD8ELkiSevfurd7JEdK7Uu+sLKnr6U1dEgAAJwxOmgcAAHCMwAUAAOAYgQsAAMAxAlcLUFJSorVr16qkpKSpS5HU/OoBAMA1AlcLsGnTJmVnZ2vTpk1NXYqk5lcPAACuEbgAAAAc47YQaHTZ2dkhf6L5iYiIUHV13Te/lSSfz6eEhAQNGDBAlZWVWrlypaqqqhQREaGuXbsqNTVVa9asUWVlpSSpffv2ys7O1ldffaXvvvtOVVVV+umnn7z+4uPjNWXKFE2aNElTp0719v3pp5904MABFRUVqaqqStHR0fL5fCopKVFpaal8Pp/at2+vSZMmKS0tTbm5ufr000+1d+9e7d69W/v371d1dbX8fr/i4+PVsWNHlZSUqKyszNu3rKxMCQkJ8vv9uuCCC9ShQwetX79eO3bsUFlZmbp166bk5GQVFRXps88+k5mpQ4cOys/P14EDB1RWViZJKi8vV2VlpcxM7dq10+WXX64DBw5IkiIjI5Wdna28vDxVVVWpoKBAycnJ6tWrl6699lpdd911+uSTT/TTTz8pJSVFZ555pjIzM/X111+rvLxceXl5KiwsVFJSklJSUlRRUaGzzz5blZWVWrhwoQ4cOKCcnBz17NlT3377rbp3764vvvhC69atk5np5JNPVo8ePXT++ecrJydHq1ev1s6dO7V7927t2bNHeXl5Ki0tVXp6uq699lrl5ORozpw52rZtm9LT09WnTx+9//77kqTzzjtP5513niIjI1VVVaX33ntP+fn56tixoz799FNt2bJF77//vvbv36/o6GhdcsklGjp0qLdPwIEDBzR79mxvjFNOOUWrV68OGUOS139iYqJKS0v17LPPaseOHZKkXr16KSUlRQMHDlRKSopycnJq1dWlSxfl5OSE9BWodfv27crMzNSECRMUFRVV6995oJ+dO3fqu+++U+fOndWtWzfl5OSoqqpKzz//vFatWqU2bdro9NNPV5cuXdStWzcNGjRIq1evDhm/qqrKO97AmJJqrQvUEZifrVu3yufzacCAASHHGFxf8Dh1HX/w3Acf38qVK7Vy5cpaj224eQjX35FsGzBggPfv6lDzHu7fSM329T3GwsJCDR8+XDt27FBqaqreeOMNJSQk1DmmMwZPfn6+3XbbbZaZmWnR0dGWmJhogwYNstmzZ9tPP/1kZmaSbPHixQ0+dmFhoUmywsLCBu87Ly/PJFleXt6ht+1cZzYt/uCfR9hPfUliYWFp4iUiIuKY++jcubNNmTLF0tPT671PYmKiLVq0yMzMpkyZYn6//5DtExISrHPnzkdUV3p6eti6OnfubImJiXXu5/f7bcqUKSGvV4sWLarz+OLj483n8x2yv5rta867z+er1UegjkPNT3p6ui1atChsfXUdf2CfmscXbk46d+4c0raucQ5VQ13b6jPvAeHmIND+UOMGy8zMDDtuZmbmUb+P1VTf928C1//Ztm2bJScnW1ZWlv3Xf/2Xff7557Zt2zZbsmSJXXzxxfaXv/zFzAhcdfVTH8f6As/CcqIsgTfecG/AHTp0aPDx2rRpY5GRkYdt161btzq3tWrVyiTZlVdeaeeee663vn///jZ69GiTVGuMcIHB5/PZJZdcYpIsKSnJbr311rBjZGVleesD/R+u70Cfgbpyc3OtuLjYZsyY4W3PyckxSdahQwf72c9+ZpLs1ltv9fYLvPkvWrTIfD6f9e/f33w+nw0bNszmzZtnw4YNCxkvEAj79Olj8fHx3vqEhASTZAsWLAip/9Zbb7X8/HwbOnSot27o0KGWn59v8+bN8+oI7uOXv/yl3XfffV44yszM9ILayJEjvePMzc21/v371zr+3NxcGzlypPl8Pi+QBI5Pkp177rm2fPlyW758echjGwhNPp+v1jiB/sLVMHLkSO+xDmybPHmySbKoqCiTZP/xH/8Rcrw1Q9eUKVO8x3PevHlh56eumgLHGBy2LrroIsvNzbWLLrrIW9dQoYvAdYSGDh1q3bt3t/3794fdXl1dbWlpaSFPtLS0NDMzmzZtmp122mn2u9/9zrp3724xMTF2xRVX2L59++o9/okeuBr6DYTlxFgO9wnHibgEPtUIfsMNLJGRkRYZGWkdO3asc/+aIW3IkCHezwUFBSHbWrVqZVFRUeb3+23fvn0hNQT3N3z4cBsxYoSlpaV524LbDB8+3MrLyy0pKcn8fr/t37/fYmJiLDIy0tLS0iwyMjLkkxKfz2cxMTFWUlJiSUlJIUEsOjrapINvpGVlZZaWlmYxMTE2YsSIkDFSU1MtMTHRYmNjax1zq1atLDIy0oYPHx4SgAI1JyYmWnp6ulVWVlplZaWlp6fbiBEj7OKLL/bGrqiosKqqKhs5cqRlZGRYWVmZN3ZJSYm3T3p6uo0cOdKqqqrMzKy0tNQbp3Pnzub3+23EiBFWVVVlZWVlXq0pKSnenPr9fktKSrLhw4dbRkaGlZSUmN/vt8TEREtMTDS/32/l5eVmZvbTTz95x5OSkhIydkVFhVdj69atLTY21g4cOOC9zgaONSkpyTv+gOBjLS8vt/T0dG/eA/0H2o0YMcJiY2MtLS2t1vEHHDhwwGJiYmrVEG5beXm5Nwfl5eVeHZWVlSHHFJiD4PYVFRUhfQfm2OfzWWlpaci24GP84YcfvHkMfEMVEDzHR/I+XRcC1xH4/vvvzefz2YwZMw7Zbs+ePSbJ5s+fb/n5+bZnzx4zOxi42rRpY+eff76tW7fO3nnnHTvppJPsmmuuqbOvsrIyKyws9JZvvvmmXg/Y0Vi1apVJB/+nlZeXF7IsWLDAJNmqVasOG7gO1c/hlqZ+k2NpnssZZ5xRr3axsbG11rVp06Ze+x7qa6SmWAIBqUePHiHre/Xq5f189913h913zJgxtdYF93POOefU2n7vvfeaJJs4cWKdNeXm5trq1avr3P7iiy+amdmcOXPq7Ov000+vtW7FihXePv369QvZdvfdd9uKFStCaggeQ5LNnTs3bD1XX321V1e4uq+88kpv/MAYubm5dtttt3ljBwT2D641cHwvvvhiSG1mZrNmzao1TmB+go9Hkr3wwgvez/PmzfPGCvQ/b948b8xZs2bV6r/m2DXnJ1B3QGD8wLwFbws+1uAxavYf3O5QbYKPteY4NbcFxps3b16tOQ8+pppzEGhfV9+B9uFq79u3r0kHP9kK58ILL/SeM8eqvoGLk+YlffHFFzIz9erVK2R9p06dvJNhJ06cqMcff1yS1K5dOyUnJ4e0LSsr0x//+Ed169ZNkvT8889r+PDhevrpp2u1laQZM2bo4YcfdnE4tWzfvl2SNGbMmEO2OSejzzH3AxyJNm3a1Kud31/7pSomJibkpPu6dO/eXXv27Dni2lw5//zz9Y9//EM//vhjyPo+ffpo8+bNkqQePXqE3feuu+7SggULQtYF9xM4kTzYjTfeqMcff1xbt26ts6a+ffvKzOrcHhMTI0kaMWKEJIXtK/BaGSw/P9/bJzMzU2vXrvW29ejRQ/n5+SE1BI9R8+dg/fv316uvvqqYmBhvv2CBf1c1+w/UGDy/gf2Daw0cX+C4g8fYtm2b93NsbGxIu+DxgtcHjiVQV6D/ESNGeBenBPoN7r/m2IF9ggWPGfg50KZmPYG+gscIN38114VrE27curYFxgvUFTznwetrzkG4xz+475pzFdz3rl27JEnTpk2r1UaSHnjgAf39738P+5xxhdtCHMKaNWu0fv169enTR+Xl5Ydsm5qa6oUtSRo4cKCqq6u9F9Capk6dqsLCQm/55ptvGrT2YOnp6ZKkBQsWKC8vL2QJvHgH2hxtP4dbgHDqE5gkeVc6BistLa3Xvt9+++0R1eTa22+/LengVZvBPvvsM+/nL7/8Muy+Tz/9dK11wf2kpqbW2v7yyy9Lknr27FlnTRs2bNCGDRvq3B6Y66VLl9bZV+vWrWut69Kli7dPzTfHL7/8Ul26dAmpIXiMmj8H++ijj7y6wtUd+HfVpUsXb4wNGzZ4NQbPb2D/4FoDxxc47uAxMjMzvZ8DN28OtAs+nuD1gWMJ9BPof+nSpd6YgX6D+685dmCfYMFjBn4OtKlZT6Cv4DHCzV/NdeHahBu3rm2B8QJ1Bc958PqacxDu8Q/uu+ZcBffdtWtXSarzg43p06dLCv+cceaYP0s7ARzuK8XBgwfb5MmTzSz8SfPTpk2zjIyMkHWB8yVWrlxZrxo4h4ulJS6cwxW6jXO4OIeLc7g4h+uEd+GFF1q3bt3CnjQfHLhatWplr732Wsj2adOmWWRkpO3cudNb97e//c0iIiIsPz+/XuOf6IHLjNDFwhJYDnWVYvv27Rt8PNdXKV5zzTUmHd1ViuPHjw87RvBVioH+D9d3oM9AXatXr7aioiJ77LHHvO2BqxTbt2/vXaU4fvz4el2lOGfOnFpXKXbq1Mmkg1cpxsXFeeuDr1IMrn/8+PG2c+dO7xwi6eBViDt37rQ5c+bUeZXiPffcU+dVioHjXL16dchVisHrD3WV4jnnnGPLli2zZcuWHfIqxXD9hauh5lWKq1evrnWVYuD8tfpcpThnzpyw81NXTeGuUrzwwgvt3XffDZl3rlJsIl988YUlJSVZVlaWLVy40D7//HPbtGmT/ed//qclJSXZnXfeaWZmPXv29C7r3bt3r5n9/5PmhwwZYuvXr7d3333XTj75ZLvqqqvqPX5LCFxmhC4WluawNMR9uBITE5vlfbgyMjLC1hX4NKmu/Y6n+3BlZGTUeZ+ruo4/sE/N4ws3J8GPU13zcLgamuI+XOGOsTndh8tndogzJVuY/Px8PfbYY3rjjTf07bffKjo6WqeccoquuOIKTZgwQbGxsfrrX/+qO++8U9u3b1e3bt20fft2PfTQQ1qyZInGjRun6dOna+/evRoxYoTmzp1b6zyNuhQVFSkhIUGFhYWKj49v0ONau3atd4frfv361b0tOUKaO1i65R2p6+lH1M+R8Pl8R70vGgd3mudO89xp/iDuNK9DjnOk207EO83X9/2bwNUAAoFr/fr1R91HSwpcDdUPAABNrb7v31ylCAAA4BiBqwXIyspSXl6esrKymroUSc2vHgAAXCNwNYCHHnromL5OdC02Nlb9+vXzbtLX1JpbPQAAuEbgAgAAcIzABQAA4BiBCwAAwDF+eXULF/hdYGvXrlVMj7bqLWnjpk0qLah9D6aNGzc2cnUAAJwYCFwt3KZNmyRJN998s85IjtDacW01evRorQsTuALi4uIaqzwAAE4IBK4WbtSoUZIO3qqhTVSENu7foZcvTpX5W4dtHxcX5/2mewAAUD/cab6ZcHmneQAA4AZ3mgcAAGgmCFwAAACOEbgAAAAcI3ABAAA4RuACAABwjMAFAADgGIELAADAMQIXAACAYwQuAAAAxwhcAAAAjhG4AAAAHCNwAQAAOEbgAgAAcIzABQAA4BiBCwAAwDECFwAAgGMELgAAAMcIXAAAAI4RuAAAABwjcAEAADhG4AIAAHCMwAUAAOAYgQsAAMAxAhcAAIBjBC4AAADHCFwAAACOEbgAAAAcI3ABAAA4RuACAABwjMAFAADgGIELAADAMQIXAACAYwQuAAAAxwhcAAAAjhG4AAAAHCNwAQAAOEbgAgAAcIzABQAA4BiBCwAAwDECFwAAgGMELgAAAMcIXAAAAI4RuAAAABwjcAEAADhG4AIAAHCMwAUAAOAYgQsAAMAxAhcAAIBjBC4AAADHCFwAAACOEbgAAAAcI3ABAAA4RuACAABwjMAFAADgGIELAADAMQIXAACAYwQuAAAAxwhcAAAAjhG4AAAAHCNwAQAAOEbgAgAAcIzABQAA4BiBCwAAwDECFwAAgGMELgAAAMcIXAAAAI4RuAAAABwjcAEAADhG4AIAAHCMwAUAAOAYgQsAAMAxAhcAAIBjBC4AAADHCFwAAACO+Zu6ABxkZpKkoqKiJq4EAADUV+B9O/A+XhcCVzNRXFwsSUpJSWniSgAAwJEqLi5WQkJCndt9drhIhkZRXV2tXbt2KS4uTj6fr8H6LSoqUkpKir755hvFx8c3WL8IxTw3Hua6cTDPjYe5bhyu5tnMVFxcrK5duyoiou4ztfiEq5mIiIhQ9+7dnfUfHx/PE7kRMM+Nh7luHMxz42GuG4eLeT7UJ1sBnDQPAADgGIELAADAMQLXCS46OlrTpk1TdHR0U5dyQmOeGw9z3TiY58bDXDeOpp5nTpoHAABwjE+4AAAAHCNwAQAAOEbgAgAAcIzABQAA4BiB6wT34osvKj09Xa1bt9aAAQO0Zs2api7puDFjxgydeeaZiouLU2JiokaNGqXNmzeHtCkrK9PEiRPVsWNHtW3bVv/6r/+q3bt3h7TZsWOHhg8frtjYWCUmJmrKlCmqrKxszEM5rsycOVM+n0+33367t455bjg7d+7UmDFj1LFjR8XExOjUU0/VRx995G03M/3mN79Rly5dFBMToyFDhmjr1q0hfezdu1ejR49WfHy82rVrpxtvvFH79+9v7ENptqqqqvTggw8qIyNDMTExyszM1G9/+9uQ37XHPB+dd999VyNHjlTXrl3l8/m0ZMmSkO0NNa+ffPKJcnJy1Lp1a6WkpOiJJ5449uINJ6yFCxdaVFSU/f73v7fPPvvMbr75ZmvXrp3t3r27qUs7LgwdOtTmz59vGzZssPXr19vFF19sqamptn//fq/N+PHjLSUlxZYvX24fffSRnX322TZo0CBve2VlpfXt29eGDBli69atszfffNM6depkU6dObYpDavbWrFlj6enp9rOf/cwmT57srWeeG8bevXstLS3NrrvuOvvggw/syy+/tP/93/+1L774wmszc+ZMS0hIsCVLltjHH39s//Iv/2IZGRlWWlrqtbnooovstNNOs3/+85/23nvv2UknnWRXX311UxxSs/Too49ax44dbenSpfbVV1/Zn//8Z2vbtq0999xzXhvm+ei8+eabdv/999vrr79ukmzx4sUh2xtiXgsLCy0pKclGjx5tGzZssFdffdViYmJszpw5x1Q7gesEdtZZZ9nEiRO9v1dVVVnXrl1txowZTVjV8WvPnj0myd555x0zM9u3b5+1atXK/vznP3ttNm7caJIsNzfXzA6+OERERFhBQYHX5qWXXrL4+HgrLy9v3ANo5oqLi61nz562bNkyGzx4sBe4mOeGc++999q5555b5/bq6mpLTk62J5980lu3b98+i46OtldffdXMzD7//HOTZB9++KHX5q233jKfz2c7d+50V/xxZPjw4XbDDTeErLvsssts9OjRZsY8N5Sagauh5nX27NnWvn37kNeOe++913r16nVM9fKV4gnqwIEDysvL05AhQ7x1ERERGjJkiHJzc5uwsuNXYWGhJKlDhw6SpLy8PFVUVITMcVZWllJTU705zs3N1amnnqqkpCSvzdChQ1VUVKTPPvusEatv/iZOnKjhw4eHzKfEPDek//mf/1H//v11xRVXKDExUWeccYbmzZvnbf/qq69UUFAQMtcJCQkaMGBAyFy3a9dO/fv399oMGTJEERER+uCDDxrvYJqxQYMGafny5dqyZYsk6eOPP9aqVas0bNgwScyzKw01r7m5ufr5z3+uqKgor83QoUO1efNm/fjjj0ddH7+8+gT1/fffq6qqKuQNSJKSkpK0adOmJqrq+FVdXa3bb79d55xzjvr27StJKigoUFRUlNq1axfSNikpSQUFBV6bcI9BYBsOWrhwodauXasPP/yw1jbmueF8+eWXeumll3TnnXfq3/7t3/Thhx/qtttuU1RUlMaOHevNVbi5DJ7rxMTEkO1+v18dOnRgrv/Pfffdp6KiImVlZSkyMlJVVVV69NFHNXr0aElinh1pqHktKChQRkZGrT4C29q3b39U9RG4gHqYOHGiNmzYoFWrVjV1KSecb775RpMnT9ayZcvUunXrpi7nhFZdXa3+/fvrsccekySdccYZ2rBhg373u99p7NixTVzdieO///u/9corr+hPf/qT+vTpo/Xr1+v2229X165dmecWjK8UT1CdOnVSZGRkrSu5du/ereTk5Caq6vj061//WkuXLtWKFSvUvXt3b31ycrIOHDigffv2hbQPnuPk5OSwj0FgGw5+Zbhnzx7169dPfr9ffr9f77zzjv793/9dfr9fSUlJzHMD6dKli0455ZSQdb1799aOHTsk/f+5OtTrRnJysvbs2ROyvbKyUnv37mWu/8+UKVN033336aqrrtKpp56qX/3qV7rjjjs0Y8YMScyzKw01r65eTwhcJ6ioqChlZ2dr+fLl3rrq6motX75cAwcObMLKjh9mpl//+tdavHix3n777VofMWdnZ6tVq1Yhc7x582bt2LHDm+OBAwfq008/DXmCL1u2TPHx8bXe+FqqCy64QJ9++qnWr1/vLf3799fo0aO9n5nnhnHOOefUurXJli1blJaWJknKyMhQcnJyyFwXFRXpgw8+CJnrffv2KS8vz2vz9ttvq7q6WgMGDGiEo2j+SkpKFBER+vYaGRmp6upqScyzKw01rwMHDtS7776riooKr82yZcvUq1evo/46URK3hTiRLVy40KKjo+0Pf/iDff7553bLLbdYu3btQq7kQt1uvfVWS0hIsJUrV1p+fr63lJSUeG3Gjx9vqamp9vbbb9tHH31kAwcOtIEDB3rbA7cruPDCC239+vX2t7/9zTp37sztCg4j+CpFM+a5oaxZs8b8fr89+uijtnXrVnvllVcsNjbWFixY4LWZOXOmtWvXzv7yl7/YJ598YpdccknYy+rPOOMM++CDD2zVqlXWs2fPFn+7gmBjx461bt26ebeFeP31161Tp052zz33eG2Y56NTXFxs69ats3Xr1pkke+aZZ2zdunX29ddfm1nDzOu+ffssKSnJfvWrX9mGDRts4cKFFhsby20hcGjPP/+8paamWlRUlJ111ln2z3/+s6lLOm5ICrvMnz/fa1NaWmoTJkyw9u3bW2xsrF166aWWn58f0s/27dtt2LBhFhMTY506dbK77rrLKioqGvloji81Axfz3HD++te/Wt++fS06OtqysrJs7ty5Idurq6vtwQcftKSkJIuOjrYLLrjANm/eHNLmhx9+sKuvvtratm1r8fHxdv3111txcXFjHkazVlRUZJMnT7bU1FRr3bq19ejRw+6///6Q2wwwz0dnxYoVYV+Xx44da2YNN68ff/yxnXvuuRYdHW3dunWzmTNnHnPtPrOgW98CAACgwXEOFwAAgGMELgAAAMcIXAAAAI4RuAAAABwjcAEAADhG4AIAAHCMwAUAAOAYgQsAAMAxAhcAAIBjBC4AAADHCFwAAACOEbgAAAAc+3+MDo86KdpsuQAAAABJRU5ErkJggg==\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Las columnas `eyesight(left)` y `eyesgiht(right)` tienen valores máximos de 9.9 pero la mayoría están entre cero y dos. Vamos a eliminar estos valores, ya que probablemente indican valores faltantes.\n",
+        "\n",
+        "Lo mismo pasa con la variable `triglyceride` y el valor 999.\n",
+        "\n",
+        "En el caso de la variable `Gtp`, hay otras observaciones cercanas al 999, en este caso parece que no es un error y lo vamos a dejar."
+      ],
+      "metadata": {
+        "id": "5V57rKJjwjSv"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Como tenemos muchas observaciones y hay muy pocos valores faltantes, eliminamos las filas con valores faltantes."
+      ],
+      "metadata": {
+        "id": "lLgTet3F88ut"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "data = data.drop(data[data['eyesight(left)']==9.9].index)\n",
+        "data = data.drop(data[data['eyesight(right)']==9.9].index)\n",
+        "data = data.drop(data[data['triglyceride']==999].index)\n",
+        "data.shape"
+      ],
+      "metadata": {
+        "id": "GxKAidL58668",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "d0245421-9cf9-4795-a6d4-1fc73172b22d"
+      },
+      "execution_count": 45,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "(55517, 25)"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 45
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "print(\"Nos hemos quedado con el\", round(data.shape[0] *100 / original_dim[0],2), \"% de observaciones\")"
+      ],
+      "metadata": {
+        "id": "RIDa1isp_o9x",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "d889031f-6216-495b-cedc-8d048fa82753"
+      },
+      "execution_count": 46,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Nos hemos quedado con el 99.69 % de observaciones\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "col = [ 'eyesight(left)', 'eyesight(right)', 'triglyceride']\n",
+        "\n",
+        "for i in col:\n",
+        "  idx = col.index(i)\n",
+        "  ax = plt.subplot(1,3, idx+1)\n",
+        "  ax.hist(data[i])\n",
+        "  ax.set_title(i)\n",
+        "plt.rcParams[\"figure.figsize\"] = (6,2) # hacemos las gráficas más pequeñas\n",
+        "plt.show()\n",
+        "\n",
+        "plt.rcParams[\"figure.figsize\"] = plt.rcParamsDefault[\"figure.figsize\"] # reset valores"
+      ],
+      "metadata": {
+        "id": "Utzb9bkvBjo-",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 452
+        },
+        "outputId": "90f03a71-5a97-4531-ff4d-1d95a9c6ac9b"
+      },
+      "execution_count": 47,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 3 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "### Balanceo del dataset\n",
+        "\n",
+        "En la exploración hemos visto que teníamos mucha más cantidad de observaciones con el valor 0 que con el valor 1 en la variable predictora.\n",
+        "\n",
+        "Deberíamos coger la misma cantidad de datos de las dos clases (smoking=0 vs smoking=1) para no desviar el modelo.\n",
+        "\n",
+        "Vamos a realizar un undersampling."
+      ],
+      "metadata": {
+        "id": "ltBsn6LkP_77"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# undersampling\n",
+        "smoking1 = data[data['smoking']==1]\n",
+        "smoking0 = data[data['smoking']==0]\n",
+        "smoking0 = smoking0.sample(n=len(smoking1), random_state=101)\n",
+        "data = pd.concat([smoking0, smoking1],axis=0)\n",
+        "print(\"Nos hemos quedado con el\", round(data.shape[0] *100 / original_dim[0],2), \"% de observaciones\")"
+      ],
+      "metadata": {
+        "id": "qpjLeB_1QS6p",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "2cdc9e61-ada0-444b-b9ba-9b98d16bc4cc"
+      },
+      "execution_count": 48,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Nos hemos quedado con el 73.25 % de observaciones\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "### Separación variables explicatorias y predictiva"
+      ],
+      "metadata": {
+        "id": "q_47pGhFyW07"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "X = data.iloc[:, :-1]\n",
+        "Y = data.iloc[:, -1]\n",
+        "\n",
+        "print(X.shape)\n",
+        "print(Y.shape)"
+      ],
+      "metadata": {
+        "id": "_T8BxrtW9M26",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "96654d24-744a-4a85-8ed2-60c1cd9de44d"
+      },
+      "execution_count": 49,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "(40792, 24)\n",
+            "(40792,)\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "### División train/test/validation\n",
+        "\n",
+        "Como tenemos un gran número de observaciones, vamos a hacer la validación de `k` con un set de validación en lugar de hacer validación cruzada."
+      ],
+      "metadata": {
+        "id": "Y74sLtK67BSj"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "X0_train, X0_test, y0_train, y_test = train_test_split(X, Y, test_size=0.2, random_state=0)\n",
+        "X1_train, X1_val, y_train, y_val = train_test_split(X0_train, y0_train, test_size=0.2, random_state=0)\n",
+        "\n",
+        "print(\"Observaciones de train:\", X1_train.shape[0]) \n",
+        "print(\"Observaciones de validación:\",X1_val.shape[0])\n",
+        "print(\"Observaciones de test:\", X0_test.shape[0])"
+      ],
+      "metadata": {
+        "id": "N33isve_Rlfl",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "2222fc1b-8ba3-47d0-8f44-f4e1cf1cf24e"
+      },
+      "execution_count": 50,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Observaciones de train: 26106\n",
+            "Observaciones de validación: 6527\n",
+            "Observaciones de test: 8159\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "!!!!!!! FALTA COMPROVAR QUE LES OBSERVACIONES ESTIGUIN BALANDEJADES EN ELS SETS !!!!!!!!! PROVA XI QUADRAT"
+      ],
+      "metadata": {
+        "id": "wK23kGLjDfTI"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "### Normalización"
+      ],
+      "metadata": {
+        "id": "yQYOwLte-UFo"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "transformer = StandardScaler().fit(X1_train)\n",
+        "X_train = transformer.transform(X1_train)\n",
+        "X_val = transformer.transform(X1_val)\n",
+        "X_test = transformer.transform(X0_test)"
+      ],
+      "metadata": {
+        "id": "DTzj118r-USo"
+      },
+      "execution_count": 51,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "### Modelo KNN"
+      ],
+      "metadata": {
+        "id": "HtHmwZOBC3yW"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "#### Entreno del modelo con varias k en el conjunto de validación"
+      ],
+      "metadata": {
+        "id": "Av-PbythOVTV"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "k_list = [1, 10, 50, 100, 200, 1000]\n",
+        "\n",
+        "# Dibujamos los errores de entrenamiento y de test en función del parámetro k\n",
+        "n_tr = X_train.shape[0]\n",
+        "pe_tr = []\n",
+        "pe_val = []\n",
+        "\n",
+        "for k in k_list:\n",
+        "    # creación y entreno del modelo\n",
+        "    KNN_k = KNeighborsClassifier(n_neighbors=k)\n",
+        "    KNN_k.fit(X_train, y_train)\n",
+        "\n",
+        "    # Errores de entrenamiento\n",
+        "    Z_tr = KNN_k.predict(X_train)\n",
+        "    E_tr = Z_tr.flatten()!=y_train\n",
+        "\n",
+        "    # Errores de val\n",
+        "    Z_tst = KNN_k.predict(X_val)\n",
+        "    E_val = Z_tst.flatten()!=y_val\n",
+        "\n",
+        "    # Tasas de error\n",
+        "    pe_tr.append(np.mean(E_tr))\n",
+        "    pe_val.append(np.mean(E_val))\n",
+        "\n",
+        "# buscamos k óptima\n",
+        "k_opt = k_list[np.argmin(pe_val)]\n",
+        "print('El valor óptimo de k es ' + str(k_opt))"
+      ],
+      "metadata": {
+        "id": "rgnTaN5pKzSJ",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "d96b6df5-9468-4004-ce49-d5158fecf03b"
+      },
+      "execution_count": 52,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "El valor óptimo de k es 50\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# graficamos\n",
+        "plt.plot(np.log10(k_list), pe_tr,'b--o',label='Training error')\n",
+        "plt.plot(np.log10(k_list), pe_val,'g--o',label='Validation error')\n",
+        "plt.stem([np.log10(k_opt), np.log10(k_opt)], [0, min(pe_val)],'r-o', label='Optimal k')\n",
+        "plt.xlabel('$log(k)$')\n",
+        "plt.ylabel('Tasa de error')\n",
+        "plt.legend(loc='best')"
+      ],
+      "metadata": {
+        "id": "WtcUYh4kGMb9",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 470
+        },
+        "outputId": "88c755a8-644e-46c4-eaa1-b36b8eef52da"
+      },
+      "execution_count": 53,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "<matplotlib.legend.Legend at 0x7fafc035fe50>"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 53
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "#### Evaluación del modelo con la mejor k"
+      ],
+      "metadata": {
+        "id": "vK80-H2G-nN6"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "clf = KNeighborsClassifier(k_opt)\n",
+        "clf.fit(X_train, y_train)\n",
+        "y_test_pred = clf.predict(X_test)\n",
+        "pe_tst = np.mean(y_test != y_test_pred)\n",
+        "print('Tasa de error', round(pe_tst,2), \"con k = \", k_opt)"
+      ],
+      "metadata": {
+        "id": "mzVyjog_47sv",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "7472a5e5-7f91-4c81-e2f5-5800b64e8310"
+      },
+      "execution_count": 54,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Tasa de error 0.25 con k =  50\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "ConfusionMatrixDisplay.from_estimator(clf, X_test, y_test)"
+      ],
+      "metadata": {
+        "id": "8onYmrSj9ScN",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 466
+        },
+        "outputId": "381746ca-cbe3-41a1-c6cc-15594d312bab"
+      },
+      "execution_count": 55,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "<sklearn.metrics._plot.confusion_matrix.ConfusionMatrixDisplay at 0x7fb0087c48e0>"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 55
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 2 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Modelo Random Forest\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "Fsv0GUMNFEgt"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# entreno modelo sencillo, no buscamos parámetros\n",
+        "rf = RandomForestClassifier(random_state =42)\n",
+        "rf.fit(X_train, y_train)\n",
+        "\n",
+        "pred_tr = rf.predict_proba(X_train)[:,1]\n",
+        "pred_va = rf.predict_proba(X_val)[:,1]\n",
+        "\n",
+        "print(roc_auc_score(y_train,pred_tr))\n",
+        "print(roc_auc_score(y_val,pred_va))"
+      ],
+      "metadata": {
+        "id": "Ltaz16j4F2u2",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "1ab7a1cc-3e3c-4577-a18e-fdba8bb744f7"
+      },
+      "execution_count": 56,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "1.0\n",
+            "0.8801376719537767\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# búsqueda parámetros óptimos con validación cruzada\n",
+        "\n",
+        "param_grid = {'n_estimators' : [50,100,150],\n",
+        "              'max_depth' : [2,5,10]}\n",
+        "clf = GridSearchCV(RandomForestClassifier(random_state = 42), param_grid, cv=2)\n",
+        "clf.fit(X_train, y_train)\n",
+        "\n",
+        "# X_train = transformer.transform(X1_train)\n",
+        "# X_val = transformer.transform(X1_val)\n",
+        "# X_test = transformer.transform(X0_test)\n",
+        "\n",
+        "print(clf.best_params_)\n",
+        "print(clf.best_score_)\n",
+        "print(clf.score(X_test, y_test))\n",
+        "\n",
+        "\n",
+        "X0_train = transformer.transform(X0_train)\n",
+        "\n",
+        "clf.fit(X0_train, y0_train)\n",
+        "print(clf.best_params_)\n",
+        "print(clf.best_score_)\n",
+        "print(clf.score(X_val, y_val))"
+      ],
+      "metadata": {
+        "id": "eORe4Ue2GSce",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "84541473-1bfa-4a56-862a-8a56c75ac652"
+      },
+      "execution_count": 57,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "{'max_depth': 10, 'n_estimators': 50}\n",
+            "0.7743047575270052\n",
+            "0.7668831964701557\n",
+            "{'max_depth': 10, 'n_estimators': 150}\n",
+            "0.7715502456291515\n",
+            "0.7888769725754557\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# búsqueda parámetros óptimos sin validación cruzada\n",
+        "\n",
+        "# Define your parameter grid\n",
+        "param_grid = {\n",
+        "    'n_estimators': [100, 200, 300],\n",
+        "    'max_depth': [None, 5, 10],\n",
+        "    'min_samples_split': [2, 5, 10]\n",
+        "}\n",
+        "\n",
+        "best_score = 0\n",
+        "best_params = {}\n",
+        "\n",
+        "# Create a list of parameter combinations\n",
+        "param_combinations = list(ParameterGrid(param_grid))\n",
+        "\n",
+        "# Define a function to train and evaluate the model for a given parameter combination\n",
+        "def train_and_evaluate(params):\n",
+        "    # Create and fit the Random Forest model with the current parameters\n",
+        "    model = RandomForestClassifier(\n",
+        "        n_estimators=params['n_estimators'],\n",
+        "        max_depth=params['max_depth'],\n",
+        "        min_samples_split=params['min_samples_split']\n",
+        "    )\n",
+        "    model.fit(X_train, y_train)\n",
+        "\n",
+        "    # Make predictions on the holdout validation set\n",
+        "    y_pred = model.predict(X_val)\n",
+        "\n",
+        "    # Calculate accuracy score\n",
+        "    score = accuracy_score(y_val, y_pred)\n",
+        "\n",
+        "    return params, score\n",
+        "\n",
+        "# Parallelize the grid search process\n",
+        "results = Parallel(n_jobs=-1)(delayed(train_and_evaluate)(params) for params in param_combinations)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "8FLqTSVa-8Q2",
+        "outputId": "5501ff1b-4137-4d09-cb34-5ea514220292"
+      },
+      "execution_count": 58,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Best parameters: {'max_depth': None, 'min_samples_split': 2, 'n_estimators': 200}\n",
+            "Best accuracy score: 0.8000612838976559\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Convert the results to a numpy array\n",
+        "param_scores = np.array([(params, score) for params, score in results])\n",
+        "\n",
+        "# Extract the parameter values and scores\n",
+        "parameters = [params for params, _ in param_scores]\n",
+        "scores = [score for _, score in param_scores]\n",
+        "\n",
+        "# Create separate columns for each parameter\n",
+        "df = pd.DataFrame(parameters, columns=['n_estimators', 'max_depth', 'min_samples_split'])\n",
+        "df['Score'] = scores\n",
+        "\n",
+        "# Color the cells based on the 'Score' column\n",
+        "df_styled = df.style.background_gradient(cmap='coolwarm', subset=['Score'])\n",
+        "\n",
+        "# Display the styled DataFrame\n",
+        "display(df_styled)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 896
+        },
+        "id": "cO7JRXktGNV3",
+        "outputId": "b5680119-19a9-420e-e9e8-3b39853cca89"
+      },
+      "execution_count": 59,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<pandas.io.formats.style.Styler at 0x7fafbc6ab160>"
+            ],
+            "text/html": [
+              "<style type=\"text/css\">\n",
+              "#T_0b2e0_row0_col3 {\n",
+              "  background-color: #da5a49;\n",
+              "  color: #f1f1f1;\n",
+              "}\n",
+              "#T_0b2e0_row1_col3 {\n",
+              "  background-color: #b40426;\n",
+              "  color: #f1f1f1;\n",
+              "}\n",
+              "#T_0b2e0_row2_col3 {\n",
+              "  background-color: #d24b40;\n",
+              "  color: #f1f1f1;\n",
+              "}\n",
+              "#T_0b2e0_row3_col3 {\n",
+              "  background-color: #e57058;\n",
+              "  color: #f1f1f1;\n",
+              "}\n",
+              "#T_0b2e0_row4_col3 {\n",
+              "  background-color: #d55042;\n",
+              "  color: #f1f1f1;\n",
+              "}\n",
+              "#T_0b2e0_row5_col3 {\n",
+              "  background-color: #bd1f2d;\n",
+              "  color: #f1f1f1;\n",
+              "}\n",
+              "#T_0b2e0_row6_col3 {\n",
+              "  background-color: #e46e56;\n",
+              "  color: #f1f1f1;\n",
+              "}\n",
+              "#T_0b2e0_row7_col3 {\n",
+              "  background-color: #e16751;\n",
+              "  color: #f1f1f1;\n",
+              "}\n",
+              "#T_0b2e0_row8_col3 {\n",
+              "  background-color: #e36b54;\n",
+              "  color: #f1f1f1;\n",
+              "}\n",
+              "#T_0b2e0_row9_col3, #T_0b2e0_row10_col3 {\n",
+              "  background-color: #3c4ec2;\n",
+              "  color: #f1f1f1;\n",
+              "}\n",
+              "#T_0b2e0_row11_col3 {\n",
+              "  background-color: #3e51c5;\n",
+              "  color: #f1f1f1;\n",
+              "}\n",
+              "#T_0b2e0_row12_col3, #T_0b2e0_row13_col3 {\n",
+              "  background-color: #4257c9;\n",
+              "  color: #f1f1f1;\n",
+              "}\n",
+              "#T_0b2e0_row14_col3 {\n",
+              "  background-color: #4358cb;\n",
+              "  color: #f1f1f1;\n",
+              "}\n",
+              "#T_0b2e0_row15_col3, #T_0b2e0_row17_col3 {\n",
+              "  background-color: #3b4cc0;\n",
+              "  color: #f1f1f1;\n",
+              "}\n",
+              "#T_0b2e0_row16_col3 {\n",
+              "  background-color: #3d50c3;\n",
+              "  color: #f1f1f1;\n",
+              "}\n",
+              "#T_0b2e0_row18_col3, #T_0b2e0_row24_col3, #T_0b2e0_row25_col3 {\n",
+              "  background-color: #8badfd;\n",
+              "  color: #000000;\n",
+              "}\n",
+              "#T_0b2e0_row19_col3 {\n",
+              "  background-color: #89acfd;\n",
+              "  color: #000000;\n",
+              "}\n",
+              "#T_0b2e0_row20_col3 {\n",
+              "  background-color: #8db0fe;\n",
+              "  color: #000000;\n",
+              "}\n",
+              "#T_0b2e0_row21_col3 {\n",
+              "  background-color: #80a3fa;\n",
+              "  color: #f1f1f1;\n",
+              "}\n",
+              "#T_0b2e0_row22_col3, #T_0b2e0_row23_col3 {\n",
+              "  background-color: #85a8fc;\n",
+              "  color: #f1f1f1;\n",
+              "}\n",
+              "#T_0b2e0_row26_col3 {\n",
+              "  background-color: #86a9fc;\n",
+              "  color: #f1f1f1;\n",
+              "}\n",
+              "</style>\n",
+              "<table id=\"T_0b2e0\" class=\"dataframe\">\n",
+              "  <thead>\n",
+              "    <tr>\n",
+              "      <th class=\"blank level0\" >&nbsp;</th>\n",
+              "      <th id=\"T_0b2e0_level0_col0\" class=\"col_heading level0 col0\" >n_estimators</th>\n",
+              "      <th id=\"T_0b2e0_level0_col1\" class=\"col_heading level0 col1\" >max_depth</th>\n",
+              "      <th id=\"T_0b2e0_level0_col2\" class=\"col_heading level0 col2\" >min_samples_split</th>\n",
+              "      <th id=\"T_0b2e0_level0_col3\" class=\"col_heading level0 col3\" >Score</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
+              "      <td id=\"T_0b2e0_row0_col0\" class=\"data row0 col0\" >100</td>\n",
+              "      <td id=\"T_0b2e0_row0_col1\" class=\"data row0 col1\" >nan</td>\n",
+              "      <td id=\"T_0b2e0_row0_col2\" class=\"data row0 col2\" >2</td>\n",
+              "      <td id=\"T_0b2e0_row0_col3\" class=\"data row0 col3\" >0.794239</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
+              "      <td id=\"T_0b2e0_row1_col0\" class=\"data row1 col0\" >200</td>\n",
+              "      <td id=\"T_0b2e0_row1_col1\" class=\"data row1 col1\" >nan</td>\n",
+              "      <td id=\"T_0b2e0_row1_col2\" class=\"data row1 col2\" >2</td>\n",
+              "      <td id=\"T_0b2e0_row1_col3\" class=\"data row1 col3\" >0.800061</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
+              "      <td id=\"T_0b2e0_row2_col0\" class=\"data row2 col0\" >300</td>\n",
+              "      <td id=\"T_0b2e0_row2_col1\" class=\"data row2 col1\" >nan</td>\n",
+              "      <td id=\"T_0b2e0_row2_col2\" class=\"data row2 col2\" >2</td>\n",
+              "      <td id=\"T_0b2e0_row2_col3\" class=\"data row2 col3\" >0.795618</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
+              "      <td id=\"T_0b2e0_row3_col0\" class=\"data row3 col0\" >100</td>\n",
+              "      <td id=\"T_0b2e0_row3_col1\" class=\"data row3 col1\" >nan</td>\n",
+              "      <td id=\"T_0b2e0_row3_col2\" class=\"data row3 col2\" >5</td>\n",
+              "      <td id=\"T_0b2e0_row3_col3\" class=\"data row3 col3\" >0.792094</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
+              "      <td id=\"T_0b2e0_row4_col0\" class=\"data row4 col0\" >200</td>\n",
+              "      <td id=\"T_0b2e0_row4_col1\" class=\"data row4 col1\" >nan</td>\n",
+              "      <td id=\"T_0b2e0_row4_col2\" class=\"data row4 col2\" >5</td>\n",
+              "      <td id=\"T_0b2e0_row4_col3\" class=\"data row4 col3\" >0.795312</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
+              "      <td id=\"T_0b2e0_row5_col0\" class=\"data row5 col0\" >300</td>\n",
+              "      <td id=\"T_0b2e0_row5_col1\" class=\"data row5 col1\" >nan</td>\n",
+              "      <td id=\"T_0b2e0_row5_col2\" class=\"data row5 col2\" >5</td>\n",
+              "      <td id=\"T_0b2e0_row5_col3\" class=\"data row5 col3\" >0.798836</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
+              "      <td id=\"T_0b2e0_row6_col0\" class=\"data row6 col0\" >100</td>\n",
+              "      <td id=\"T_0b2e0_row6_col1\" class=\"data row6 col1\" >nan</td>\n",
+              "      <td id=\"T_0b2e0_row6_col2\" class=\"data row6 col2\" >10</td>\n",
+              "      <td id=\"T_0b2e0_row6_col3\" class=\"data row6 col3\" >0.792401</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
+              "      <td id=\"T_0b2e0_row7_col0\" class=\"data row7 col0\" >200</td>\n",
+              "      <td id=\"T_0b2e0_row7_col1\" class=\"data row7 col1\" >nan</td>\n",
+              "      <td id=\"T_0b2e0_row7_col2\" class=\"data row7 col2\" >10</td>\n",
+              "      <td id=\"T_0b2e0_row7_col3\" class=\"data row7 col3\" >0.793167</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
+              "      <td id=\"T_0b2e0_row8_col0\" class=\"data row8 col0\" >300</td>\n",
+              "      <td id=\"T_0b2e0_row8_col1\" class=\"data row8 col1\" >nan</td>\n",
+              "      <td id=\"T_0b2e0_row8_col2\" class=\"data row8 col2\" >10</td>\n",
+              "      <td id=\"T_0b2e0_row8_col3\" class=\"data row8 col3\" >0.792707</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row9\" class=\"row_heading level0 row9\" >9</th>\n",
+              "      <td id=\"T_0b2e0_row9_col0\" class=\"data row9 col0\" >100</td>\n",
+              "      <td id=\"T_0b2e0_row9_col1\" class=\"data row9 col1\" >5.000000</td>\n",
+              "      <td id=\"T_0b2e0_row9_col2\" class=\"data row9 col2\" >2</td>\n",
+              "      <td id=\"T_0b2e0_row9_col3\" class=\"data row9 col3\" >0.750421</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row10\" class=\"row_heading level0 row10\" >10</th>\n",
+              "      <td id=\"T_0b2e0_row10_col0\" class=\"data row10 col0\" >200</td>\n",
+              "      <td id=\"T_0b2e0_row10_col1\" class=\"data row10 col1\" >5.000000</td>\n",
+              "      <td id=\"T_0b2e0_row10_col2\" class=\"data row10 col2\" >2</td>\n",
+              "      <td id=\"T_0b2e0_row10_col3\" class=\"data row10 col3\" >0.750421</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row11\" class=\"row_heading level0 row11\" >11</th>\n",
+              "      <td id=\"T_0b2e0_row11_col0\" class=\"data row11 col0\" >300</td>\n",
+              "      <td id=\"T_0b2e0_row11_col1\" class=\"data row11 col1\" >5.000000</td>\n",
+              "      <td id=\"T_0b2e0_row11_col2\" class=\"data row11 col2\" >2</td>\n",
+              "      <td id=\"T_0b2e0_row11_col3\" class=\"data row11 col3\" >0.750728</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row12\" class=\"row_heading level0 row12\" >12</th>\n",
+              "      <td id=\"T_0b2e0_row12_col0\" class=\"data row12 col0\" >100</td>\n",
+              "      <td id=\"T_0b2e0_row12_col1\" class=\"data row12 col1\" >5.000000</td>\n",
+              "      <td id=\"T_0b2e0_row12_col2\" class=\"data row12 col2\" >5</td>\n",
+              "      <td id=\"T_0b2e0_row12_col3\" class=\"data row12 col3\" >0.751341</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row13\" class=\"row_heading level0 row13\" >13</th>\n",
+              "      <td id=\"T_0b2e0_row13_col0\" class=\"data row13 col0\" >200</td>\n",
+              "      <td id=\"T_0b2e0_row13_col1\" class=\"data row13 col1\" >5.000000</td>\n",
+              "      <td id=\"T_0b2e0_row13_col2\" class=\"data row13 col2\" >5</td>\n",
+              "      <td id=\"T_0b2e0_row13_col3\" class=\"data row13 col3\" >0.751341</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row14\" class=\"row_heading level0 row14\" >14</th>\n",
+              "      <td id=\"T_0b2e0_row14_col0\" class=\"data row14 col0\" >300</td>\n",
+              "      <td id=\"T_0b2e0_row14_col1\" class=\"data row14 col1\" >5.000000</td>\n",
+              "      <td id=\"T_0b2e0_row14_col2\" class=\"data row14 col2\" >5</td>\n",
+              "      <td id=\"T_0b2e0_row14_col3\" class=\"data row14 col3\" >0.751494</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row15\" class=\"row_heading level0 row15\" >15</th>\n",
+              "      <td id=\"T_0b2e0_row15_col0\" class=\"data row15 col0\" >100</td>\n",
+              "      <td id=\"T_0b2e0_row15_col1\" class=\"data row15 col1\" >5.000000</td>\n",
+              "      <td id=\"T_0b2e0_row15_col2\" class=\"data row15 col2\" >10</td>\n",
+              "      <td id=\"T_0b2e0_row15_col3\" class=\"data row15 col3\" >0.750115</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row16\" class=\"row_heading level0 row16\" >16</th>\n",
+              "      <td id=\"T_0b2e0_row16_col0\" class=\"data row16 col0\" >200</td>\n",
+              "      <td id=\"T_0b2e0_row16_col1\" class=\"data row16 col1\" >5.000000</td>\n",
+              "      <td id=\"T_0b2e0_row16_col2\" class=\"data row16 col2\" >10</td>\n",
+              "      <td id=\"T_0b2e0_row16_col3\" class=\"data row16 col3\" >0.750575</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row17\" class=\"row_heading level0 row17\" >17</th>\n",
+              "      <td id=\"T_0b2e0_row17_col0\" class=\"data row17 col0\" >300</td>\n",
+              "      <td id=\"T_0b2e0_row17_col1\" class=\"data row17 col1\" >5.000000</td>\n",
+              "      <td id=\"T_0b2e0_row17_col2\" class=\"data row17 col2\" >10</td>\n",
+              "      <td id=\"T_0b2e0_row17_col3\" class=\"data row17 col3\" >0.750268</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row18\" class=\"row_heading level0 row18\" >18</th>\n",
+              "      <td id=\"T_0b2e0_row18_col0\" class=\"data row18 col0\" >100</td>\n",
+              "      <td id=\"T_0b2e0_row18_col1\" class=\"data row18 col1\" >10.000000</td>\n",
+              "      <td id=\"T_0b2e0_row18_col2\" class=\"data row18 col2\" >2</td>\n",
+              "      <td id=\"T_0b2e0_row18_col3\" class=\"data row18 col3\" >0.762218</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row19\" class=\"row_heading level0 row19\" >19</th>\n",
+              "      <td id=\"T_0b2e0_row19_col0\" class=\"data row19 col0\" >200</td>\n",
+              "      <td id=\"T_0b2e0_row19_col1\" class=\"data row19 col1\" >10.000000</td>\n",
+              "      <td id=\"T_0b2e0_row19_col2\" class=\"data row19 col2\" >2</td>\n",
+              "      <td id=\"T_0b2e0_row19_col3\" class=\"data row19 col3\" >0.762065</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row20\" class=\"row_heading level0 row20\" >20</th>\n",
+              "      <td id=\"T_0b2e0_row20_col0\" class=\"data row20 col0\" >300</td>\n",
+              "      <td id=\"T_0b2e0_row20_col1\" class=\"data row20 col1\" >10.000000</td>\n",
+              "      <td id=\"T_0b2e0_row20_col2\" class=\"data row20 col2\" >2</td>\n",
+              "      <td id=\"T_0b2e0_row20_col3\" class=\"data row20 col3\" >0.762678</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row21\" class=\"row_heading level0 row21\" >21</th>\n",
+              "      <td id=\"T_0b2e0_row21_col0\" class=\"data row21 col0\" >100</td>\n",
+              "      <td id=\"T_0b2e0_row21_col1\" class=\"data row21 col1\" >10.000000</td>\n",
+              "      <td id=\"T_0b2e0_row21_col2\" class=\"data row21 col2\" >5</td>\n",
+              "      <td id=\"T_0b2e0_row21_col3\" class=\"data row21 col3\" >0.760686</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row22\" class=\"row_heading level0 row22\" >22</th>\n",
+              "      <td id=\"T_0b2e0_row22_col0\" class=\"data row22 col0\" >200</td>\n",
+              "      <td id=\"T_0b2e0_row22_col1\" class=\"data row22 col1\" >10.000000</td>\n",
+              "      <td id=\"T_0b2e0_row22_col2\" class=\"data row22 col2\" >5</td>\n",
+              "      <td id=\"T_0b2e0_row22_col3\" class=\"data row22 col3\" >0.761606</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row23\" class=\"row_heading level0 row23\" >23</th>\n",
+              "      <td id=\"T_0b2e0_row23_col0\" class=\"data row23 col0\" >300</td>\n",
+              "      <td id=\"T_0b2e0_row23_col1\" class=\"data row23 col1\" >10.000000</td>\n",
+              "      <td id=\"T_0b2e0_row23_col2\" class=\"data row23 col2\" >5</td>\n",
+              "      <td id=\"T_0b2e0_row23_col3\" class=\"data row23 col3\" >0.761606</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row24\" class=\"row_heading level0 row24\" >24</th>\n",
+              "      <td id=\"T_0b2e0_row24_col0\" class=\"data row24 col0\" >100</td>\n",
+              "      <td id=\"T_0b2e0_row24_col1\" class=\"data row24 col1\" >10.000000</td>\n",
+              "      <td id=\"T_0b2e0_row24_col2\" class=\"data row24 col2\" >10</td>\n",
+              "      <td id=\"T_0b2e0_row24_col3\" class=\"data row24 col3\" >0.762372</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row25\" class=\"row_heading level0 row25\" >25</th>\n",
+              "      <td id=\"T_0b2e0_row25_col0\" class=\"data row25 col0\" >200</td>\n",
+              "      <td id=\"T_0b2e0_row25_col1\" class=\"data row25 col1\" >10.000000</td>\n",
+              "      <td id=\"T_0b2e0_row25_col2\" class=\"data row25 col2\" >10</td>\n",
+              "      <td id=\"T_0b2e0_row25_col3\" class=\"data row25 col3\" >0.762218</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th id=\"T_0b2e0_level0_row26\" class=\"row_heading level0 row26\" >26</th>\n",
+              "      <td id=\"T_0b2e0_row26_col0\" class=\"data row26 col0\" >300</td>\n",
+              "      <td id=\"T_0b2e0_row26_col1\" class=\"data row26 col1\" >10.000000</td>\n",
+              "      <td id=\"T_0b2e0_row26_col2\" class=\"data row26 col2\" >10</td>\n",
+              "      <td id=\"T_0b2e0_row26_col3\" class=\"data row26 col3\" >0.761759</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n"
+            ]
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Iterate over the results and find the best parameters\n",
+        "for params, score in results:\n",
+        "    if score > best_score:\n",
+        "        best_score = score\n",
+        "        best_params = params\n",
+        "\n",
+        "print(\"Best parameters:\", best_params)\n",
+        "print(\"Best accuracy score:\", best_score)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "s0EG7nQw9WIP",
+        "outputId": "52ed8c79-e87e-4670-b4eb-e5c866ce335b"
+      },
+      "execution_count": 63,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Best parameters: {'max_depth': None, 'min_samples_split': 2, 'n_estimators': 200}\n",
+            "Best accuracy score: 0.8000612838976559\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Evaluación mejor modelo Random forest"
+      ],
+      "metadata": {
+        "id": "kxNfpWgLwWVV"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Initialize and train the random forest model with the best parameters\n",
+        "model = RandomForestClassifier(**best_params)\n",
+        "model.fit(X_train, y_train)\n",
+        "\n",
+        "# Make predictions on the test set\n",
+        "y_pred = model.predict(X_test)\n",
+        "\n",
+        "# Evaluate the accuracy of the model on the test set\n",
+        "print(\"Best parameters:\", best_params)\n",
+        "print(\"Accuracy on test set:\", accuracy_score(y_test, y_pred))"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "q34iw-DGH4pf",
+        "outputId": "a66b6a9c-24e4-4e12-ef07-39b4ce29589f"
+      },
+      "execution_count": 62,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Best parameters: {'max_depth': None, 'min_samples_split': 2, 'n_estimators': 200}\n",
+            "Accuracy on test set: 0.8061036891775953\n"
+          ]
+        }
+      ]
+    }
+  ]
+}
\ No newline at end of file